{"aliases": [], "authors": ["Toby Jia-Jun Li", "Marissa Radensky", "Justin Jia", "Kirielle Singarajah", "Tom M. Mitchell", "Brad A. Myers"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4cef465f53abcbaad50c83f24e0ce54fb7f23390955e9f7e5592ec0b8287839e", "submitted_at": "2019-08-30T18:35:01Z", "updated_at": "2020-01-07T00:57:53Z", "version": 2, "versioned_url": "https://arxiv.org/abs/1909.00031v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T07:57:26Z", "role": "primary", "sha256": "3e89566cdb4521a8b3b0d99c514c3401645eda5b5c0de9720eb726b1ffe0a11f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=1511.03745%2C1602.02261%2C1809.04860%2C1811.06521%2C1811.07871%2C1812.03426%2C1901.11528%2C1909.00031%2C1912.03098%2C2003.00431%2C2004.14973%2C2006.16241%2C2007.04428%2C2010.09670%2C2010.12083%2C2012.12350%2C2104.08244%2C2105.11941%2C2106.09422%2C2106.13500%2C2107.05911%2C2108.03298%2C2108.05308%2C2110.10661%2C2201.04100%2C2201.11676%2C2203.10897%2C2204.05239%2C2205.10816%2C2206.08853%2C2206.12839%2C2206.15407%2C2208.06032%2C2208.08080%2C2209.14981%2C2210.01379%2C2210.03735%2C2210.08073%2C2210.10275%2C2210.11435%2C2211.07912%2C2211.09527%2C2212.13326%2C2301.10677%2C2301.13779%2C2302.12173%2C2303.00001%2C2303.11366%2C2303.12027%2C2304.03442&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:11:46Z", "role": "primary", "sha256": "ee42fc28e088432e79837641c310dbd2d72f260a2a01d86f5f7f8b9c1b544a39", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/1909.00031v2"}], "id": "arxiv:1909.00031", "identifiers": {"arxiv": "1909.00031"}, "kind": "paper", "last_verified_at": "2026-10-17T09:11:46Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/1909.00031"}], "name": "Interactive Task and Concept Learning from Natural Language Instructions and GUI Demonstrations", "notes": "Reviewed against the exact-version official arXiv abstract page; its normalized abstract SHA-256 matches the retained bibliographic snapshot. The original API response body was not locally available for this review. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2019-08-30", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces PUMICE, an agent that learns mobile-app procedures and conditional concepts through natural-language conversation and GUI demonstrations, recursively resolving ambiguous instructions with users.", "topics": ["human-in-the-loop", "mobile-navigation", "imitation-learning"], "updated_at": "2020-01-07", "url": "https://arxiv.org/abs/1909.00031"}
{"aliases": [], "authors": ["Yang Li", "Jiacong He", "Xin Zhou", "Yuan Zhang", "Jason Baldridge"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3af7b45455ffbd616e8cdf5612b19275ecb7bf07b1065af9f5b724ae19e96fb4", "submitted_at": "2020-05-07T21:41:40Z", "updated_at": "2020-06-05T02:11:56Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2005.03776v2"}, "publication": {"authors": ["Yang Li", "Jiacong He", "Xin Zhou", "Yuan Zhang", "Jason Baldridge"], "date_basis": "Explicit publisher metadata: 2020/7; precision=month.", "date_parts": [2020, 7], "doi": "10.18653/v1/2020.acl-main.729", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2020.acl-main.729/"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "8198-8210", "pdf_url": "https://aclanthology.org/2020.acl-main.729.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Mapping Natural Language Instructions to Mobile UI Action Sequences", "type": "conference-paper", "url": "https://aclanthology.org/2020.acl-main.729/", "venue": "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", "volume": null}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:48+00:00", "role": "primary", "sha256": "c196294e19378d08d71a7cfd41c2e368f5a6b49ee7c3601257537b9ae5c42add", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2020.acl-main.729/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}], "id": "arxiv:2005.03776", "identifiers": {"arxiv": "2005.03776"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:20Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2005.03776"}, {"rel": "publication", "url": "https://aclanthology.org/2020.acl-main.729/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2020.acl-main.729.pdf"}], "name": "Mapping Natural Language Instructions to Mobile UI Action Sequences", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2020-05-07", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces PIXELHELP for predicting mobile UI action sequences from instructions, together with action-phrase annotations and synthetic UI action descriptions for training. Separate Transformers extract instruction steps and ground object descriptions using interface content and screen position.", "topics": ["mobile-navigation", "grounding", "data-generation", "action-prediction"], "updated_at": "2020-06-05", "url": "https://arxiv.org/abs/2005.03776"}
{"aliases": [], "authors": ["Andrea Burns", "Deniz Arsan", "Sanjna Agrawal", "Ranjitha Kumar", "Kate Saenko", "Bryan A. Plummer"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1687369e31b0ad3632381d4a46b1d555c2e2ed1d6504e9c1b63006dd29f3445e", "submitted_at": "2022-02-04T18:51:50Z", "updated_at": "2022-08-15T00:24:24Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2202.02312v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}], "id": "arxiv:2202.02312", "identifiers": {"arxiv": "2202.02312"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:20Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2202.02312"}], "name": "A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2022-02-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces MoTIF mobile-app interactions with feasible and infeasible commands, feasibility explanations, and follow-up questions for ambiguous requests.", "topics": ["mobile-navigation", "human-in-the-loop", "evaluation"], "updated_at": "2022-08-15", "url": "https://arxiv.org/abs/2202.02312"}
{"aliases": [], "authors": ["Liangtai Sun", "Xingyu Chen", "Lu Chen", "Tianle Dai", "Zichen Zhu", "Kai Yu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fbe2a4ece7ef72dfa008740991a5c46d9ab4b9de73f3de02f5dabcee2a5c1aa5", "submitted_at": "2022-05-23T04:05:37Z", "updated_at": "2022-11-24T06:34:43Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2205.11029v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}], "id": "arxiv:2205.11029", "identifiers": {"arxiv": "2205.11029"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:20Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2205.11029"}], "name": "META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2022-05-23", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces GUI-based task-oriented dialogue and a dataset pairing mobile-interface operations with conversational responses.", "topics": ["mobile-navigation", "human-in-the-loop"], "updated_at": "2022-11-24", "url": "https://arxiv.org/abs/2205.11029"}
{"aliases": [], "authors": ["Bryan Wang", "Gang Li", "Yang Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "65813c1784ba00e354aff4e38796b1bdc8e9b691cba9dd56b8232b5d86555d1b", "submitted_at": "2022-09-18T20:58:39Z", "updated_at": "2023-02-17T21:24:09Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2209.08655v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}], "id": "arxiv:2209.08655", "identifiers": {"arxiv": "2209.08655"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:20Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2209.08655"}], "name": "Enabling Conversational Interaction with Mobile UI using Large Language Models", "notes": "Reviewed against the retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2022-09-18", "relations": [], "review_status": "curated", "scope": "core", "summary": "Studies few-shot prompting of a single language model for four mobile-UI interaction tasks, aiming to support conversational interface use without a separate trained model for each task.", "topics": ["mobile-navigation", "screen-understanding", "training-free"], "updated_at": "2023-02-17", "url": "https://arxiv.org/abs/2209.08655"}
{"aliases": [], "authors": ["Sagar Gubbi Venkatesh", "Partha Talukdar", "Srini Narayanan"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "52319819402cec76a69c0bb513f3a7000053208ddd9d2a8c675e055422402fbe", "submitted_at": "2022-11-14T18:36:19Z", "updated_at": "2023-05-23T16:08:10Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2211.07615v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}], "id": "arxiv:2211.07615", "identifiers": {"arxiv": "2211.07615"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:20Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2211.07615"}], "name": "UGIF: UI Grounded Instruction Following", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2022-11-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces multilingual smartphone instruction-following data and a pipeline that retrieves help instructions and maps them to UI actions.", "topics": ["mobile-navigation", "grounding"], "updated_at": "2023-05-23", "url": "https://arxiv.org/abs/2211.07615"}
{"aliases": [], "authors": ["Hao Wen", "Hongming Wang", "Jiaxuan Liu", "Yuanchun Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "420c9005fd0c687c27c758da70ef05a60b3b2d9b9efbf91a5d7661bf893a8b09", "submitted_at": "2023-04-14T11:31:56Z", "updated_at": "2024-01-07T08:23:47Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2304.07061v5"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}], "id": "arxiv:2304.07061", "identifiers": {"arxiv": "2304.07061"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:20Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2304.07061"}], "name": "DroidBot-GPT: GPT-powered UI Automation for Android", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2023-04-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "Transforms Android UI states and available actions into language prompts for an LLM to choose and execute task steps.", "topics": ["mobile-navigation", "automation"], "updated_at": "2024-01-07", "url": "https://arxiv.org/abs/2304.07061"}
{"aliases": [], "authors": ["Christopher Rawles", "Alice Li", "Daniel Rodriguez", "Oriana Riva", "Timothy Lillicrap"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "def4616f7cb13fe839e500c4b3171eafbe37b155b5d14301137806d6a5cde939", "submitted_at": "2023-07-19T15:57:24Z", "updated_at": "2023-10-27T14:24:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2307.10088v2"}, "publication": {"authors": ["Christopher Rawles", "Alice Li", "Daniel Rodriguez", "Oriana Riva", "Timothy Lillicrap"], "date_basis": "Explicit publisher citation_publication_date: 2023-12-15. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2023, 12, 15], "doi": "10.52202/075280-2609", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "59708-59728", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2023/file/bbbb6308b402fe909c39dd29950c32e0-Paper-Datasets_and_Benchmarks.pdf", "publisher": null, "series": null, "title": "AndroidInTheWild: A Large-Scale Dataset For Android Device Control", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html", "venue": "Advances in Neural Information Processing Systems", "volume": "36"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:10:02Z", "role": "primary", "sha256": "7fa75eae1a17878ef28414f64e1c46cc83539008f2644331b762248ec96efce5", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue", "details.publication.volume"], "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:20Z", "role": "primary", "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"}], "id": "arxiv:2307.10088", "identifiers": {"arxiv": "2307.10088"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:20Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2307.10088"}, {"rel": "publication", "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html"}, {"rel": "publication_pdf", "url": "https://proceedings.neurips.cc/paper_files/paper/2023/file/bbbb6308b402fe909c39dd29950c32e0-Paper-Datasets_and_Benchmarks.pdf"}], "name": "Android in the Wild: A Large-Scale Dataset for Android Device Control", "notes": "Annotation reviewed against the primary abstract. Original dataset scale and experimental results are not independently reproduced.", "published_at": "2023-07-19", "relations": [], "review_status": "curated", "scope": "core", "summary": "Collects Android interaction demonstrations with screens, actions, and instructions across device and platform variations for robustness evaluation.", "topics": ["data-generation", "mobile-navigation", "evaluation"], "updated_at": "2023-10-27", "url": "https://arxiv.org/abs/2307.10088"}
{"aliases": [], "authors": ["Hao Wen", "Yuanchun Li", "Guohong Liu", "Shanhui Zhao", "Tao Yu", "Toby Jia-Jun Li", "Shiqi Jiang", "Yunhao Liu", "Yaqin Zhang", "Yunxin Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6a103fe10850a39d25bbb2b4a9ea0593d686938243bb912c674fd906e754c1fb", "submitted_at": "2023-08-29T13:02:30Z", "updated_at": "2024-03-09T09:38:51Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2308.15272v4"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2308.15272", "identifiers": {"arxiv": "2308.15272"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2308.15272"}], "name": "AutoDroid: LLM-powered Task Automation in Android", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2023-08-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines language-model reasoning with app analysis, UI representations, and exploration-derived memory for Android task automation.", "topics": ["mobile-navigation", "memory"], "updated_at": "2024-03-09", "url": "https://arxiv.org/abs/2308.15272"}
{"aliases": [], "authors": ["Zhuosheng Zhang", "Aston Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6d9cff1ece6115e87b7a9032f5720deb49694fbf570bea1f152018c4fa80d981", "submitted_at": "2023-09-20T16:12:32Z", "updated_at": "2024-06-07T04:52:29Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2309.11436v4"}, "publication": {"authors": ["Zhuosheng Zhang", "Aston Zhang"], "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 8], "doi": "10.18653/v1/2024.findings-acl.186", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-acl.186/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "3132-3149", "pdf_url": "https://aclanthology.org/2024.findings-acl.186.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "You Only Look at Screens: Multimodal Chain-of-Action Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-acl.186/", "venue": "Findings of the Association for Computational Linguistics: ACL 2024", "volume": null}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:48Z", "role": "primary", "sha256": "80fb0185db71f714655c22f5e1eb46d890c045b8af09c49d1b5ee2e0b6911478", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2024.findings-acl.186/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2309.11436", "identifiers": {"arxiv": "2309.11436"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2309.11436"}, {"rel": "publication", "url": "https://aclanthology.org/2024.findings-acl.186/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2024.findings-acl.186.pdf"}], "name": "You Only Look at Screens: Multimodal Chain-of-Action Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2023-09-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Auto-GUI, a screenshot-based agent using previous actions and future action plans to guide device interaction.", "topics": ["mobile-navigation", "planning"], "updated_at": "2024-06-07", "url": "https://arxiv.org/abs/2309.11436"}
{"aliases": [], "authors": ["An Yan", "Zhengyuan Yang", "Wanrong Zhu", "Kevin Lin", "Linjie Li", "Jianfeng Wang", "Jianwei Yang", "Yiwu Zhong", "Julian McAuley", "Jianfeng Gao", "Zicheng Liu", "Lijuan Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ebe6ff09f876b81d033a064301a1c23e3c141d2a1ad0d7a5df91e729377fcd3b", "submitted_at": "2023-11-13T18:53:37Z", "updated_at": "2023-11-13T18:53:37Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2311.07562v1"}}, "environments": ["ios", "android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2311.07562", "identifiers": {"arxiv": "2311.07562"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2311.07562"}], "name": "GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2023-11-13", "relations": [], "review_status": "curated", "scope": "core", "summary": "Studies MM-Navigator, a multimodal agent that interprets smartphone screenshots and predicts localized actions without task-specific training.", "topics": ["mobile-navigation", "grounding"], "updated_at": "2023-11-13", "url": "https://arxiv.org/abs/2311.07562"}
{"aliases": [], "authors": ["Sunjae Lee", "Junyoung Choi", "Jungjae Lee", "Munim Hasan Wasi", "Hojun Choi", "Steven Y. Ko", "Sangeun Oh", "Insik Shin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b9b6f10b17513f565a13e035802d8bd681b5b0d468ba000df1427a8d59591e2c", "submitted_at": "2023-12-04T06:13:35Z", "updated_at": "2024-10-16T08:15:53Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2312.03003v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2312.03003", "identifiers": {"arxiv": "2312.03003"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2312.03003"}], "name": "Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation", "notes": "Reviewed against the retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2023-12-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces MobileGPT, which organizes mobile-app experience into reusable subtasks using an explore, select, derive, and recall cycle. Its memory supports learning task procedures and adapting them to new contexts.", "topics": ["mobile-navigation", "memory", "planning"], "updated_at": "2024-10-16", "url": "https://arxiv.org/abs/2312.03003"}
{"aliases": [], "authors": ["Yanchu Guan", "Dong Wang", "Zhixuan Chu", "Shiyu Wang", "Feiyue Ni", "Ruihua Song", "Longfei Li", "Jinjie Gu", "Chenyi Zhuang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "598c8c30348d454c638944c932dd55355b5d3ecda6eb6f3910a27fffcab9622a", "submitted_at": "2023-12-04T07:51:58Z", "updated_at": "2023-12-04T07:51:58Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2312.06677v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2312.06677", "identifiers": {"arxiv": "2312.06677"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2312.06677"}], "name": "Intelligent Virtual Assistants with LLM-based Process Automation", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental findings and artifact availability have not been independently reproduced. The abstract names Alipay but does not establish Android or iOS specifically.", "published_at": "2023-12-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents LLMPA, a mobile process-automation architecture that decomposes requests, identifies interface elements, predicts actions and checks errors. Demonstrations evaluate multistep operations in Alipay.", "topics": ["mobile-navigation", "planning", "automation"], "updated_at": "2023-12-04", "url": "https://arxiv.org/abs/2312.06677"}
{"aliases": [], "authors": ["Yunpeng Song", "Yiheng Bian", "Yongtao Tang", "Guiyu Ma", "Zhongmin Cai"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "df1390eab35db18dedaf135ddbbc9fdfcacbc9a70c51ec2609cf331cc05e06bd", "submitted_at": "2023-12-18T13:35:46Z", "updated_at": "2024-07-29T14:52:38Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2312.11190v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}], "id": "arxiv:2312.11190", "identifiers": {"arxiv": "2312.11190"}, "kind": "paper", "last_verified_at": "2026-10-16T06:45:04Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2312.11190"}], "name": "VisionTasker: Mobile Task Automation Using Vision Based UI Understanding and LLM Task Planning", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2023-12-18", "relations": [], "review_status": "curated", "scope": "core", "summary": "VisionTasker converts screenshots into textual UI interpretations and presents one interface at a time to an LLM planner for action selection. It evaluates visual representations and execution of 147 tasks on an Android smartphone, including integration with programming by demonstration.", "topics": ["screen-understanding", "planning", "mobile-navigation"], "updated_at": "2024-07-29", "url": "https://arxiv.org/abs/2312.11190"}
{"aliases": [], "authors": ["Chi Zhang", "Zhao Yang", "Jiaxuan Liu", "Yanda Li", "Yucheng Han", "Xin Chen", "Zebiao Huang", "Bin Fu", "Gang Yu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "61e54d83304755ce89c2ab69f7bb93a7fdc4d68cb5182daad9b5210f809d7ae1", "submitted_at": "2023-12-21T11:52:45Z", "updated_at": "2026-07-05T07:51:04Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2312.13771v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2312.13771", "identifiers": {"arxiv": "2312.13771"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2312.13771"}], "name": "AppAgent: Multimodal Agents as Smartphone Users", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2023-12-21", "relations": [], "review_status": "curated", "scope": "core", "summary": "Builds app knowledge through exploration or human demonstrations and uses it to guide multimodal smartphone interactions.", "topics": ["mobile-navigation", "memory"], "updated_at": "2026-07-05", "url": "https://arxiv.org/abs/2312.13771"}
{"aliases": [], "authors": ["Lihang Pan", "Bowen Wang", "Chun Yu", "Yuxuan Chen", "Xiangyu Zhang", "Yuanchun Shi"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0f592712517da90bfeb807ab445034c3974b406e0ed6b4933fbd19078984b9b8", "submitted_at": "2023-12-26T14:20:36Z", "updated_at": "2023-12-26T14:20:36Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2312.16062v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2312.16062", "identifiers": {"arxiv": "2312.16062"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2312.16062"}], "name": "AutoTask: Executing Arbitrary Voice Commands by Exploring and Learning from Mobile GUI", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2023-12-26", "relations": [], "review_status": "curated", "scope": "core", "summary": "Executes voice-requested mobile tasks through GUI exploration, backtracking, and accumulated interaction experience.", "topics": ["mobile-navigation", "memory"], "updated_at": "2023-12-26", "url": "https://arxiv.org/abs/2312.16062"}
{"aliases": [], "authors": ["Tinghe Ding"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9b8aaa2bccafd7f41802e5b7c25bc98f78307f77aeb36b7c75c57ef0f8e583a1", "submitted_at": "2024-01-04T03:44:42Z", "updated_at": "2024-01-17T06:35:45Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2401.04124v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2401.04124", "identifiers": {"arxiv": "2401.04124"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2401.04124"}], "name": "MobileAgent: enhancing mobile control via human-machine interaction and SOP integration", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-01-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines operating-procedure context with user interaction to guide mobile task automation and handle personalized or sensitive requests.", "topics": ["mobile-navigation", "workflow", "human-in-the-loop"], "updated_at": "2024-01-17", "url": "https://arxiv.org/abs/2401.04124"}
{"aliases": [], "authors": ["Minh Duc Vu", "Han Wang", "Zhuang Li", "Jieshan Chen", "Shengdong Zhao", "Zhenchang Xing", "Chunyang Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a1c95264a931b10a57ee4b364498e2d2795abaf9a3e89096a0f29d2408174693", "submitted_at": "2024-01-25T16:02:56Z", "updated_at": "2024-08-14T00:48:43Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2401.14268v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2401.14268", "identifiers": {"arxiv": "2401.14268"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2401.14268"}], "name": "GPTVoiceTasker: Advancing Multi-step Mobile Task Efficiency Through Dynamic Interface Exploration and Learning", "notes": "Reviewed against the retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2024-01-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces GPTVoiceTasker, a mobile assistant that interprets user commands, executes device interactions, and learns from prior commands to streamline later task execution. The work includes a user study of task efficiency.", "topics": ["mobile-navigation", "human-in-the-loop", "memory"], "updated_at": "2024-08-14", "url": "https://arxiv.org/abs/2401.14268"}
{"aliases": [], "authors": ["Junyang Wang", "Haiyang Xu", "Jiabo Ye", "Ming Yan", "Weizhou Shen", "Ji Zhang", "Fei Huang", "Jitao Sang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "81ac041a3e5f98bfc23c91f768b32ad7adc3f28d8c9d55a285bb29906c8b5a9c", "submitted_at": "2024-01-29T13:46:37Z", "updated_at": "2024-04-18T06:53:38Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2401.16158v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2401.16158", "identifiers": {"arxiv": "2401.16158"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2401.16158"}], "name": "Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception", "notes": "Summary and topic tags reviewed against the primary abstract. Reported experiments, task counts, and artifact availability are not independently reproduced.", "published_at": "2024-01-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses visual perception tools and task decomposition to operate mobile applications without relying on app interface metadata.", "topics": ["mobile-navigation", "planning"], "updated_at": "2024-04-18", "url": "https://arxiv.org/abs/2401.16158"}
{"aliases": [], "authors": ["Xinbei Ma", "Zhuosheng Zhang", "Hai Zhao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "98930b10832d8169bdc60620f882b4b8f753440979c8e9a8de167b12d38d7060", "submitted_at": "2024-02-19T08:29:03Z", "updated_at": "2024-06-02T13:25:05Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2402.11941v3"}, "publication": {"authors": ["Xinbei Ma", "Zhuosheng Zhang", "Hai Zhao (赵海)"], "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 8], "doi": "10.18653/v1/2024.findings-acl.539", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-acl.539"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "9097-9110", "pdf_url": "https://aclanthology.org/2024.findings-acl.539.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-acl.539", "venue": "Findings of the Association for Computational Linguistics: ACL 2024", "volume": null}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:49Z", "role": "primary", "sha256": "022e2ca49699ec713f11eec442b2139fc0ce4d075f0812f88844289749f13d6c", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2024.findings-acl.539"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}], "id": "arxiv:2402.11941", "identifiers": {"arxiv": "2402.11941"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2402.11941"}, {"rel": "publication", "url": "https://aclanthology.org/2024.findings-acl.539"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2024.findings-acl.539.pdf"}], "name": "CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-02-19", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines screenshots, layout information, and action history with a factored action predictor for smartphone automation.", "topics": ["mobile-navigation", "screen-understanding"], "updated_at": "2024-06-02", "url": "https://arxiv.org/abs/2402.11941"}
{"aliases": [], "authors": ["Jiwen Zhang", "Jihao Wu", "Yihua Teng", "Minghui Liao", "Nuo Xu", "Xiao Xiao", "Zhongyu Wei", "Duyu Tang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4de9e7d68aa8450cab65ecb300524e85b1d2b2a91d58fecef370deceaba64b1e", "submitted_at": "2024-03-05T07:09:35Z", "updated_at": "2024-07-13T02:12:30Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2403.02713v2"}, "publication": {"authors": ["Jiwen Zhang (张霁雯)", "Jihao Wu", "Teng Yihua", "Minghui Liao", "Nuo Xu", "Xiao Xiao", "Zhongyu Wei (魏忠钰)", "Duyu Tang"], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 11], "doi": "10.18653/v1/2024.findings-emnlp.702", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-emnlp.702/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "12016-12031", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.702.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Android in the Zoo: Chain-of-Action-Thought for GUI Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.702/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:50Z", "role": "primary", "sha256": "87a46c27e83152e7741c2398f790320f937b8fd770fa7ac7d3a68395427e87d2", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2024.findings-emnlp.702/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2403.02713", "identifiers": {"arxiv": "2403.02713"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2403.02713"}, {"rel": "publication", "url": "https://aclanthology.org/2024.findings-emnlp.702/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2024.findings-emnlp.702.pdf"}], "name": "Android in the Zoo: Chain-of-Action-Thought for GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-03-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Chain-of-Action-Thought and Android-In-The-Zoo annotations that connect prior actions, screen observations, intended actions, and expected outcomes.", "topics": ["mobile-navigation", "planning"], "updated_at": "2024-07-13", "url": "https://arxiv.org/abs/2403.02713"}
{"aliases": [], "authors": ["Tian Huang", "Chun Yu", "Weinan Shi", "Zijian Peng", "David Yang", "Weiqi Sun", "Yuanchun Shi"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6b2f357e166bddc2bbb5db4ec102721fc12fd27ba45d953193be0354fa5c7bce", "submitted_at": "2024-04-03T05:32:05Z", "updated_at": "2025-03-18T09:59:25Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2404.02475v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}], "id": "arxiv:2404.02475", "identifiers": {"arxiv": "2404.02475"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2404.02475"}], "name": "Prompt2Task: Automating UI Tasks on Smartphones from Textual Prompts", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-04-03", "relations": [], "review_status": "curated", "scope": "core", "summary": "Prompt2Task converts textual goals or procedures into smartphone UI automation using agents for intent interpretation, external-information handling, and execution. User feedback and accumulated task knowledge support subsequent task generation and operation.", "topics": ["mobile-navigation", "human-in-the-loop", "workflow"], "updated_at": "2025-03-18", "url": "https://arxiv.org/abs/2404.02475"}
{"aliases": [], "authors": ["Nicolai Dorka", "Janusz Marecki", "Ammar Anwar"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a2f255b2c2870d9fbe5a543f2a0e09a30c3154fa0c13e9f46eedcefc11d2be43", "submitted_at": "2024-04-12T18:28:44Z", "updated_at": "2024-04-12T18:28:44Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2404.08755v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}], "id": "arxiv:2404.08755", "identifiers": {"arxiv": "2404.08755"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2404.08755"}], "name": "Training a Vision Language Model as Smartphone Assistant", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-04-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "Trains a smartphone assistant from sequences of screenshots paired with earlier actions. The model predicts UI-only interactions such as taps and swipes, with evaluation on Android in the Wild.", "topics": ["mobile-navigation", "interaction-history", "action-prediction"], "updated_at": "2024-04-12", "url": "https://arxiv.org/abs/2404.08755"}
{"aliases": [], "authors": ["Lei Ding", "Jeshwanth Bheemanpally", "Yi Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b3a030a53a942eacfabafc64af67591fd0a85af66291c5d1b48baea14556e8aa", "submitted_at": "2024-04-13T00:20:09Z", "updated_at": "2024-07-09T01:14:21Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2404.08860v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}], "id": "arxiv:2404.08860", "identifiers": {"arxiv": "2404.08860"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2404.08860"}], "name": "Enhancing Mobile \"How-to\" Queries with Automated Search Results Verification and Reranking", "notes": "Reviewed against the retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2024-04-13", "relations": [], "review_status": "curated", "scope": "core", "summary": "Executes instructions from mobile how-to search results inside a controlled Android environment, then uses the observed success of those instructions to verify and rerank technical-support results.", "topics": ["mobile-navigation", "evaluation", "automation"], "updated_at": "2024-07-09", "url": "https://arxiv.org/abs/2404.08860"}
{"aliases": [], "authors": ["Li Zhang", "Shihe Wang", "Xianqing Jia", "Zhihan Zheng", "Yunhe Yan", "Longxi Gao", "Yuanchun Li", "Mengwei Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "28c3ad086106ec4199dcc9da2b8aa3b20eac9347d9354b9dfb373e50ea4c3f50", "submitted_at": "2024-04-12T15:39:09Z", "updated_at": "2024-08-02T13:49:32Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2404.16054v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}], "id": "arxiv:2404.16054", "identifiers": {"arxiv": "2404.16054"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2404.16054"}], "name": "LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-04-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "LlamaTouch executes mobile tasks on devices and evaluates whether an agent visits manually annotated essential application or system states. Screenshot and hierarchy annotations, combined with exact and fuzzy state matching, support evaluation of 496 tasks across multiple agents.", "topics": ["evaluation", "mobile-navigation", "state-tracking"], "updated_at": "2024-08-02", "url": "https://arxiv.org/abs/2404.16054"}
{"aliases": [], "authors": ["Christopher Rawles", "Sarah Clinckemaillie", "Yifan Chang", "Jonathan Waltz", "Gabrielle Lau", "Marybeth Fair", "Alice Li", "William Bishop", "Wei Li", "Folawiyo Campbell-Ajala", "Daniel Toyama", "Robert Berry", "Divya Tyamagundlu", "Timothy Lillicrap", "Oriana Riva"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a33b8b0a03c0dc7ac3f699c34193a526d20791bfedfdde2a2fb89604959e08c2", "submitted_at": "2024-05-23T13:48:54Z", "updated_at": "2025-04-06T20:37:50Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2405.14573v5"}, "publication": {"authors": ["Chris Rawles", "Sarah Clinckemaillie", "Yifan Chang", "Jonathan Waltz", "Gabrielle Lau", "Marybeth Fair", "Alice Li", "William Bishop", "Wei Li", "Folawiyo Campbell-Ajala", "Daniel Toyama", "Robert Berry", "Divya Tyamagundlu", "Timothy Lillicrap", "Oriana Riva"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/01a83bc2f2732a58e6aa731e659e7101-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "406-441", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/01a83bc2f2732a58e6aa731e659e7101-Paper-Conference.pdf", "publisher": null, "series": null, "title": "AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/01a83bc2f2732a58e6aa731e659e7101-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:10:00Z", "role": "primary", "sha256": "e525e5eeedcb08e61765eb0d4034c43381bd3ecc5cc4bf9cc8788cf50e7a2bca", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue", "details.publication.volume"], "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/01a83bc2f2732a58e6aa731e659e7101-Abstract-Conference.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}], "id": "arxiv:2405.14573", "identifiers": {"arxiv": "2405.14573"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2405.14573"}, {"rel": "publication", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/01a83bc2f2732a58e6aa731e659e7101-Abstract-Conference.html"}, {"rel": "publication_pdf", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/01a83bc2f2732a58e6aa731e659e7101-Paper-Conference.pdf"}], "name": "AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents", "notes": "Editorial summary based on the primary paper abstract; experiments and released artifacts have not been independently reproduced.", "published_at": "2024-05-23", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces parameterized Android tasks with initialization, success checks, and cleanup for reproducible interactive evaluation.", "topics": ["evaluation", "mobile-navigation"], "updated_at": "2025-04-06", "url": "https://arxiv.org/abs/2405.14573"}
{"aliases": [], "authors": ["Junyang Wang", "Haiyang Xu", "Haitao Jia", "Xi Zhang", "Ming Yan", "Weizhou Shen", "Ji Zhang", "Fei Huang", "Jitao Sang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a1338f3543a04bc2f9734e5fcabbfd5ebda6ac263461c2305f7c39383e938573", "submitted_at": "2024-06-03T05:50:00Z", "updated_at": "2024-06-03T05:50:00Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2406.01014v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}], "id": "arxiv:2406.01014", "identifiers": {"arxiv": "2406.01014"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2406.01014"}], "name": "Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration", "notes": "Summary and topic tags reviewed against the primary abstract. Reported experiments, task counts, and artifact availability are not independently reproduced.", "published_at": "2024-06-03", "relations": [], "review_status": "curated", "scope": "core", "summary": "Separates mobile planning, decision-making, and reflection, with a memory unit for task progress and relevant content.", "topics": ["planning", "memory", "mobile-navigation"], "updated_at": "2024-06-03", "url": "https://arxiv.org/abs/2406.01014"}
{"aliases": [], "authors": ["Wei Li", "William Bishop", "Alice Li", "Chris Rawles", "Folawiyo Campbell-Ajala", "Divya Tyamagundlu", "Oriana Riva"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6eb3209d8e2a431987fe19f01cd0818f9fb490e684d7369e7d3002dc388ff271", "submitted_at": "2024-06-06T01:49:29Z", "updated_at": "2024-11-13T16:42:22Z", "version": 6, "versioned_url": "https://arxiv.org/abs/2406.03679v6"}, "publication": {"authors": ["Wei Li", "William Bishop", "Alice Li", "Chris Rawles", "Folawiyo Campbell-Ajala", "Divya Tyamagundlu", "Oriana Riva"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-2925", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "92130-92154", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/a79f3ef3b445fd4659f44648f7ea8ffd-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "On the Effects of Data Scale on UI Control Agents", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:10:03Z", "role": "primary", "sha256": "0f499dc380fcd787579aab846e3d1e39b720b672fd9916b4a016688218ca48dd", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue", "details.publication.volume"], "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}], "id": "arxiv:2406.03679", "identifiers": {"arxiv": "2406.03679"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2406.03679"}, {"rel": "publication", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html"}, {"rel": "publication_pdf", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/a79f3ef3b445fd4659f44648f7ea8ffd-Paper-Datasets_and_Benchmarks_Track.pdf"}], "name": "On the Effects of Data Scale on UI Control Agents", "notes": "Annotation reviewed against the primary abstract. Original dataset scale and experimental results are not independently reproduced.", "published_at": "2024-06-06", "relations": [], "review_status": "curated", "scope": "core", "summary": "Studies how Android task performance changes with demonstration scale and releases AndroidControl with high- and low-level instructions.", "topics": ["data-generation", "mobile-navigation", "evaluation"], "updated_at": "2024-11-13", "url": "https://arxiv.org/abs/2406.03679"}
{"aliases": [], "authors": ["Luyuan Wang", "Yongyu Deng", "Yiwei Zha", "Guodong Mao", "Qinmin Wang", "Tianchen Min", "Wei Chen", "Shoufa Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "637843b1b8634e608bed71fc0f3df205ae218d1b0b5550ce480046c67bb14b0f", "submitted_at": "2024-06-12T13:14:50Z", "updated_at": "2024-06-12T13:14:50Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2406.08184v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}], "id": "arxiv:2406.08184", "identifiers": {"arxiv": "2406.08184"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2406.08184"}], "name": "MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-06-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a mobile-agent benchmark with tasks across open-source applications, organized by difficulty to reduce manual evaluation effort.", "topics": ["evaluation", "mobile-navigation"], "updated_at": "2024-06-12", "url": "https://arxiv.org/abs/2406.08184"}
{"aliases": [], "authors": ["Hao Bai", "Yifei Zhou", "Mert Cemri", "Jiayi Pan", "Alane Suhr", "Sergey Levine", "Aviral Kumar"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2c5d4e75d6ba88574f6f033bb2c1cf44cf04149e94e017cd8a1a227e7a1c8238", "submitted_at": "2024-06-14T17:49:55Z", "updated_at": "2024-06-14T17:49:55Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2406.11896v1"}, "publication": {"authors": ["Hao Bai", "Yifei Zhou", "Mert Cemri", "Jiayi Pan", "Alane Suhr", "Sergey Levine", "Aviral Kumar"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-0397", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "12461-12495", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/1704ddd0bb89f159dfe609b32c889995-Paper-Conference.pdf", "publisher": null, "series": null, "title": "DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:10:03Z", "role": "primary", "sha256": "0fd68a0f088591eb695e205286823c7be4059fba8a14e62030ca1b5b11707e21", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue", "details.publication.volume"], "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}], "id": "arxiv:2406.11896", "identifiers": {"arxiv": "2406.11896"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2406.11896"}, {"rel": "publication", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html"}, {"rel": "publication_pdf", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/1704ddd0bb89f159dfe609b32c889995-Paper-Conference.pdf"}], "name": "DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-06-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines offline initialization and online reinforcement learning in Android environments, with automated evaluation and curriculum-based sampling.", "topics": ["reinforcement-learning", "mobile-navigation"], "updated_at": "2024-06-14", "url": "https://arxiv.org/abs/2406.11896"}
{"aliases": [], "authors": ["Ke Wang", "Tianyu Xia", "Zhangxuan Gu", "Yi Zhao", "Shuheng Shen", "Changhua Meng", "Weiqiang Wang", "Ke Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e4d5a46d2141ca59fcf221bbe618601cb7cce29c1b067ae60712e53e907095bd", "submitted_at": "2024-06-20T12:22:05Z", "updated_at": "2024-07-01T08:37:14Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2406.14250v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:32Z", "role": "primary", "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:32Z", "role": "primary", "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"}], "id": "arxiv:2406.14250", "identifiers": {"arxiv": "2406.14250"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2406.14250"}], "name": "E-ANT: A Large-Scale Dataset for Efficient Automatic GUI NavigaTion", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-06-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Chinese-language GUI navigation traces and annotated screenshots collected from human interactions with mini-applications.", "topics": ["mobile-navigation", "evaluation"], "updated_at": "2024-07-01", "url": "https://arxiv.org/abs/2406.14250"}
{"aliases": [], "authors": ["Jiayi Zhang", "Chuang Zhao", "Yihan Zhao", "Zhaoyang Yu", "Ming He", "Jianping Fan"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aa74755c53e20b3a9ff4b72e03a557f455ecceaefc96a50587aefd78ac3c8176", "submitted_at": "2024-07-04T13:12:19Z", "updated_at": "2024-07-04T13:12:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2407.03913v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:32Z", "role": "primary", "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:32Z", "role": "primary", "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"}], "id": "arxiv:2407.03913", "identifiers": {"arxiv": "2407.03913"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2407.03913"}], "name": "MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devices", "notes": "Reviewed against the retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2024-07-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces MobileExperts, which assembles mobile-agent teams, lets agents explore and formulate tools, and coordinates them through two levels of planning. A benchmark organizes tasks by hierarchical intelligence levels.", "topics": ["mobile-navigation", "planning", "tool-integration"], "updated_at": "2024-07-04", "url": "https://arxiv.org/abs/2407.03913"}
{"aliases": [], "authors": ["Songqin Nong", "Jiali Zhu", "Rui Wu", "Jiongchao Jin", "Shuo Shan", "Xiutian Huang", "Wenhao Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "59708ce4edeba4e913ae890f458b51907dd2f3b0b10bb18c86469b36375c84e4", "submitted_at": "2024-07-05T08:37:10Z", "updated_at": "2024-12-06T07:43:34Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2407.04346v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2407.04346", "identifiers": {"arxiv": "2407.04346"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2407.04346"}], "name": "MobileFlow: A Multimodal LLM For Mobile GUI Agent", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-07-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a mobile GUI model using hybrid visual encoders, mixture-of-experts expansion, and alignment training for multilingual interfaces.", "topics": ["mobile-navigation", "screen-understanding"], "updated_at": "2024-12-06", "url": "https://arxiv.org/abs/2407.04346"}
{"aliases": [], "authors": ["Yuxiang Chai", "Siyuan Huang", "Yazhe Niu", "Han Xiao", "Liang Liu", "Dingyu Zhang", "Shuai Ren", "Hongsheng Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9c80665716bf665fe4688a27a4c7dcf26fcfe93cb7f79a6f28784a795e0bd3cb", "submitted_at": "2024-07-03T17:59:58Z", "updated_at": "2025-05-29T02:43:50Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2407.17490v2"}, "publication": {"authors": ["Yuxiang Chai", "Siyuan Huang", "Yazhe Niu", "Han Xiao", "Liang Liu", "Guozhi Wang", "Dingyu Zhang", "Shuai Ren", "Hongsheng Li"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.110", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.110/", "https://aclanthology.org/2025.findings-acl.110.pdf"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. The publisher PDF, page 1, lists nine authors including Guozhi Wang; the retained arXiv snapshot lists eight. Each edition retains its own authors.", "pages": "2138-2156", "pdf_url": "https://aclanthology.org/2025.findings-acl.110.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.110/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:52Z", "role": "primary", "sha256": "9cb5bd38791ee3df95d04815ca650bf0f020518b009c04b4a54857c122f161c8", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2025.findings-acl.110/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:14:02.000709+00:00", "role": "primary", "sha256": "344342e1c229e46269d26d879b32a4d2947932607b968f7e18382d231ad05ee2", "supports": ["details.publication.authors", "details.publication.identity_basis", "details.publication.notes"], "url": "https://aclanthology.org/2025.findings-acl.110.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2407.17490", "identifiers": {"arxiv": "2407.17490"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2407.17490"}, {"rel": "publication", "url": "https://aclanthology.org/2025.findings-acl.110/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2025.findings-acl.110.pdf"}], "name": "AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-07-03", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Android screenshots with element locations, functionality descriptions, and instructions linked to sequences of GUI actions.", "topics": ["grounding", "screen-understanding", "mobile-navigation"], "updated_at": "2025-05-29", "url": "https://arxiv.org/abs/2407.17490"}
{"aliases": [], "authors": ["Yanda Li", "Chi Zhang", "Wenjia Jiang", "Wanqi Yang", "Bin Fu", "Pei Cheng", "Xin Chen", "Ling Chen", "Yunchao Wei"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d5b471c61c2ac9d4932bd71052ea35585699d70e9710f8366bc4fa8e4f2ebbae", "submitted_at": "2024-08-05T06:31:39Z", "updated_at": "2025-09-17T09:06:58Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2408.11824v4"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:32Z", "role": "primary", "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:32Z", "role": "primary", "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"}], "id": "arxiv:2408.11824", "identifiers": {"arxiv": "2408.11824"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2408.11824"}], "name": "AppAgent v2: Advanced Agent for Flexible Mobile Interactions", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-08-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "Separates exploration and deployment while using a structured application knowledge base and retrieval to guide mobile workflows.", "topics": ["mobile-navigation", "memory"], "updated_at": "2025-09-17", "url": "https://arxiv.org/abs/2408.11824"}
{"aliases": [], "authors": ["Kelin Fu", "Yang Tian", "Kaigui Bian"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b46dabe4135f0caca15d54f84cfe805cdb7fe7f1abcce6b004483d99eb21e637", "submitted_at": "2024-09-14T07:54:25Z", "updated_at": "2024-09-14T07:54:25Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2409.09354v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:32Z", "role": "primary", "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:32Z", "role": "primary", "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"}], "id": "arxiv:2409.09354", "identifiers": {"arxiv": "2409.09354"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2409.09354"}], "name": "PeriGuru: A Peripheral Robotic Mobile App Operation Assistant based on GUI Image Understanding and Prompting with LLM", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-09-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "PeriGuru interprets smartphone GUI screenshots with computer vision and uses a language model to decide the next action. A peripheral robotic arm executes the phone interactions, providing an alternative mechanism for operating mobile apps.", "topics": ["mobile-navigation", "screen-understanding", "automation"], "updated_at": "2024-09-14", "url": "https://arxiv.org/abs/2409.09354"}
{"aliases": [], "authors": ["Shaoqing Zhang", "Zhuosheng Zhang", "Kehai Chen", "Xinbei Ma", "Muyun Yang", "Tiejun Zhao", "Min Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f370d105dc1fc1a377fd1b1fd5d1fc3d0f035694cc7c364e6326c587607c98c6", "submitted_at": "2024-10-01T07:49:24Z", "updated_at": "2024-12-19T14:29:31Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.00467v3"}, "publication": {"authors": ["Shaoqing Zhang", "Zhuosheng Zhang", "Kehai Chen (陈科海)", "Xinbei Ma", "Muyun Yang (杨沐昀)", "Tiejun Zhao (赵铁军)", "Min Zhang"], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 11], "doi": "10.18653/v1/2024.findings-emnlp.70", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-emnlp.70/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "1304-1320", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.70.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Dynamic Planning for LLM-based Graphical User Interface Automation", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.70/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:53Z", "role": "primary", "sha256": "1d89601c2a7a81756b9e7441c48a312132f385e5370780507d27c9848aa1176d", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2024.findings-emnlp.70/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}], "id": "arxiv:2410.00467", "identifiers": {"arxiv": "2410.00467"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:35Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2410.00467"}, {"rel": "publication", "url": "https://aclanthology.org/2024.findings-emnlp.70/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2024.findings-emnlp.70.pdf"}], "name": "Dynamic Planning for LLM-based Graphical User Interface Automation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-10-01", "relations": [], "review_status": "curated", "scope": "core", "summary": "Dynamic Planning of Thoughts revises a mobile GUI plan using current environmental feedback and execution history. The study compares this planning strategy with long-dialogue prompting and examines its behavior on unfamiliar tasks and different language-model backbones.", "topics": ["planning", "interaction-history", "mobile-navigation", "robustness"], "updated_at": "2024-12-19", "url": "https://arxiv.org/abs/2410.00467"}
{"aliases": [], "authors": ["Zhuohao Jerry Zhang", "Eldon Schoop", "Jeffrey Nichols", "Anuj Mahajan", "Amanda Swearngin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ff649a0792864bd40b7bf2f825f6a8a815eb60cc795ed4dc0c6b55a942477758", "submitted_at": "2024-10-11T17:24:00Z", "updated_at": "2025-03-22T18:01:37Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.09006v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}], "id": "arxiv:2410.09006", "identifiers": {"arxiv": "2410.09006"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:35Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2410.09006"}], "name": "From Interaction to Impact: Towards Safer AI Agents Through Understanding and Evaluating Mobile UI Operation Impacts", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-10-11", "relations": [], "review_status": "curated", "scope": "core", "summary": "Develops a taxonomy of mobile-action consequences and annotated interaction data to evaluate whether models recognize impactful or risky UI operations.", "topics": ["safety-security", "mobile-navigation", "evaluation"], "updated_at": "2025-03-22", "url": "https://arxiv.org/abs/2410.09006"}
{"aliases": [], "authors": ["Jakub Hoscilowicz", "Bartosz Maj", "Bartosz Kozakiewicz", "Oleksii Tymoshchuk", "Artur Janicki"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e804944da205076ac6cf88c7966c471697e526f657bda339e09df240257f7217", "submitted_at": "2024-10-09T14:49:02Z", "updated_at": "2024-10-17T07:12:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.11872v2"}, "publication": {"authors": ["Jakub Hoscilowicz", "Bartosz Maj", "Bartosz Kozakiewicz", "Oleksii Tymoshchuk", "Artur Janicki"], "date_basis": "Explicit publisher citation_publication_date: 2025/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 8], "doi": "10.18653/v1/2025.sigdial-1.38", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.sigdial-1.38/", "https://aclanthology.org/2025.sigdial-1.38.pdf"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the five-author list on page 1 of the publisher PDF. Landing-page citation metadata lists only Jakub Hoscilowicz and Artur Janicki.", "pages": "471-476", "pdf_url": "https://aclanthology.org/2025.sigdial-1.38.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.sigdial-1.38/", "venue": "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue", "volume": null}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:53Z", "role": "primary", "sha256": "7c710272d48754149cc5947f5382b8123eac5855db7655410259c4a3129b8b5b", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2025.sigdial-1.38/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:14:09.676954+00:00", "role": "primary", "sha256": "c5b5cd07e3ca2f2911e183c4752e01c721971c47fd20c836605452f2b80e5260", "supports": ["details.publication.authors", "details.publication.identity_basis", "details.publication.notes"], "url": "https://aclanthology.org/2025.sigdial-1.38.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}], "id": "arxiv:2410.11872", "identifiers": {"arxiv": "2410.11872"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:35Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2410.11872"}, {"rel": "publication", "url": "https://aclanthology.org/2025.sigdial-1.38/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2025.sigdial-1.38.pdf"}], "name": "ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-10-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Separates multimodal reasoning and action planning from a dedicated UI localization model, with evaluation on Android devices.", "topics": ["mobile-navigation", "grounding"], "updated_at": "2024-10-17", "url": "https://arxiv.org/abs/2410.11872"}
{"aliases": [], "authors": ["Zichen Zhu", "Hao Tang", "Yansi Li", "Dingye Liu", "Hongshen Xu", "Kunyao Lan", "Danyang Zhang", "Yixuan Jiang", "Hao Zhou", "Chenrun Wang", "Situo Zhang", "Liangtai Sun", "Yixiao Wang", "Yuheng Sun", "Lu Chen", "Kai Yu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c0ef02f9c31bf2f095330cf018e7525aecc7644eb1552fb6b511ffced3889122", "submitted_at": "2024-10-17T16:53:50Z", "updated_at": "2025-05-13T06:25:09Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.13757v3"}, "publication": {"authors": ["Zichen Zhu", "Hao Tang", "Yansi Li", "Dingye Liu", "Hongshen Xu", "Kunyao Lan", "Danyang Zhang", "Yixuan Jiang", "Hao Zhou", "Chenrun Wang", "Situo Zhang", "Liangtai Sun", "Yixiao Wang", "Yuheng Sun", "Lu Chen", "Kai Yu"], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 4], "doi": "10.18653/v1/2025.naacl-demo.43", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.naacl-demo.43/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "535-549", "pdf_url": "https://aclanthology.org/2025.naacl-demo.43.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-demo.43/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "volume": null}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:53Z", "role": "primary", "sha256": "a873b34264be14f64599c0897219ff2796ab74d111df8a2fdc667fd22ad87028", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2025.naacl-demo.43/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}], "id": "arxiv:2410.13757", "identifiers": {"arxiv": "2410.13757"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:35Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2410.13757"}, {"rel": "publication", "url": "https://aclanthology.org/2025.naacl-demo.43/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2025.naacl-demo.43.pdf"}], "name": "MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-10-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines adaptive mobile-task planning, reflection-based recovery, and multiple memory components, evaluated with MobBench and AndroidArena.", "topics": ["memory", "planning", "mobile-navigation"], "updated_at": "2025-05-13", "url": "https://arxiv.org/abs/2410.13757"}
{"aliases": [], "authors": ["Jingxuan Chen", "Derek Yuen", "Bin Xie", "Yuhao Yang", "Gongwei Chen", "Zhihao Wu", "Li Yixing", "Xurui Zhou", "Weiwen Liu", "Shuai Wang", "Kaiwen Zhou", "Rui Shao", "Liqiang Nie", "Yasheng Wang", "Jianye Hao", "Jun Wang", "Kun Shao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "206059754652205f1e036fac8ee117f71dd356bfe2d35fd84aff8d2935ea242d", "submitted_at": "2024-10-19T17:28:48Z", "updated_at": "2025-03-31T20:39:17Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.15164v3"}, "publication": {"authors": ["Jingxuan Chen", "Derek Yuen", "Bin Xie", "Yuhao Yang", "Gongwei Chen", "Zhihao Wu", "Li Yixing", "Xurui Zhou", "Weiwen Liu", "Shuai Wang", "Kaiwen Zhou", "Rui Shao", "Liqiang Nie", "Yasheng Wang", "Jianye HAO", "Jun Wang", "Kun Shao"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/9a75f4dd9679aa4ff80a4e6f0a1dc700-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "61769-61806", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/9a75f4dd9679aa4ff80a4e6f0a1dc700-Paper-Conference.pdf", "publisher": null, "series": null, "title": "SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/9a75f4dd9679aa4ff80a4e6f0a1dc700-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:10:02Z", "role": "primary", "sha256": "56efdfea12b96edd94ad366f941d57668cdb75f6889fc03297e749497ff03e92", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue", "details.publication.volume"], "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/9a75f4dd9679aa4ff80a4e6f0a1dc700-Abstract-Conference.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}], "id": "arxiv:2410.15164", "identifiers": {"arxiv": "2410.15164"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:35Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2410.15164"}, {"rel": "publication", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/9a75f4dd9679aa4ff80a4e6f0a1dc700-Abstract-Conference.html"}, {"rel": "publication_pdf", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/9a75f4dd9679aa4ff80a4e6f0a1dc700-Paper-Conference.pdf"}], "name": "SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-10-19", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a smartphone-agent benchmark with English and Chinese tasks, real-time Android interaction, and completion and resource-use metrics.", "topics": ["evaluation", "efficiency", "mobile-navigation"], "updated_at": "2025-03-31", "url": "https://arxiv.org/abs/2410.15164"}
{"aliases": [], "authors": ["Filippos Christianos", "Georgios Papoudakis", "Thomas Coste", "Jianye Hao", "Jun Wang", "Kun Shao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9f6eb76587ef91a21942d34ba9ee7ba0ebc846277b12c69ecb179c2b2d1720df", "submitted_at": "2024-10-23T13:57:00Z", "updated_at": "2025-02-12T17:51:51Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.17883v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}], "id": "arxiv:2410.17883", "identifiers": {"arxiv": "2410.17883"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:35Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2410.17883"}], "name": "Lightweight Neural App Control", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-10-23", "relations": [], "review_status": "curated", "scope": "core", "summary": "LiMAC combines a compact Action Transformer with a fine-tuned vision-language model for Android app control. It uses textual goals and histories of screenshots and UI trees to predict actions, with evaluation on two mobile-control datasets.", "topics": ["mobile-navigation", "action-prediction", "efficiency", "interaction-history"], "updated_at": "2025-02-12", "url": "https://arxiv.org/abs/2410.17883"}
{"aliases": [], "authors": ["Yifan Xu", "Xiao Liu", "Xueqiao Sun", "Siyi Cheng", "Hao Yu", "Hanyu Lai", "Shudan Zhang", "Dan Zhang", "Jie Tang", "Yuxiao Dong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d29fe5262adf8677bbd5fead628c5fc28707af263aa7e800d1dee1f7e499784c", "submitted_at": "2024-10-31T15:25:20Z", "updated_at": "2024-11-04T05:57:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.24024v2"}, "publication": {"authors": ["Yifan Xu", "Xiao Liu", "Xueqiao Sun", "Siyi Cheng", "Hao Yu (余浩)", "Hanyu Lai", "Shudan Zhang", "Dan Zhang", "Jie Tang", "Yuxiao Dong"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.acl-long.107", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.107/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "2144-2166", "pdf_url": "https://aclanthology.org/2025.acl-long.107.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.107/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:56Z", "role": "primary", "sha256": "52b82854b5f4703e6e7f3cd3e9fc49adcd011ca3ba0a8fd1aced77214c452043", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2025.acl-long.107/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:35Z", "role": "primary", "sha256": "b3e67984f59a1b05ccd946eb54e2d37b0bb78ab0ca796fbb6d544793dafea3e0", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2410.00467%2C2410.00689%2C2410.02810%2C2410.02907%2C2410.05243%2C2410.06703%2C2410.08164%2C2410.09006%2C2410.09024%2C2410.11843%2C2410.11871%2C2410.11872%2C2410.13232%2C2410.13757%2C2410.13824%2C2410.13825%2C2410.13886%2C2410.14803%2C2410.15164%2C2410.16464%2C2410.17236%2C2410.17401%2C2410.17520%2C2410.17883%2C2410.18603%2C2410.18963%2C2410.18967%2C2410.19054%2C2410.19100%2C2410.19461%2C2410.19609%2C2410.20745%2C2410.22552%2C2410.23218%2C2410.24024%2C2411.00820%2C2411.02337%2C2411.02391%2C2411.04468%2C2411.04890%2C2411.06559%2C2411.07618%2C2411.10323%2C2411.13451%2C2411.13591%2C2411.15004%2C2411.17465%2C2411.18279%2C2412.00402%2C2412.01268&max_results=50"}], "id": "arxiv:2410.24024", "identifiers": {"arxiv": "2410.24024"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:35Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2410.24024"}, {"rel": "publication", "url": "https://aclanthology.org/2025.acl-long.107/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2025.acl-long.107.pdf"}], "name": "AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents", "notes": "Summary and topic tags reviewed against the primary abstract. Reported experiments, task counts, and artifact availability are not independently reproduced.", "published_at": "2024-10-31", "relations": [], "review_status": "curated", "scope": "core", "summary": "Provides a shared Android action environment, reproducible tasks, and instruction data for training and comparing language and multimodal agents.", "topics": ["evaluation", "data-generation", "mobile-navigation"], "updated_at": "2024-11-04", "url": "https://arxiv.org/abs/2410.24024"}
{"aliases": [], "authors": ["Biao Wu", "Yanda Li", "Zhiwei Zhang", "Yunchao Wei", "Meng Fang", "Ling Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "de860a29f6c54317586c2218688436898f1d7a8b61207b1d5f4a65b05b3a4e6e", "submitted_at": "2024-11-04T11:50:58Z", "updated_at": "2025-09-14T09:13:39Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2411.02006v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T07:57:41Z", "role": "primary", "sha256": "0ba893415123ecc1763614ef5fc97e5c8bb7835f10b26b43f1b921ea860484cf", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2410.06212%2C2410.06215%2C2410.07283%2C2410.07331%2C2410.07869%2C2410.08209%2C2410.08368%2C2410.10570%2C2410.12481%2C2410.12669%2C2410.15549%2C2410.16950%2C2410.21909%2C2410.22584%2C2410.22770%2C2410.23022%2C2410.23555%2C2411.02006%2C2411.02393%2C2411.02479%2C2411.03312%2C2411.03817%2C2411.05451%2C2411.11145%2C2411.11904%2C2411.11916%2C2411.12990%2C2411.14228%2C2411.15397%2C2412.01857%2C2412.04144%2C2412.04383%2C2412.05819%2C2412.06224%2C2412.06771%2C2412.09530%2C2412.09613%2C2412.10047%2C2412.10380%2C2412.10673%2C2412.12004%2C2412.13178%2C2412.13810%2C2412.14203%2C2412.14222%2C2412.16359%2C2412.19638%2C2412.20206%2C2501.03895%2C2501.05179&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:13:27Z", "role": "primary", "sha256": "bda47fcb119c581a798dbc791b4929af91832d5053ac073a02dab8fd4e10ace3", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/2411.02006v3"}], "id": "arxiv:2411.02006", "identifiers": {"arxiv": "2411.02006"}, "kind": "survey", "last_verified_at": "2026-10-17T09:13:27Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2411.02006"}], "name": "Foundations and Recent Trends in Multimodal Mobile Agents: A Survey", "notes": "Reviewed against the exact-version official arXiv abstract page; its normalized abstract SHA-256 matches the retained bibliographic snapshot. The original API response body was not locally available for this review. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2024-11-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "Surveys multimodal mobile agents, organizing prompt-based and training-based approaches alongside evaluation benchmarks, supporting technologies, and open challenges in mobile task execution.", "topics": ["survey", "mobile-navigation", "evaluation"], "updated_at": "2025-09-14", "url": "https://arxiv.org/abs/2411.02006"}
{"aliases": [], "authors": ["Minghe Gao", "Wendong Bu", "Bingchen Miao", "Yang Wu", "Yunfei Li", "Juncheng Li", "Siliang Tang", "Qi Wu", "Yueting Zhuang", "Meng Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "daa9b7092616e94a1d0124d36d8b75d0401b9647ec762c963524616a92def9a5", "submitted_at": "2024-11-17T02:44:56Z", "updated_at": "2024-11-17T02:44:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2411.10943v1"}}, "environments": ["web", "desktop", "android", "windows"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:29:13.577033+00:00", "role": "primary", "sha256": "92f18020e481d6f42a6d35e96dff820594e9370597f5392d038e9ee908c49f1e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/html/2411.10943v1"}], "id": "arxiv:2411.10943", "identifiers": {"arxiv": "2411.10943"}, "kind": "survey", "last_verified_at": "2026-10-18T04:29:13.577033+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2411.10943"}], "name": "Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platforms", "notes": "Reviewed the complete retained arXiv abstract and exact-version official HTML sections on browser/application/OS environments, screen observations, input actions and evaluation. The HTML abstract fingerprint and ordered authors match the retained Atom entry. Literature claims and experiments were not independently reproduced.", "published_at": "2024-11-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "Surveys virtual agents for browsers, applications and operating systems, organizing prior work by task type, observation and action spaces, model strategies and evaluation methods. It examines screen-based interaction and keyboard, mouse and touch control, alongside transferability and long-sequence decision-making challenges.", "topics": ["survey", "web-navigation", "mobile-navigation", "evaluation", "planning"], "updated_at": "2024-11-17", "url": "https://arxiv.org/abs/2411.10943"}
{"aliases": [], "authors": ["Hao Wen", "Shizuo Tian", "Borislav Pavlov", "Wenjie Du", "Yixuan Li", "Ge Chang", "Shanhui Zhao", "Jiacheng Liu", "Yunxin Liu", "Ya-Qin Zhang", "Yuanchun Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3190c452dbfa24b131cc34f66192bbdb9c538d30a1919082a9fed334f6169fff", "submitted_at": "2024-12-24T02:54:56Z", "updated_at": "2025-05-06T12:24:43Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2412.18116v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2412.18116", "identifiers": {"arxiv": "2412.18116"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2412.18116"}], "name": "AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-12-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "Recasts mobile UI automation as on-device code generation, using app-specific documentation and synthetic tasks to guide smaller models.", "topics": ["mobile-navigation", "tool-integration"], "updated_at": "2025-05-06", "url": "https://arxiv.org/abs/2412.18116"}
{"aliases": [], "authors": ["Kangjia Zhao", "Jiahui Song", "Leigang Sha", "Haozhan Shen", "Zhi Chen", "Tiancheng Zhao", "Xiubo Liang", "Jianwei Yin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9e509f015068bcf1294a97236ff3bbde5e3ceb167f3cb032fcfd84fc4a5b01d0", "submitted_at": "2024-12-24T13:41:47Z", "updated_at": "2024-12-24T13:41:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2412.18426v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"}], "id": "arxiv:2412.18426", "identifiers": {"arxiv": "2412.18426"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:38Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2412.18426"}], "name": "GUI Testing Arena: A Unified Benchmark for Advancing Autonomous GUI Testing Agent", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-12-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "Evaluates GUI testing through test-intent generation, execution, and defect detection using real, modified, and synthetic mobile application data.", "topics": ["evaluation", "automation", "mobile-navigation"], "updated_at": "2024-12-24", "url": "https://arxiv.org/abs/2412.18426"}
{"aliases": [], "authors": ["Yuxiang Chai", "Shunye Tang", "Han Xiao", "Weifeng Lin", "Hanhao Li", "Jiayu Zhang", "Liang Liu", "Pengxiang Zhao", "Guangyi Liu", "Guozhi Wang", "Shuai Ren", "Rongduo Han", "Haining Zhang", "Siyuan Huang", "Hongsheng Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8ac7100a0f3cc3f004672eb6923b1f0ecb43c3d98da6959f0ff7514d0fb2f442", "submitted_at": "2025-01-02T09:03:56Z", "updated_at": "2026-01-12T07:01:09Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2501.01149v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2501.01149", "identifiers": {"arxiv": "2501.01149"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2501.01149"}], "name": "A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-01-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Android Agent Arena with online application tasks and procedural evaluation based on reaching essential intermediate states.", "topics": ["evaluation", "mobile-navigation"], "updated_at": "2026-01-12", "url": "https://arxiv.org/abs/2501.01149"}
{"aliases": [], "authors": ["Zhenhailong Wang", "Haiyang Xu", "Junyang Wang", "Xi Zhang", "Ming Yan", "Ji Zhang", "Fei Huang", "Heng Ji"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5cf28f084cac7fc38e5c2dc4654115356d2d57f16009aad8925e071b8005be9c", "submitted_at": "2025-01-20T20:35:46Z", "updated_at": "2025-01-28T16:58:02Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2501.11733v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"}], "id": "arxiv:2501.11733", "identifiers": {"arxiv": "2501.11733"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:38Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2501.11733"}], "name": "Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-01-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses hierarchical mobile agents and persistent tips and reusable action shortcuts to improve complex tasks from accumulated experience.", "topics": ["mobile-navigation", "memory", "long-horizon"], "updated_at": "2025-01-28", "url": "https://arxiv.org/abs/2501.11733"}
{"aliases": [], "authors": ["Qinzhuo Wu", "Wei Liu", "Jian Luan", "Bin Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d3e0b19f259bcdb57b0dea92578d0ee1c7c229ea11e622c56e808f17ca2568cc", "submitted_at": "2025-02-05T07:35:23Z", "updated_at": "2025-02-05T07:35:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2502.02955v1"}, "publication": {"authors": ["Qinzhuo Wu", "Wei Liu", "Jian Luan", "Bin Wang"], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 4], "doi": "10.18653/v1/2025.naacl-long.244", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.naacl-long.244/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "4760-4775", "pdf_url": "https://aclanthology.org/2025.naacl-long.244.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-long.244/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", "volume": null}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:58Z", "role": "primary", "sha256": "bb33865bafca385d3d1ce446d5cd85b6c1bf41d567509ac5ea539d4cc9c64799", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2025.naacl-long.244/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}], "id": "arxiv:2502.02955", "identifiers": {"arxiv": "2502.02955"}, "kind": "paper", "last_verified_at": "2026-10-16T06:45:04Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2502.02955"}, {"rel": "publication", "url": "https://aclanthology.org/2025.naacl-long.244/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2025.naacl-long.244.pdf"}], "name": "ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-02-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "Splits mobile tasks into reaching the required page and operating on it, using subtask data and preferred GUI trajectories for training.", "topics": ["mobile-navigation", "planning", "data-generation"], "updated_at": "2025-02-05", "url": "https://arxiv.org/abs/2502.02955"}
{"aliases": [], "authors": ["Wenhao Wang", "Mengying Yuan", "Zijie Yu", "Guangyi Liu", "Rui Ye", "Tian Jin", "Siheng Chen", "Yanfeng Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ecab608111104ac044bb7d28996604e9b87bdad4543c250c57bf432f883b96d5", "submitted_at": "2025-02-05T08:26:17Z", "updated_at": "2025-05-20T07:03:02Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2502.02982v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2502.02982", "identifiers": {"arxiv": "2502.02982"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2502.02982"}], "name": "MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-02-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "Studies automatic annotation and federated training of mobile GUI agents from decentralized user interaction data with heterogeneous distributions.", "topics": ["mobile-navigation", "data-generation"], "updated_at": "2025-05-20", "url": "https://arxiv.org/abs/2502.02982"}
{"aliases": [], "authors": ["Georgios Papoudakis", "Thomas Coste", "Zhihao Wu", "Jianye Hao", "Jun Wang", "Kun Shao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "44ec9907c8d536488e59dea307aa05bd8adcadf96cb4f3ba25a355ffe4cf8ff7", "submitted_at": "2025-02-10T12:32:21Z", "updated_at": "2025-02-10T12:32:21Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2502.06395v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"}], "id": "arxiv:2502.06395", "identifiers": {"arxiv": "2502.06395"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:38Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2502.06395"}], "name": "AppVLM: A Lightweight Vision Language Model for Online App Control", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-02-10", "relations": [], "review_status": "curated", "scope": "core", "summary": "AppVLM first learns app actions from AndroidControl and then refines its policy through data collected in AndroidWorld. The study compares offline action prediction and online task completion for a lightweight vision-language smartphone agent.", "topics": ["mobile-navigation", "imitation-learning", "data-generation", "efficiency"], "updated_at": "2025-02-10", "url": "https://arxiv.org/abs/2502.06395"}
{"aliases": [], "authors": ["Junyang Wang", "Haiyang Xu", "Xi Zhang", "Ming Yan", "Ji Zhang", "Fei Huang", "Jitao Sang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d723cb764deb78b194ff0199c7f1b921a12b6a41655c07b06ae88c3d0af58358", "submitted_at": "2025-02-24T12:51:23Z", "updated_at": "2025-06-03T08:37:03Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2502.17110v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}], "id": "arxiv:2502.17110", "identifiers": {"arxiv": "2502.17110"}, "kind": "paper", "last_verified_at": "2026-10-16T06:45:04Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2502.17110"}], "name": "Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced. The authors identify arXiv:2505.13887 as an accidental duplicate and direct future updates to this record.", "published_at": "2025-02-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "Extracts operational guidance from video for mobile task execution and introduces Mobile-Knowledge to evaluate the contribution of external knowledge.", "topics": ["mobile-navigation", "video", "memory"], "updated_at": "2025-06-03", "url": "https://arxiv.org/abs/2502.17110"}
{"aliases": [], "authors": ["Jiahui Sun", "Zhichao Hua", "Yubin Xia"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a0c393d109ab0f8da2bf25bb39581236babd50f7554f2ec99679a99fb7215171", "submitted_at": "2025-03-04T08:44:30Z", "updated_at": "2025-09-24T05:11:34Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.02403v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}], "id": "arxiv:2503.02403", "identifiers": {"arxiv": "2503.02403"}, "kind": "paper", "last_verified_at": "2026-10-16T06:45:04Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.02403"}], "name": "AutoEval: A Practical Framework for Autonomous Evaluation of Mobile Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-03-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "Generates reward signals from UI-state changes and uses a judging system to evaluate mobile agents with reduced manual evaluator construction.", "topics": ["evaluation", "mobile-navigation"], "updated_at": "2025-09-24", "url": "https://arxiv.org/abs/2503.02403"}
{"aliases": [], "authors": ["Yuqi Zhou", "Shuai Wang", "Sunhao Dai", "Qinglin Jia", "Zhaocheng Du", "Zhenhua Dong", "Jun Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "380d00c46e5dd221b7c481a68b4fbdc00826e64e4b70a98f06a56f8c12b8f5e4", "submitted_at": "2025-03-05T18:56:16Z", "updated_at": "2025-03-05T18:56:16Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2503.03743v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:52Z", "role": "primary", "sha256": "0b730323b2ce85c39aa7d534665901a480ff06540c73f1f80832fcc0735b8789", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2310.08588%2C2402.09205%2C2406.05720%2C2407.21075%2C2410.07166%2C2503.03743%2C2508.04037%2C2508.10833%2C2508.11360%2C2508.13024%2C2508.13186%2C2508.14104%2C2509.01619%2C2509.01720%2C2509.02322%2C2509.04198%2C2509.07764%2C2509.21823%2C2509.22256%2C2509.23263%2C2509.23866%2C2509.25047%2C2509.26539%2C2510.00413%2C2510.00536%2C2510.01524%2C2510.02204%2C2510.02250%2C2510.02418%2C2510.03204%2C2510.03612%2C2510.04039%2C2510.04373%2C2510.04607%2C2510.06223%2C2510.06607%2C2510.09872%2C2510.10666%2C2510.11035%2C2510.11221%2C2510.11892%2C2510.13543%2C2510.15455%2C2510.15863%2C2510.16252%2C2510.18113%2C2510.18314%2C2510.19205%2C2510.22732%2C2511.06101&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:52Z", "role": "primary", "sha256": "0b730323b2ce85c39aa7d534665901a480ff06540c73f1f80832fcc0735b8789", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2310.08588%2C2402.09205%2C2406.05720%2C2407.21075%2C2410.07166%2C2503.03743%2C2508.04037%2C2508.10833%2C2508.11360%2C2508.13024%2C2508.13186%2C2508.14104%2C2509.01619%2C2509.01720%2C2509.02322%2C2509.04198%2C2509.07764%2C2509.21823%2C2509.22256%2C2509.23263%2C2509.23866%2C2509.25047%2C2509.26539%2C2510.00413%2C2510.00536%2C2510.01524%2C2510.02204%2C2510.02250%2C2510.02418%2C2510.03204%2C2510.03612%2C2510.04039%2C2510.04373%2C2510.04607%2C2510.06223%2C2510.06607%2C2510.09872%2C2510.10666%2C2510.11035%2C2510.11221%2C2510.11892%2C2510.13543%2C2510.15455%2C2510.15863%2C2510.16252%2C2510.18113%2C2510.18314%2C2510.19205%2C2510.22732%2C2511.06101&max_results=50"}], "id": "arxiv:2503.03743", "identifiers": {"arxiv": "2503.03743"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.03743"}], "name": "CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-03-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses human-planned subtasks to constrain and refine the intermediate plans connecting user goals with executable mobile operations.", "topics": ["mobile-navigation", "planning"], "updated_at": "2025-03-05", "url": "https://arxiv.org/abs/2503.03743"}
{"aliases": [], "authors": ["Wenhao Wang", "Zijie Yu", "Rui Ye", "Jianqing Zhang", "Siheng Chen", "Yanfeng Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b408c850ae83e603a1b3d8303164b9f2d7be51580be99027275b0734ea8f56f2", "submitted_at": "2025-03-07T04:52:20Z", "updated_at": "2025-03-07T04:52:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2503.05143v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"}], "id": "arxiv:2503.05143", "identifiers": {"arxiv": "2503.05143"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:38Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.05143"}], "name": "FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Data", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-03-07", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a benchmark for federated mobile-agent training under heterogeneous user and application distributions, combining datasets, algorithms, and base models.", "topics": ["evaluation", "mobile-navigation"], "updated_at": "2025-03-07", "url": "https://arxiv.org/abs/2503.05143"}
{"aliases": [], "authors": ["Gaole Dai", "Shiqi Jiang", "Ting Cao", "Yuanchun Li", "Yuqing Yang", "Rui Tan", "Mo Li", "Lili Qiu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6449576cb8ba45569b57844d87f22d01645b3639a222c648d914dc38e3421553", "submitted_at": "2025-03-20T08:25:00Z", "updated_at": "2026-02-21T01:36:43Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2503.15937v5"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2503.15937", "identifiers": {"arxiv": "2503.15937"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.15937"}], "name": "Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-03-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces V-Droid, which verifies candidate actions in a discrete action space rather than directly generating each mobile operation.", "topics": ["mobile-navigation", "efficiency", "planning"], "updated_at": "2026-02-21", "url": "https://arxiv.org/abs/2503.15937"}
{"aliases": [], "authors": ["Pengzhou Cheng", "Zheng Wu", "Zongru Wu", "Aston Zhang", "Zhuosheng Zhang", "Gongshen Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aa6201528b13c6a1aae8dcd745f4f5d995e79982ef7c54a1962e2f9035233293", "submitted_at": "2025-02-26T12:31:16Z", "updated_at": "2025-07-14T15:56:44Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2503.16465v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2503.16465", "identifiers": {"arxiv": "2503.16465"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.16465"}], "name": "OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-02-26", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses step-level confidence estimates to decide when a GUI agent should act autonomously or request human intervention in complex situations.", "topics": ["human-in-the-loop", "safety-security", "mobile-navigation"], "updated_at": "2025-07-14", "url": "https://arxiv.org/abs/2503.16465"}
{"aliases": [], "authors": ["Li Zhang", "Longxi Gao", "Mengwei Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e450216f8f802d8f3d16c5886097cef801d051951af0c57fdf195cc176ac744f", "submitted_at": "2025-03-21T01:52:43Z", "updated_at": "2025-03-21T01:52:43Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2503.16788v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2503.16788", "identifiers": {"arxiv": "2503.16788"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.16788"}], "name": "Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-03-21", "relations": [], "review_status": "curated", "scope": "core", "summary": "This study compares matched reasoning and non-reasoning vision-language models on static mobile GUI tasks and interactive AndroidWorld navigation. It finds that chain-of-thought effects vary across tasks and model families.", "topics": ["evaluation", "mobile-navigation", "planning"], "updated_at": "2025-03-21", "url": "https://arxiv.org/abs/2503.16788"}
{"aliases": [], "authors": ["Jungjae Lee", "Dongjae Lee", "Chihun Choi", "Youngmin Im", "Jaeyoung Wi", "Kihong Heo", "Sangeun Oh", "Sunjae Lee", "Insik Shin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "10e7a9a4471555c6e4001cd10c1e4b375b503adfe6ea48d5808d1d7721dfc162", "submitted_at": "2025-03-24T09:46:05Z", "updated_at": "2025-09-11T04:15:45Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.18492v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2503.18492", "identifiers": {"arxiv": "2503.18492"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.18492"}], "name": "VeriSafe Agent: Safeguarding Mobile GUI Agent via Logic-based Action Verification", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-03-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "Translates user instructions into formal specifications and applies runtime logic-based checks to proposed mobile GUI actions.", "topics": ["safety-security", "mobile-navigation"], "updated_at": "2025-09-11", "url": "https://arxiv.org/abs/2503.18492"}
{"aliases": [], "authors": ["Noam Kahlon", "Guy Rom", "Anatoly Efros", "Filippo Galgani", "Omri Berkovitch", "Sapir Caduri", "William E. Bishop", "Oriana Riva", "Ido Dagan"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8a49d662eddf84690395b025e50f3378c3be2a3fc8abe02bd7202c6ff879bbe3", "submitted_at": "2025-03-25T10:46:08Z", "updated_at": "2025-03-25T10:46:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2503.19537v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}], "id": "arxiv:2503.19537", "identifiers": {"arxiv": "2503.19537"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:42Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.19537"}], "name": "Agent-Initiated Interaction in Phone UI Automation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-03-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "Defines when phone agents should request user interaction and introduces AndroidInteraction annotations for deciding whether and how to engage the user.", "topics": ["human-in-the-loop", "mobile-navigation", "evaluation"], "updated_at": "2025-03-25", "url": "https://arxiv.org/abs/2503.19537"}
{"aliases": [], "authors": ["Biniam Fisseha Demissie", "Yan Naing Tun", "Lwin Khin Shar", "Mariano Ceccato"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1a25cb3ca680732a08cf2c461a65caa0c6a70404224bdfd919ba5bec7760ba72", "submitted_at": "2025-04-16T00:19:31Z", "updated_at": "2025-04-16T00:19:31Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2504.11675v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}], "id": "arxiv:2504.11675", "identifiers": {"arxiv": "2504.11675"}, "kind": "paper", "last_verified_at": "2026-10-16T06:45:04Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2504.11675"}], "name": "VLM-Fuzz: Vision Language Model Assisted Recursive Depth-first Search Exploration for Effective UI Testing of Android Apps", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-04-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "VLM-Fuzz combines depth-first UI exploration with Android manifest analysis, runtime widget hierarchies, and on-demand visual reasoning to generate app test inputs. It evaluates coverage on 59 benchmark apps and uses additional Google Play apps to study crash discovery.", "topics": ["automation", "evaluation", "mobile-navigation"], "updated_at": "2025-04-16", "url": "https://arxiv.org/abs/2504.11675"}
{"aliases": [], "authors": ["Guangyi Liu", "Pengxiang Zhao", "Liang Liu", "Zhiming Chen", "Yuxiang Chai", "Shuai Ren", "Hao Wang", "Shibo He", "Wenchao Meng"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2bbe6c4969a9557546752235809d25912bff96a97001fade30102d8d2c751054", "submitted_at": "2025-04-18T17:13:34Z", "updated_at": "2025-04-18T17:13:34Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2504.13805v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2504.13805", "identifiers": {"arxiv": "2504.13805"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2504.13805"}], "name": "LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-04-18", "relations": [], "review_status": "curated", "scope": "core", "summary": "LearnAct parses human demonstrations into reusable knowledge, retrieves relevant examples, and uses them during mobile GUI task execution. The accompanying LearnGUI benchmark includes 2,252 offline tasks and 101 online tasks for studying adaptation from demonstrations.", "topics": ["mobile-navigation", "memory", "human-in-the-loop", "evaluation"], "updated_at": "2025-04-18", "url": "https://arxiv.org/abs/2504.13805"}
{"aliases": [], "authors": ["Dezhao Luo", "Bohan Tang", "Kang Li", "Georgios Papoudakis", "Jifei Song", "Shaogang Gong", "Jianye Hao", "Jun Wang", "Kun Shao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "15e00237ef710c37c0c9f7768d699f57e9d5dcc190e8de7e20e9ec3b21b82750", "submitted_at": "2025-04-15T14:03:10Z", "updated_at": "2025-05-20T14:11:37Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.13936v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}], "id": "arxiv:2504.13936", "identifiers": {"arxiv": "2504.13936"}, "kind": "paper", "last_verified_at": "2026-10-16T06:45:04Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2504.13936"}], "name": "ViMo: A Generative Visual GUI World Model for App Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-04-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "ViMo predicts the next mobile-app screenshot after a candidate action by separately modeling graphics and text. A symbolic placeholder representation preserves layout while a second predictor supplies readable text, enabling visual lookahead for GUI-agent planning.", "topics": ["world-models", "planning", "mobile-navigation"], "updated_at": "2025-05-20", "url": "https://arxiv.org/abs/2504.13936"}
{"aliases": [], "authors": ["Biao Yi", "Xavier Hu", "Yurun Chen", "Shengyu Zhang", "Hongxia Yang", "Fan Wu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8f5fdf474c1cb0d7e9f42d617de27afae38a9fd8f5e0b07d1c86e082dc872a35", "submitted_at": "2025-05-08T17:31:20Z", "updated_at": "2025-11-17T09:12:00Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.05440v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "kind", "scope", "environments", "topics", "summary", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}], "id": "arxiv:2505.05440", "identifiers": {"arxiv": "2505.05440"}, "kind": "paper", "last_verified_at": "2026-10-18T04:21:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.05440"}], "name": "EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation", "notes": "Reviewed against the complete official arXiv abstract. Experimental results and linked artifact availability have not been independently reproduced.", "published_at": "2025-05-08", "relations": [], "review_status": "curated", "scope": "core", "summary": "EcoAgent splits mobile automation between cloud planning and on-device observation and verification. Compact screen descriptions and feedback reduce communication costs, with evaluation on AndroidWorld.", "topics": ["mobile-navigation", "planning", "efficiency"], "updated_at": "2025-11-17", "url": "https://arxiv.org/abs/2505.05440"}
{"aliases": [], "authors": ["Shanhui Zhao", "Hao Wen", "Wenjie Du", "Cheng Liang", "Yunxin Liu", "Xiaozhou Ye", "Ye Ouyang", "Yuanchun Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "08cc5be720ac4e82560ad6b7549f4c38c24603d23d9d051894d1078c247059e2", "submitted_at": "2025-05-15T05:28:35Z", "updated_at": "2025-05-15T05:28:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.10593v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "kind", "scope", "environments", "topics", "summary", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}], "id": "arxiv:2505.10593", "identifiers": {"arxiv": "2505.10593"}, "kind": "paper", "last_verified_at": "2026-10-18T04:21:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.10593"}], "name": "LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps", "notes": "Reviewed against the complete official arXiv abstract. Experimental results and linked artifact availability have not been independently reproduced.", "published_at": "2025-05-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "LLM-Explorer uses language models to maintain compact knowledge for mobile app exploration, then generates actions without invoking the model at every step. The study compares exploration coverage and cost across twenty apps.", "topics": ["mobile-navigation", "efficiency"], "updated_at": "2025-05-15", "url": "https://arxiv.org/abs/2505.10593"}
{"aliases": [], "authors": ["Weikai Xu", "Zhizheng Jiang", "Yuxuan Liu", "Pengzhi Gao", "Wei Liu", "Jian Luan", "Yuanchun Li", "Yunxin Liu", "Bin Wang", "Bo An"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5ca1ebfdd5a96e146d37539294462c7fb67bf20deaf77307de37aa3bb1dde082", "submitted_at": "2025-05-17T07:58:34Z", "updated_at": "2026-02-02T06:55:10Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.11891v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}], "id": "arxiv:2505.11891", "identifiers": {"arxiv": "2505.11891"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:42Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.11891"}], "name": "Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "Mobile-Bench-v2 evaluates mobile GUI agents using multiple acceptable offline action paths, noisy interfaces with ads or pop-ups, and ambiguous instructions with scripted clarification exchanges. These splits separate step-level execution, robustness, and proactive interaction.", "topics": ["evaluation", "mobile-navigation", "robustness", "human-in-the-loop"], "updated_at": "2026-02-02", "url": "https://arxiv.org/abs/2505.11891"}
{"aliases": [], "authors": ["Kun Huang", "Weikai Xu", "Yuxuan Liu", "Quandong Wang", "Pengzhi Gao", "Wei Liu", "Jian Luan", "Bin Wang", "Bo An"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9bc92029e16b5afb4b54837d2ab2304c7b8176548061c9deafdca101754128dc", "submitted_at": "2025-05-18T08:28:05Z", "updated_at": "2026-03-21T09:25:27Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2505.12299v4"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}], "id": "arxiv:2505.12299", "identifiers": {"arxiv": "2505.12299"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:42Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.12299"}], "name": "MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-18", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileIPL samples trees of action-planning thoughts, propagates rule-based leaf rewards backward, and forms preference pairs for reasoning-level optimization. It also expands screenshot-based instruction data through staged evolution before evaluation on mobile GUI-agent benchmarks.", "topics": ["mobile-navigation", "reinforcement-learning", "planning", "data-generation"], "updated_at": "2026-03-21", "url": "https://arxiv.org/abs/2505.12299"}
{"aliases": [], "authors": ["Longxi Gao", "Li Zhang", "Pengzhi Gao", "Wei Liu", "Jian Luan", "Mengwei Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "10d826ea7715ab7054522a9dcba622d5dae3e6c3faee421e4b168e16104d184b", "submitted_at": "2025-05-18T16:34:30Z", "updated_at": "2025-10-10T09:28:53Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.12493v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2505.12493", "identifiers": {"arxiv": "2505.12493"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.12493"}], "name": "GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-18", "relations": [], "review_status": "curated", "scope": "core", "summary": "GUI-Shift trains an inverse-dynamics task that predicts the initial action connecting two GUI states, using trajectories without natural-language instructions. It combines rule-based reinforcement learning with data filtering and evaluates transfer to Android automation and screenshot grounding.", "topics": ["reinforcement-learning", "data-generation", "grounding", "mobile-navigation"], "updated_at": "2025-10-10", "url": "https://arxiv.org/abs/2505.12493"}
{"aliases": [], "authors": ["Yunseok Jang", "Yeda Song", "Sungryull Sohn", "Lajanugen Logeswaran", "Tiange Luo", "Dong-Ki Kim", "Kyunghoon Bae", "Honglak Lee"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "64672e6a3450256a8b04d9db231e885e2dd4e8688235f6c7853d70d6276610ff", "submitted_at": "2025-05-19T02:39:03Z", "updated_at": "2025-05-19T02:39:03Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.12632v1"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}], "id": "arxiv:2505.12632", "identifiers": {"arxiv": "2505.12632"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:42Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.12632"}], "name": "Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-19", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces MONDAY and an automated pipeline that extracts mobile-navigation training data from instructional videos across operating-system platforms.", "topics": ["video", "data-generation", "mobile-navigation"], "updated_at": "2025-05-19", "url": "https://arxiv.org/abs/2505.12632"}
{"aliases": [], "authors": ["Liangxuan Wu", "Chao Wang", "Tianming Liu", "Yanjie Zhao", "Haoyu Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9657a66aebe46151ed56bf76131ffe45f52459c1cf0e000907113776c91259d9", "submitted_at": "2025-05-19T11:17:46Z", "updated_at": "2025-05-20T07:02:05Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2505.12981v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:08Z", "role": "primary", "sha256": "00d275cd5407cec847fa9d43fe73cfc4384c5570b68a5e058c97921799be0bec", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2302.01560%2C2303.16563%2C2305.15486%2C2305.16291%2C2305.17144%2C2306.00003%2C2306.00349%2C2306.17882%2C2310.01557%2C2310.08235%2C2310.08367%2C2311.05997%2C2311.17600%2C2312.02519%2C2312.11865%2C2402.01118%2C2402.10196%2C2402.11208%2C2403.10249%2C2403.12037%2C2404.06647%2C2404.12241%2C2404.13246%2C2407.15325%2C2409.00138%2C2410.14573%2C2410.18927%2C2410.19012%2C2411.09523%2C2411.10349%2C2411.13543%2C2412.01547%2C2501.05366%2C2501.09004%2C2502.07463%2C2502.14538%2C2503.02732%2C2503.08175%2C2503.11387%2C2504.10147%2C2504.11703%2C2504.14064%2C2504.15810%2C2504.16208%2C2504.20635%2C2504.21776%2C2505.12981%2C2505.13076%2C2506.01616%2C2506.13205&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:08Z", "role": "primary", "sha256": "00d275cd5407cec847fa9d43fe73cfc4384c5570b68a5e058c97921799be0bec", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2302.01560%2C2303.16563%2C2305.15486%2C2305.16291%2C2305.17144%2C2306.00003%2C2306.00349%2C2306.17882%2C2310.01557%2C2310.08235%2C2310.08367%2C2311.05997%2C2311.17600%2C2312.02519%2C2312.11865%2C2402.01118%2C2402.10196%2C2402.11208%2C2403.10249%2C2403.12037%2C2404.06647%2C2404.12241%2C2404.13246%2C2407.15325%2C2409.00138%2C2410.14573%2C2410.18927%2C2410.19012%2C2411.09523%2C2411.10349%2C2411.13543%2C2412.01547%2C2501.05366%2C2501.09004%2C2502.07463%2C2502.14538%2C2503.02732%2C2503.08175%2C2503.11387%2C2504.10147%2C2504.11703%2C2504.14064%2C2504.15810%2C2504.16208%2C2504.20635%2C2504.21776%2C2505.12981%2C2505.13076%2C2506.01616%2C2506.13205&max_results=50"}], "id": "arxiv:2505.12981", "identifiers": {"arxiv": "2505.12981"}, "kind": "paper", "last_verified_at": "2026-10-18T10:54:08Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.12981"}], "name": "From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-19", "relations": [], "review_status": "curated", "scope": "core", "summary": "Analyzes security vulnerabilities across OEM system-level, third-party, and research mobile LLM agents, covering GUI and cross-application attack surfaces.", "topics": ["safety-security", "mobile-navigation", "evaluation"], "updated_at": "2025-05-20", "url": "https://arxiv.org/abs/2505.12981"}
{"aliases": [], "authors": ["Fanglin Mo", "Junzhe Chen", "Haoxuan Zhu", "Xuming Hu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "de6c501a42c3828bdf795ac59c38b982e738c38bd5d0c59cfb6cb10b51e39292", "submitted_at": "2025-05-20T09:45:55Z", "updated_at": "2025-05-20T09:45:55Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.14141v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2505.14141", "identifiers": {"arxiv": "2505.14141"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.14141"}], "name": "Building a Stable Planner: An Extended Finite State Machine Based Planning Module for Mobile GUI Agent", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "SPlanner models mobile-app functions and configurations with extended finite-state machines, traverses them to construct execution paths, and converts those paths into natural-language plans. A VLM follows these plans to perform GUI actions, with evaluation on AndroidWorld.", "topics": ["planning", "mobile-navigation"], "updated_at": "2025-05-20", "url": "https://arxiv.org/abs/2505.14141"}
{"aliases": [], "authors": ["Pengzhou Cheng", "Haowen Hu", "Zheng Wu", "Zongru Wu", "Tianjie Ju", "Zhuosheng Zhang", "Gongshen Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "815345ed44d70f40ce9784c212d269ffaaa476e5c2ea5cdbbaaeb98d22eba3cb", "submitted_at": "2025-05-20T14:29:18Z", "updated_at": "2026-06-15T06:42:51Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.14418v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2505.14418", "identifiers": {"arxiv": "2505.14418"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.14418"}], "name": "Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents", "notes": "Reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2025-05-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "Studies backdoor risks in mobile GUI agents through AgentGhost, which combines goal-level and interaction-history triggers during model training. The paper evaluates multiple mobile agents and a tailored defense.", "topics": ["safety-security", "mobile-navigation", "interaction-history"], "updated_at": "2026-06-15", "url": "https://arxiv.org/abs/2505.14418"}
{"aliases": [], "authors": ["Xiaoran Yin", "Xu Luo", "Hao Wu", "Lianli Gao", "Jingkuan Song"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "93c67222fb0f581e9f9cb3ff59c8d28faec9dc037180060ad5ac962b4469144c", "submitted_at": "2025-05-22T09:08:47Z", "updated_at": "2025-09-05T02:24:00Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.16422v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "kind", "scope", "environments", "topics", "summary", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}], "id": "arxiv:2505.16422", "identifiers": {"arxiv": "2505.16422"}, "kind": "paper", "last_verified_at": "2026-10-18T04:21:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.16422"}], "name": "Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach", "notes": "Reviewed against the complete official arXiv abstract. Experimental results and linked artifact availability have not been independently reproduced.", "published_at": "2025-05-22", "relations": [], "review_status": "curated", "scope": "core", "summary": "FPWC builds and refines a task-oriented world model before planning mobile-device actions. It executes plans as code and evaluates the approach in simulated environments and on real mobile devices.", "topics": ["world-models", "planning", "mobile-navigation"], "updated_at": "2025-09-05", "url": "https://arxiv.org/abs/2505.16422"}
{"aliases": [], "authors": ["Bin Xie", "Rui Shao", "Gongwei Chen", "Kaiwen Zhou", "Yinchuan Li", "Jie Liu", "Min Zhang", "Liqiang Nie"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "641001c49fccac1e1c0659fe765eba5a30cefd2a7ff5d00c821f79092c45a1df", "submitted_at": "2025-05-22T16:01:06Z", "updated_at": "2025-05-22T16:01:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.16827v1"}, "publication": {"authors": ["Bin Xie", "Rui Shao", "Gongwei Chen", "Kaiwen Zhou", "Yinchuan Li", "Jie Liu", "Min Zhang", "Liqiang Nie"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.acl-long.282", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.282/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "5650-5667", "pdf_url": "https://aclanthology.org/2025.acl-long.282.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.282/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:59Z", "role": "primary", "sha256": "40babce7d310777fa65a498c170320124d4d4941f2cb46ad0ff04aae3583e02f", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2025.acl-long.282/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2505.16827", "identifiers": {"arxiv": "2505.16827"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.16827"}, {"rel": "publication", "url": "https://aclanthology.org/2025.acl-long.282/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2025.acl-long.282.pdf"}], "name": "GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-22", "relations": [], "review_status": "curated", "scope": "core", "summary": "GUI-explorer generates exploration goals from screenshots and interface structure, then mines observation-action-outcome triples for app-specific transition knowledge. The resulting training-free agent uses this knowledge during mobile task execution, evaluated on SPA-Bench and AndroidWorld.", "topics": ["mobile-navigation", "data-generation", "memory", "planning"], "updated_at": "2025-05-22", "url": "https://arxiv.org/abs/2505.16827"}
{"aliases": [], "authors": ["Qinzhuo Wu", "Pengzhi Gao", "Wei Liu", "Jian Luan"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d2d51388193e19501b580740969a6e08661c6e0a2cf09e2489c46fe4f19209cd", "submitted_at": "2025-05-27T03:09:06Z", "updated_at": "2025-05-27T03:09:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.20660v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2505.20660", "identifiers": {"arxiv": "2505.20660"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.20660"}], "name": "BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "BacktrackAgent adds verification, judgment, and reflection modules to detect erroneous GUI actions and guide recovery. It develops backtracking-oriented training data that includes post-action pages and evaluates task completion and step accuracy on Mobile3M and Auto-UI.", "topics": ["robustness", "planning", "data-generation", "mobile-navigation"], "updated_at": "2025-05-27", "url": "https://arxiv.org/abs/2505.20660"}
{"aliases": [], "authors": ["Han Xiao", "Guozhi Wang", "Yuxiang Chai", "Zimu Lu", "Weifeng Lin", "Hao He", "Lue Fan", "Liuyang Bian", "Rui Hu", "Liang Liu", "Shuai Ren", "Yafei Wen", "Xiaoxin Chen", "Aojun Zhou", "Hongsheng Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f19671a527de76b702e68311656e42feea88249716f68911a41ec80be205e4c", "submitted_at": "2025-05-27T17:58:06Z", "updated_at": "2025-05-27T17:58:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.21496v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2505.21496", "identifiers": {"arxiv": "2505.21496"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.21496"}], "name": "UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "UI-Genie jointly improves a mobile GUI agent and a reward model that processes screenshots with interaction history and supplies action- and task-level feedback. Its data pipeline uses rule-based verification, corrupted trajectories, and hard negatives to support reward-guided exploration and iterative training.", "topics": ["data-generation", "reinforcement-learning", "mobile-navigation", "interaction-history"], "updated_at": "2025-05-27", "url": "https://arxiv.org/abs/2505.21496"}
{"aliases": [], "authors": ["Linqiang Guo", "Wei Liu", "Yi Wen Heng", "Tse-Hsun", "Chen", "Yang Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f0ec81429fb39e56414d3bfe621df6c6adf461e63fc1a1c8886ea2b6850b8ee", "submitted_at": "2025-05-29T16:08:51Z", "updated_at": "2025-11-19T16:48:16Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.23596v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T07:54:03Z", "role": "primary", "sha256": "13d5969845070cd2877dc51ae5300c2d623e5daef00c8a1552ffa46af3f721a5", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2401.05507%2C2406.07275%2C2409.16427%2C2410.00079%2C2503.07701%2C2503.22738%2C2505.15859%2C2505.17735%2C2505.23596%2C2507.05257%2C2507.06134%2C2507.21953%2C2507.23336%2C2508.06960%2C2508.08997%2C2509.02473%2C2509.23694%2C2510.09116%2C2510.14438%2C2511.18423%2C2512.12818%2C2512.13564%2C2601.10758%2C2601.12449%2C2601.21841%2C2603.01152%2C2603.19993%2C2603.20576%2C2604.04503%2C2604.17562%2C2604.23941%2C2605.16265%2C2606.06448%2C2606.06462%2C2606.29193%2C2607.01647%2C2607.13157&max_results=37"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T07:54:03Z", "role": "primary", "sha256": "13d5969845070cd2877dc51ae5300c2d623e5daef00c8a1552ffa46af3f721a5", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2401.05507%2C2406.07275%2C2409.16427%2C2410.00079%2C2503.07701%2C2503.22738%2C2505.15859%2C2505.17735%2C2505.23596%2C2507.05257%2C2507.06134%2C2507.21953%2C2507.23336%2C2508.06960%2C2508.08997%2C2509.02473%2C2509.23694%2C2510.09116%2C2510.14438%2C2511.18423%2C2512.12818%2C2512.13564%2C2601.10758%2C2601.12449%2C2601.21841%2C2603.01152%2C2603.19993%2C2603.20576%2C2604.04503%2C2604.17562%2C2604.23941%2C2605.16265%2C2606.06448%2C2606.06462%2C2606.29193%2C2607.01647%2C2607.13157&max_results=37"}], "id": "arxiv:2505.23596", "identifiers": {"arxiv": "2505.23596"}, "kind": "paper", "last_verified_at": "2026-10-16T07:54:03Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.23596"}], "name": "Agent-SAMA: State-Aware Mobile Assistant", "notes": "Hugging Face discovery used the label MAPLE for this ID; the record follows the current primary arXiv title, Agent-SAMA. The secondary-title discrepancy is not treated as proof of a historical rename. Experiments not independently reproduced.", "published_at": "2025-05-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "Models mobile application execution as a finite-state machine to support planning, verification, and recovery across interface transitions.", "topics": ["planning", "memory", "mobile-navigation"], "updated_at": "2025-11-19", "url": "https://arxiv.org/abs/2505.23596"}
{"aliases": [], "authors": ["Zhong Zhang", "Yaxi Lu", "Yikun Fu", "Yupeng Huo", "Shenzhi Yang", "Yesai Wu", "Han Si", "Xin Cong", "Haotian Chen", "Yankai Lin", "Jie Xie", "Wei Zhou", "Wang Xu", "Yuanheng Zhang", "Zhou Su", "Zhongwu Zhai", "Xiaoming Liu", "Yudong Mei", "Jianming Xu", "Hongyan Tian", "Chongyi Wang", "Chi Chen", "Yuan Yao", "Zhiyuan Liu", "Maosong Sun"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3c0b2a065898ba4f73fcb5e5b2e92d723b0b55ac6caa46d5bf02d44eb7a2cdd9", "submitted_at": "2025-06-02T07:30:29Z", "updated_at": "2025-06-17T02:57:04Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2506.01391v2"}, "publication": {"authors": ["Zhong Zhang", "Yaxi Lu", "Yikun Fu", "Yupeng Huo", "Shenzhi Yang", "Yesai Wu", "Han Si (司函)", "Xin Cong", "Haotian Chen", "Yankai Lin (林衍凯)", "Jie Xie", "Wei Zhou", "Wang Xu", "Yuanheng Zhang", "Zhou Su", "Zhongwu Zhai", "Xiaoming Liu", "Yudong Mei", "Jianming Xu", "Hongyan Tian", "Chongyi Wang", "Chi Chen", "Yuan Yao", "Zhiyuan Liu", "Maosong Sun (孙茂松)"], "date_basis": "Explicit publisher citation_publication_date: 2025/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 11], "doi": "10.18653/v1/2025.emnlp-demos.12", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.emnlp-demos.12/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "155-180", "pdf_url": "https://aclanthology.org/2025.emnlp-demos.12.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning", "type": "conference-paper", "url": "https://aclanthology.org/2025.emnlp-demos.12/", "venue": "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", "volume": null}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:09:59Z", "role": "primary", "sha256": "5de5a828e06a63c1627b8ad9f9a46c1643d8b4b7d8ed6156fd9790b6bd083155", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://aclanthology.org/2025.emnlp-demos.12/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}], "id": "arxiv:2506.01391", "identifiers": {"arxiv": "2506.01391"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:42Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2506.01391"}, {"rel": "publication", "url": "https://aclanthology.org/2025.emnlp-demos.12/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2025.emnlp-demos.12.pdf"}], "name": "AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning", "notes": "Summary and topic tags reviewed against the primary abstract. Reported experiments, task counts, and artifact availability are not independently reproduced.", "published_at": "2025-06-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines grounding pretraining, bilingual interaction trajectories, and reinforcement fine-tuning for mobile GUI actions.", "topics": ["reinforcement-learning", "mobile-navigation"], "updated_at": "2025-06-17", "url": "https://arxiv.org/abs/2506.01391"}
{"aliases": [], "authors": ["Shengcheng Yu", "Yuchen Ling", "Chunrong Fang", "Quan Zhou", "Yi Zhao", "Chunyang Chen", "Shaomin Zhu", "Zhenyu Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bad447e8bca06f720a9476492de06978c73a356a38b00671203f8af0b81f1952", "submitted_at": "2025-06-05T14:27:40Z", "updated_at": "2026-05-03T08:25:53Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2506.05079v4"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "kind", "scope", "environments", "topics", "summary", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}], "id": "arxiv:2506.05079", "identifiers": {"arxiv": "2506.05079"}, "kind": "paper", "last_verified_at": "2026-10-18T04:21:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2506.05079"}], "name": "Scenario-Guided LLM-based Mobile App GUI Testing", "notes": "Reviewed against the complete official arXiv abstract. Experimental results and linked artifact availability have not been independently reproduced.", "published_at": "2025-06-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "ScenGen organizes mobile GUI testing around business scenarios rather than unrestricted exploration. Five collaborating agents observe the interface, choose and execute actions, check scenario completion, and record operations and runtime bugs.", "topics": ["automation", "mobile-navigation", "planning"], "updated_at": "2026-05-03", "url": "https://arxiv.org/abs/2506.05079"}
{"aliases": [], "authors": ["Ruofan Liu", "Xiwen Teoh", "Yun Lin", "Guanjie Chen", "Ruofei Ren", "Denys Poshyvanyk", "Jin Song Dong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bea3e76b3124ebbcd8f7817b3e32d667d8aaae6e31f1b75ac3fc8c39e7637c6f", "submitted_at": "2025-06-09T03:09:48Z", "updated_at": "2025-06-09T03:09:48Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2506.07385v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T07:57:51Z", "role": "primary", "sha256": "b91987360225499418fcd3645d7d5effac91e8202bf7c7e17c9f9e31d25b5be8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2506.01423%2C2506.03231%2C2506.04301%2C2506.05336%2C2506.07385%2C2506.07398%2C2506.08136%2C2506.08837%2C2506.10953%2C2506.11425%2C2506.11763%2C2506.13538%2C2506.14683%2C2506.15461%2C2506.18959%2C2506.19502%2C2506.20668%2C2506.21252%2C2506.21495%2C2506.21614%2C2507.01599%2C2507.02279%2C2507.02825%2C2507.04036%2C2507.07400%2C2507.09481%2C2507.09884%2C2507.13348%2C2507.14447%2C2507.16704%2C2507.19902%2C2507.21678%2C2507.22925%2C2508.01548%2C2508.02866%2C2508.04002%2C2508.04389%2C2508.05193%2C2508.05294%2C2508.05748%2C2508.07871%2C2508.07999%2C2508.08228%2C2508.09124%2C2508.09981%2C2508.15804%2C2508.16153%2C2508.17398%2C2508.18489%2C2508.19611&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:20:30Z", "role": "primary", "sha256": "23030fd266519162c51c7f4a87bc38e75bb171ef7fa95e30c2d7afd820a0bc3f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/2506.07385v1"}], "id": "arxiv:2506.07385", "identifiers": {"arxiv": "2506.07385"}, "kind": "paper", "last_verified_at": "2026-10-17T11:20:30Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2506.07385"}], "name": "GUIPilot: A Consistency-based Mobile GUI Testing Approach for Detecting Application-specific Bugs", "notes": "Reviewed against the exact-version official arXiv abstract page; its complete title, ordered author list, visible version, and normalized abstract SHA match the retained snapshot. The original API response body was not locally available. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2025-06-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces GUIPilot, which compares mobile design mock-ups with implemented screens through widget alignment and tests expected transitions by executing inferred UI actions. It evaluates both visual inconsistencies and workflow-specific bugs.", "topics": ["evaluation", "mobile-navigation", "robustness"], "updated_at": "2025-06-09", "url": "https://arxiv.org/abs/2506.07385"}
{"aliases": [], "authors": ["Penghao Wu", "Shengnan Ma", "Bo Wang", "Jiaheng Yu", "Lewei Lu", "Ziwei Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ce3b7d2c25b5a99f110f00be7389d4230d625ac1f7f33d5ab81f3d6f441f3610", "submitted_at": "2025-06-09T17:59:57Z", "updated_at": "2025-06-09T17:59:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2506.08012v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}], "id": "arxiv:2506.08012", "identifiers": {"arxiv": "2506.08012"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:42Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2506.08012"}], "name": "GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-06-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "GUI-Reflection synthesizes reflection and error-correction examples from successful trajectories and adds dedicated learning stages for these behaviors. It introduces a reflection task suite, a mobile environment for online data collection, and iterative reflection tuning.", "topics": ["robustness", "data-generation", "evaluation", "mobile-navigation"], "updated_at": "2025-06-09", "url": "https://arxiv.org/abs/2506.08012"}
{"aliases": [], "authors": ["Yuan Guo", "Tingjia Miao", "Zheng Wu", "Pengzhou Cheng", "Ming Zhou", "Zhuosheng Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8dbc84aa582b94775d490cf84e17eff05be84af7dbcc2de7de61b886fa3c9178", "submitted_at": "2025-06-10T16:45:29Z", "updated_at": "2025-06-10T16:45:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2506.08972v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}], "id": "arxiv:2506.08972", "identifiers": {"arxiv": "2506.08972"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:42Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2506.08972"}], "name": "Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-06-10", "relations": [], "review_status": "curated", "scope": "core", "summary": "UI-NEXUS evaluates compositional mobile tasks in local utility apps and online Chinese and English service apps. AGENT-NEXUS decomposes those long tasks into self-contained atomic subtasks to study generalization beyond isolated screens or short action chains.", "topics": ["evaluation", "long-horizon", "planning", "mobile-navigation"], "updated_at": "2025-06-10", "url": "https://arxiv.org/abs/2506.08972"}
{"aliases": [], "authors": ["Yuquan Xie", "Zaijing Li", "Rui Shao", "Gongwei Chen", "Kaiwen Zhou", "Yinchuan Li", "Dongmei Jiang", "Liqiang Nie"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9b353606ce29a5bc60d263e86827a825af46883e25da5bd290b48affa9dd3838", "submitted_at": "2025-06-12T06:21:19Z", "updated_at": "2025-06-12T06:21:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2506.10387v1"}}, "environments": ["android", "web", "cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2506.10387", "identifiers": {"arxiv": "2506.10387"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2506.10387"}], "name": "Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-06-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "Mirage-1 organizes interaction trajectories into execution, core, and meta-skills, then uses them to guide Monte Carlo tree search during online GUI tasks. It introduces AndroidLH for long-horizon evaluation and tests the approach on Android and web-navigation benchmarks.", "topics": ["planning", "memory", "long-horizon", "mobile-navigation", "web-navigation"], "updated_at": "2025-06-12", "url": "https://arxiv.org/abs/2506.10387"}
{"aliases": [], "authors": ["Xuan Wang", "Siyuan Liang", "Zhe Liu", "Yi Yu", "Aishan Liu", "Yuliang Lu", "Xitong Gao", "Ee-Chien Chang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "390304ce515886fa15fb8cd74d8b2df161a75b9adc0f4d2fad1f65976c6a6ce7", "submitted_at": "2025-06-16T08:09:32Z", "updated_at": "2025-09-05T14:19:03Z", "version": 6, "versioned_url": "https://arxiv.org/abs/2506.13205v6"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:08Z", "role": "primary", "sha256": "00d275cd5407cec847fa9d43fe73cfc4384c5570b68a5e058c97921799be0bec", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2302.01560%2C2303.16563%2C2305.15486%2C2305.16291%2C2305.17144%2C2306.00003%2C2306.00349%2C2306.17882%2C2310.01557%2C2310.08235%2C2310.08367%2C2311.05997%2C2311.17600%2C2312.02519%2C2312.11865%2C2402.01118%2C2402.10196%2C2402.11208%2C2403.10249%2C2403.12037%2C2404.06647%2C2404.12241%2C2404.13246%2C2407.15325%2C2409.00138%2C2410.14573%2C2410.18927%2C2410.19012%2C2411.09523%2C2411.10349%2C2411.13543%2C2412.01547%2C2501.05366%2C2501.09004%2C2502.07463%2C2502.14538%2C2503.02732%2C2503.08175%2C2503.11387%2C2504.10147%2C2504.11703%2C2504.14064%2C2504.15810%2C2504.16208%2C2504.20635%2C2504.21776%2C2505.12981%2C2505.13076%2C2506.01616%2C2506.13205&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:08Z", "role": "primary", "sha256": "00d275cd5407cec847fa9d43fe73cfc4384c5570b68a5e058c97921799be0bec", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2302.01560%2C2303.16563%2C2305.15486%2C2305.16291%2C2305.17144%2C2306.00003%2C2306.00349%2C2306.17882%2C2310.01557%2C2310.08235%2C2310.08367%2C2311.05997%2C2311.17600%2C2312.02519%2C2312.11865%2C2402.01118%2C2402.10196%2C2402.11208%2C2403.10249%2C2403.12037%2C2404.06647%2C2404.12241%2C2404.13246%2C2407.15325%2C2409.00138%2C2410.14573%2C2410.18927%2C2410.19012%2C2411.09523%2C2411.10349%2C2411.13543%2C2412.01547%2C2501.05366%2C2501.09004%2C2502.07463%2C2502.14538%2C2503.02732%2C2503.08175%2C2503.11387%2C2504.10147%2C2504.11703%2C2504.14064%2C2504.15810%2C2504.16208%2C2504.20635%2C2504.21776%2C2505.12981%2C2505.13076%2C2506.01616%2C2506.13205&max_results=50"}], "id": "arxiv:2506.13205", "identifiers": {"arxiv": "2506.13205"}, "kind": "paper", "last_verified_at": "2026-10-18T10:54:08Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2506.13205"}], "name": "Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-06-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "Demonstrates clean-text visual backdoor attacks (VIBMA) that compromise fine-tuned VLM mobile agents through visual triggers while keeping text instructions intact.", "topics": ["safety-security", "mobile-navigation", "robustness"], "updated_at": "2025-09-05", "url": "https://arxiv.org/abs/2506.13205"}
{"aliases": [], "authors": ["Jihao Gu", "Qihang Ai", "Yingyao Wang", "Pi Bu", "Jingxuan Xing", "Zekun Zhu", "Wei Jiang", "Ziming Wang", "Yingxiu Zhao", "Ming-Liang Zhang", "Jun Song", "Yuning Jiang", "Bo Zheng"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9620eb7d8fa5f5c2a318ff516d45b8a4cfd35cf0c235b96bab3bba4e5a6aab9b", "submitted_at": "2025-06-25T11:34:43Z", "updated_at": "2026-04-25T13:54:32Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2506.20332v4"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}], "id": "arxiv:2506.20332", "identifiers": {"arxiv": "2506.20332"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2506.20332"}], "name": "Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-06-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses a staged curriculum from response-format alignment through action feedback to interactive task-level training for mobile agents.", "topics": ["reinforcement-learning", "mobile-navigation"], "updated_at": "2026-04-25", "url": "https://arxiv.org/abs/2506.20332"}
{"aliases": [], "authors": ["Siyuan Liang", "Tianmeng Fang", "Zhe Liu", "Aishan Liu", "Yan Xiao", "Jinyuan He", "Ee-Chien Chang", "Xiaochun Cao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "78dd523ad6123fe1ee5164685a3853719c9a4442adac8661050f147ff6a9f619", "submitted_at": "2025-07-01T15:10:00Z", "updated_at": "2025-07-01T15:10:00Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2507.00841v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:01:16.030926+00:00", "role": "primary", "sha256": "4dcd1ba66ba21c0f2cb2aeb00c8bcab7c0cee4da37ff2fa6c16b45066aaa9db0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:01:16.030926+00:00", "role": "primary", "sha256": "4dcd1ba66ba21c0f2cb2aeb00c8bcab7c0cee4da37ff2fa6c16b45066aaa9db0", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:10:56.912207+00:00", "role": "primary", "sha256": "a25da6700a238167d5e9915cf6fb3a4bcd910cefc300f4be6eed56271be26f00", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/pdf/2507.00841v1"}], "id": "arxiv:2507.00841", "identifiers": {"arxiv": "2507.00841"}, "kind": "paper", "last_verified_at": "2026-10-18T10:01:16.030926+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2507.00841"}], "name": "SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents", "notes": "The reviewed evaluation uses Android emulation and a specific MobileSafetyBench-derived setup. Its judge and score threshold are evaluator choices, not universal safety measurements, and its task population is not the whole later MobileSafetyBench corpus. No results were reproduced. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (II.B Defense objective; III Chain-level guard and GPTJudge; IV.B Evaluation setup; V.D Judge validity); not an entire-paper reading or reproduction claim.", "published_at": "2025-07-01", "relations": [], "review_status": "curated", "scope": "core", "summary": "Studies chain-level risk detection for mobile multimodal agents and a language-model-assisted evaluator, assessing safety interventions together with functional preservation.", "topics": ["safety-security", "evaluation", "mobile-navigation"], "updated_at": "2025-07-01", "url": "https://arxiv.org/abs/2507.00841"}
{"aliases": [], "authors": ["Gongwei Chen", "Xurui Zhou", "Rui Shao", "Yibo Lyu", "Kaiwen Zhou", "Shuai Wang", "Wentao Li", "Yinchuan Li", "Zhongang Qi", "Liqiang Nie"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "774e2515b563f75d4561daaa6a4b672423d917a3f50e98308ab448e2ae0731e5", "submitted_at": "2025-07-04T17:37:15Z", "updated_at": "2025-07-04T17:37:15Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2507.03730v1"}}, "environments": ["web", "cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2507.03730", "identifiers": {"arxiv": "2507.03730"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2507.03730"}], "name": "Less is More: Empowering GUI Agent with Context-Aware Simplification", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-07-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "SimpAgent prunes distracting interface elements with visual masks and compresses interaction history using consistency-based guidance. The study evaluates these two forms of context reduction during GUI navigation in web and mobile environments.", "topics": ["efficiency", "interaction-history", "web-navigation", "mobile-navigation"], "updated_at": "2025-07-04", "url": "https://arxiv.org/abs/2507.03730"}
{"aliases": [], "authors": ["Guohong Liu", "Jialei Ye", "Jiacheng Liu", "Yuanchun Li", "Wei Liu", "Pengzhi Gao", "Jian Luan", "Yunxin Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "85ebf8b3b5916e66e4b4221c73bb29519156c41e8d1695bcc46d275dd50cf58d", "submitted_at": "2025-07-06T03:31:36Z", "updated_at": "2026-04-14T14:47:25Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2507.04227v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2507.04227", "identifiers": {"arxiv": "2507.04227"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2507.04227"}], "name": "Mobile GUI Agents under Real-world Threats: Are We There Yet?", "notes": "Reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2025-07-06", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces an app-content instrumentation framework and complementary interactive and static test suites for mobile GUI agents. It studies how untrusted third-party content changes task execution and state understanding.", "topics": ["mobile-navigation", "safety-security", "evaluation"], "updated_at": "2026-04-14", "url": "https://arxiv.org/abs/2507.04227"}
{"aliases": [], "authors": ["Yucheng Shi", "Wenhao Yu", "Zaitang Li", "Yonglin Wang", "Hongming Zhang", "Ninghao Liu", "Haitao Mi", "Dong Yu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "45d36dd32b30bf4faee6d9a72e3cdfe91edff465bbd886bdfc3c27c3da475b82", "submitted_at": "2025-07-08T07:07:53Z", "updated_at": "2025-07-08T07:07:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2507.05720v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2507.05720", "identifiers": {"arxiv": "2507.05720"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2507.05720"}], "name": "MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-07-08", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileGUI-RL constructs an online training curriculum through agent exploration and task filtering. It adapts GRPO with trajectory-aware advantages and rewards for task completion and execution efficiency, evaluated on three online mobile-agent benchmarks.", "topics": ["mobile-navigation", "reinforcement-learning", "data-generation", "efficiency"], "updated_at": "2025-07-08", "url": "https://arxiv.org/abs/2507.05720"}
{"aliases": [], "authors": ["Ning Li", "Xiangmou Qu", "Jiamu Zhou", "Jun Wang", "Muning Wen", "Kounianhua Du", "Xingyu Lou", "Qiuying Peng", "Jun Wang", "Weinan Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6d58a188742fef5862b299c1dcf17bb6be139e81aafd3d2e1bdbe26f88001384", "submitted_at": "2025-07-21T09:37:05Z", "updated_at": "2025-07-21T09:37:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2507.16853v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2507.16853", "identifiers": {"arxiv": "2507.16853"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2507.16853"}], "name": "MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-07-21", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileUse reflects on errors at action and task timescales, invoking reflection when needed and using proactive exploration to learn unfamiliar apps. It evaluates this mobile execution framework on AndroidWorld and AndroidLab and describes a toolkit for physical-device operation.", "topics": ["mobile-navigation", "self-reflection", "robustness", "long-horizon"], "updated_at": "2025-07-21", "url": "https://arxiv.org/abs/2507.16853"}
{"aliases": [], "authors": ["Qinglong Yang", "Haoming Li", "Haotian Zhao", "Xiaokai Yan", "Jingtao Ding", "Fengli Xu", "Yong Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "947c85efc189635a118b823b8ca0787ff6b1c922d1af8b21a8686b7df9a27cf8", "submitted_at": "2025-06-09T06:38:41Z", "updated_at": "2026-03-16T09:14:01Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2507.21071v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T17:11:36Z", "role": "primary", "sha256": "90a03448678a584f29ef11ae2afe1ef7040b4f3658c492f6e48eafe8fb6d2fa2", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}], "id": "arxiv:2507.21071", "identifiers": {"arxiv": "2507.21071"}, "kind": "paper", "last_verified_at": "2026-10-17T17:11:36Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2507.21071"}], "name": "FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2025-06-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "FingerTip 20K gathers 20K human Android demonstrations from users' long-term everyday app use, with user context, to evaluate proactive task suggestion and preference-aware task execution.", "topics": ["evaluation", "data-generation", "mobile-navigation", "interaction-history"], "updated_at": "2026-03-16", "url": "https://arxiv.org/abs/2507.21071"}
{"aliases": [], "authors": ["Yi Kong", "Dianxi Shi", "Guoli Yang", "Zhang ke-di", "Chenlin Huang", "Xiaopeng Li", "Songchang Jin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "197dbb0e2734f30349260444fca80a8ac830a5d4000a677d6417f46509737475", "submitted_at": "2025-07-29T16:05:32Z", "updated_at": "2025-07-29T16:05:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2507.21953v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T07:54:03Z", "role": "primary", "sha256": "13d5969845070cd2877dc51ae5300c2d623e5daef00c8a1552ffa46af3f721a5", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2401.05507%2C2406.07275%2C2409.16427%2C2410.00079%2C2503.07701%2C2503.22738%2C2505.15859%2C2505.17735%2C2505.23596%2C2507.05257%2C2507.06134%2C2507.21953%2C2507.23336%2C2508.06960%2C2508.08997%2C2509.02473%2C2509.23694%2C2510.09116%2C2510.14438%2C2511.18423%2C2512.12818%2C2512.13564%2C2601.10758%2C2601.12449%2C2601.21841%2C2603.01152%2C2603.19993%2C2603.20576%2C2604.04503%2C2604.17562%2C2604.23941%2C2605.16265%2C2606.06448%2C2606.06462%2C2606.29193%2C2607.01647%2C2607.13157&max_results=37"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T07:54:03Z", "role": "primary", "sha256": "13d5969845070cd2877dc51ae5300c2d623e5daef00c8a1552ffa46af3f721a5", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2401.05507%2C2406.07275%2C2409.16427%2C2410.00079%2C2503.07701%2C2503.22738%2C2505.15859%2C2505.17735%2C2505.23596%2C2507.05257%2C2507.06134%2C2507.21953%2C2507.23336%2C2508.06960%2C2508.08997%2C2509.02473%2C2509.23694%2C2510.09116%2C2510.14438%2C2511.18423%2C2512.12818%2C2512.13564%2C2601.10758%2C2601.12449%2C2601.21841%2C2603.01152%2C2603.19993%2C2603.20576%2C2604.04503%2C2604.17562%2C2604.23941%2C2605.16265%2C2606.06448%2C2606.06462%2C2606.29193%2C2607.01647%2C2607.13157&max_results=37"}], "id": "arxiv:2507.21953", "identifiers": {"arxiv": "2507.21953"}, "kind": "paper", "last_verified_at": "2026-10-16T07:54:03Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2507.21953"}], "name": "MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation", "notes": "Editorial summary based on the primary paper abstract; experiments and released artifacts have not been independently reproduced.", "published_at": "2025-07-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "Builds reusable page memories from past mobile trajectories and retrieves them to support task planning and execution.", "topics": ["memory", "planning", "mobile-navigation"], "updated_at": "2025-07-29", "url": "https://arxiv.org/abs/2507.21953"}
{"aliases": [], "authors": ["Liujian Tang", "Shaokang Dong", "Yijia Huang", "Minqi Xiang", "Hongtao Ruan", "Bin Wang", "Shuo Li", "Zhiheng Xi", "Zhihui Cao", "Hailiang Pang", "Heng Kong", "He Yang", "Mingxu Chai", "Zhilin Gao", "Xingyu Liu", "Yingnan Fu", "Jiaming Liu", "Xuanjing Huang", "Yu-Gang Jiang", "Tao Gui", "Qi Zhang", "Kang Wang", "Yunke Zhang", "Yuran Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d5175e5ed0061660fa950512300daa878eb90e5c98bdac8f80d478414b0a2931", "submitted_at": "2025-07-19T12:33:43Z", "updated_at": "2025-09-11T14:28:11Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2508.03700v5"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2508.03700", "identifiers": {"arxiv": "2508.03700"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2508.03700"}], "name": "MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-07-19", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines a mobile GUI data pipeline, perception and planning capabilities, and reinforcement fine-tuning for interactive task execution.", "topics": ["mobile-navigation", "data-generation", "reinforcement-learning"], "updated_at": "2025-09-11", "url": "https://arxiv.org/abs/2508.03700"}
{"aliases": [], "authors": ["Chao Hao", "Shuai Wang", "Kaiwen Zhou"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "499a462f9f14b8afdd367bb7cf7a7ffb1b2e166c212fb5c36686d3145f08ab5f", "submitted_at": "2025-08-06T02:38:02Z", "updated_at": "2025-08-06T02:38:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2508.04025v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2508.04025", "identifiers": {"arxiv": "2508.04025"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2508.04025"}], "name": "Uncertainty-Aware GUI Agent: Adaptive Perception through Component Recommendation and Human-in-the-Loop Refinement", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-08-06", "relations": [], "review_status": "curated", "scope": "core", "summary": "RecAgent narrows attention to recommended UI components and requests user feedback when task intent or decisions remain uncertain. It introduces ComplexAction to evaluate specified single-step GUI actions in difficult interface scenarios.", "topics": ["mobile-navigation", "human-in-the-loop", "screen-understanding", "evaluation"], "updated_at": "2025-08-06", "url": "https://arxiv.org/abs/2508.04025"}
{"aliases": [], "authors": ["Zeyu Huang", "Juyuan Wang", "Longfeng Chen", "Boyi Xiao", "Leng Cai", "Yawen Zeng", "Jin Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d4efa329c3b106219c9b25f675be0c561743085ac999d2964458a5f22ff6e62f", "submitted_at": "2025-08-12T16:18:30Z", "updated_at": "2025-08-14T16:36:45Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.09057v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}], "id": "arxiv:2508.09057", "identifiers": {"arxiv": "2508.09057"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2508.09057"}], "name": "MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Unethical Instructions", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-08-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "MVISU-Bench evaluates bilingual mobile tasks involving cross-app work, vague requests, user interaction and unethical instructions alongside ordinary single-app tasks. Its Aider prompting module is designed to clarify intent and mitigate risky execution within agent workflows.", "topics": ["evaluation", "mobile-navigation", "human-in-the-loop", "safety-security"], "updated_at": "2025-08-14", "url": "https://arxiv.org/abs/2508.09057"}
{"aliases": [], "authors": ["Songqin Nong", "Xiaoxuan Tang", "Jingxuan Xu", "Sheng Zhou", "Jianfeng Chen", "Tao Jiang", "Wenhao Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ea849d8e7640d7a40d582431233418cf1cbd29585ca6c78638919b8832265445", "submitted_at": "2025-08-15T09:55:02Z", "updated_at": "2026-03-13T11:10:50Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.11360v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:52Z", "role": "primary", "sha256": "0b730323b2ce85c39aa7d534665901a480ff06540c73f1f80832fcc0735b8789", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2310.08588%2C2402.09205%2C2406.05720%2C2407.21075%2C2410.07166%2C2503.03743%2C2508.04037%2C2508.10833%2C2508.11360%2C2508.13024%2C2508.13186%2C2508.14104%2C2509.01619%2C2509.01720%2C2509.02322%2C2509.04198%2C2509.07764%2C2509.21823%2C2509.22256%2C2509.23263%2C2509.23866%2C2509.25047%2C2509.26539%2C2510.00413%2C2510.00536%2C2510.01524%2C2510.02204%2C2510.02250%2C2510.02418%2C2510.03204%2C2510.03612%2C2510.04039%2C2510.04373%2C2510.04607%2C2510.06223%2C2510.06607%2C2510.09872%2C2510.10666%2C2510.11035%2C2510.11221%2C2510.11892%2C2510.13543%2C2510.15455%2C2510.15863%2C2510.16252%2C2510.18113%2C2510.18314%2C2510.19205%2C2510.22732%2C2511.06101&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:52Z", "role": "primary", "sha256": "0b730323b2ce85c39aa7d534665901a480ff06540c73f1f80832fcc0735b8789", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2310.08588%2C2402.09205%2C2406.05720%2C2407.21075%2C2410.07166%2C2503.03743%2C2508.04037%2C2508.10833%2C2508.11360%2C2508.13024%2C2508.13186%2C2508.14104%2C2509.01619%2C2509.01720%2C2509.02322%2C2509.04198%2C2509.07764%2C2509.21823%2C2509.22256%2C2509.23263%2C2509.23866%2C2509.25047%2C2509.26539%2C2510.00413%2C2510.00536%2C2510.01524%2C2510.02204%2C2510.02250%2C2510.02418%2C2510.03204%2C2510.03612%2C2510.04039%2C2510.04373%2C2510.04607%2C2510.06223%2C2510.06607%2C2510.09872%2C2510.10666%2C2510.11035%2C2510.11221%2C2510.11892%2C2510.13543%2C2510.15455%2C2510.15863%2C2510.16252%2C2510.18113%2C2510.18314%2C2510.19205%2C2510.22732%2C2511.06101&max_results=50"}], "id": "arxiv:2508.11360", "identifiers": {"arxiv": "2508.11360"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2508.11360"}], "name": "CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-08-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "CRAFT-GUI organizes GUI trajectories by difficulty for curriculum-based GRPO training. Its reward combines rule-based signals with model judgments, with evaluation on Android Control and an internal online benchmark.", "topics": ["reinforcement-learning", "reward-models", "mobile-navigation"], "updated_at": "2026-03-13", "url": "https://arxiv.org/abs/2508.11360"}
{"aliases": [], "authors": ["Jiabo Ye", "Xi Zhang", "Haiyang Xu", "Haowei Liu", "Junyang Wang", "Zhaoqing Zhu", "Ziwei Zheng", "Feiyu Gao", "Junjie Cao", "Zhengxi Lu", "Jitong Liao", "Qi Zheng", "Fei Huang", "Jingren Zhou", "Ming Yan"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "629421d60bb8beeba3f087854ebaddc5461f9af0e5fb0bc572d0c20394ba9dcd", "submitted_at": "2025-08-21T00:39:12Z", "updated_at": "2025-09-01T05:38:34Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.15144v2"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}], "id": "arxiv:2508.15144", "identifiers": {"arxiv": "2508.15144"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2508.15144"}], "name": "Mobile-Agent-v3: Fundamental Agents for GUI Automation", "notes": "Summary and topic tags reviewed against the primary abstract. Reported experiments, task counts, and artifact availability are not independently reproduced.", "published_at": "2025-08-21", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces GUI-Owl models and Mobile-Agent-v3 orchestration, using environment-generated trajectories to support GUI capabilities.", "topics": ["data-generation", "planning", "mobile-navigation"], "updated_at": "2025-09-01", "url": "https://arxiv.org/abs/2508.15144"}
{"aliases": [], "authors": ["Xin Wang", "Zhiyao Cui", "Hao Li", "Ya Zeng", "Chenxu Wang", "Ruiqi Song", "Yihang Chen", "Kun Shao", "Qiaosheng Zhang", "Jinzhuo Liu", "Siyue Ren", "Shuyue Hu", "Zhen Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "57d5fc98a2eb2232f237d71b34060df0acef89cfeaa4bc247580a4dda3223e0b", "submitted_at": "2025-08-25T13:57:02Z", "updated_at": "2025-08-25T13:57:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2508.18040v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:01:10.946679+00:00", "role": "primary", "sha256": "594b5261dd2039777d36c46cdb8525d973ad57a154b902ff1a171bcbed2c64cc", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:01:10.946679+00:00", "role": "primary", "sha256": "594b5261dd2039777d36c46cdb8525d973ad57a154b902ff1a171bcbed2c64cc", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:18:36.598801+00:00", "role": "primary", "sha256": "3c3474b771af7bdd500e6aaa91b83d39ec0d455e59bb83df906e7a94700ad2b7", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/pdf/2508.18040v1"}], "id": "arxiv:2508.18040", "identifiers": {"arxiv": "2508.18040"}, "kind": "paper", "last_verified_at": "2026-10-18T10:01:10.946679+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2508.18040"}], "name": "PerPilot: Personalizing VLM-based Mobile Agents via Memory and Exploration", "notes": "Personalization depends on the validity of stored or inferred user information and retrieval access. This is instruction completion with interaction, not demonstrated permanent model-weight personalization. No specific operating system or reproduced result is asserted. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (The Framework of PerPilot; Personalization Perception; Personalization Completion; PerInstruct Data Construction); not an entire-paper reading or reproduction claim.", "published_at": "2025-08-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces PerPilot and the PerInstruct dataset for completing user-specific mobile instructions through memory retrieval, app exploration, and clarification when missing context remains unresolved.", "topics": ["memory", "planning", "human-in-the-loop", "mobile-navigation"], "updated_at": "2025-08-25", "url": "https://arxiv.org/abs/2508.18040"}
{"aliases": [], "authors": ["Zhixin Lin", "Jungang Li", "Shidong Pan", "Yibo Shi", "Yue Yao", "Dongliang Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "815c8c1fa5993d2ef58798abd43a2b8945c476c27c777d30c1cbfacadd87af84", "submitted_at": "2025-08-27T00:41:28Z", "updated_at": "2025-09-03T07:48:34Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.19493v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}], "id": "arxiv:2508.19493", "identifiers": {"arxiv": "2508.19493"}, "kind": "paper", "last_verified_at": "2026-10-18T10:54:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2508.19493"}], "name": "Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-08-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces SAPA-Bench with 7,138 smartphone scenarios to evaluate whether MLLM-powered mobile agents detect and protect sensitive personal information on screen.", "topics": ["safety-security", "mobile-navigation", "evaluation"], "updated_at": "2025-09-03", "url": "https://arxiv.org/abs/2508.19493"}
{"aliases": [], "authors": ["Qihang Ai", "Pi Bu", "Yue Cao", "Yingyao Wang", "Jihao Gu", "Jingxuan Xing", "Zekun Zhu", "Wei Jiang", "Zhicheng Zheng", "Jun Song", "Yuning Jiang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "385ed1b6e60c27660f0cbf281b0f2bbde052691801f7faae99cc053dfbc0d127", "submitted_at": "2025-08-27T08:40:05Z", "updated_at": "2026-04-25T13:29:08Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.19679v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}], "id": "arxiv:2508.19679", "identifiers": {"arxiv": "2508.19679"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2508.19679"}], "name": "InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-08-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "InquireMobile trains mobile agents to seek human confirmation at critical decisions using staged reinforcement fine-tuning and pre-action reasoning. InquireBench evaluates safe interaction and proactive inquiry, distinguishing asking for help from completing the underlying task.", "topics": ["human-in-the-loop", "reinforcement-learning", "evaluation", "mobile-navigation"], "updated_at": "2026-04-25", "url": "https://arxiv.org/abs/2508.19679"}
{"aliases": [], "authors": ["Ziyi Guan", "Jason Chun Lok Li", "Zhijian Hou", "Pingping Zhang", "Donglai Xu", "Yuzhi Zhao", "Mengyang Wu", "Jinpeng Chen", "Thanh-Toan Nguyen", "Pengfei Xian", "Wenao Ma", "Shengchao Qin", "Graziano Chesi", "Ngai Wong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c22f63bb5de22dd922ba37ea45df9404def017fee492e8ade03c83ab8b4f9b58", "submitted_at": "2025-08-30T05:32:32Z", "updated_at": "2025-08-30T05:32:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.00366v1"}}, "environments": ["android", "web", "desktop", "cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2509.00366", "identifiers": {"arxiv": "2509.00366"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2509.00366"}], "name": "KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-08-30", "relations": [], "review_status": "curated", "scope": "core", "summary": "KG-RAG converts UI transition graphs into a searchable vector store and uses intent-guided retrieval to construct actionable navigation paths. It introduces KG-Android-Bench and KG-Harmony-Bench and evaluates transfer from mobile apps to web and desktop tasks.", "topics": ["memory", "planning", "mobile-navigation", "evaluation"], "updated_at": "2025-08-30", "url": "https://arxiv.org/abs/2509.00366"}
{"aliases": [], "authors": ["Cheng Zhang", "Erhu Feng", "Xi Zhao", "Yisheng Zhao", "Wangbo Gong", "Jiahui Sun", "Dong Du", "Zhichao Hua", "Yubin Xia", "Haibo Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dbf26f28382245db085fd48f15e905bfa31f1c289a9a7f0799d35440069b442a", "submitted_at": "2025-08-30T15:24:47Z", "updated_at": "2025-08-30T15:24:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.00531v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T07:57:56Z", "role": "primary", "sha256": "3429cc2fc7737050cac964c976293fc4793e52c5913636c1f67d04243fbefb6a", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.20410%2C2508.20890%2C2508.21456%2C2509.00088%2C2509.00531%2C2509.00969%2C2509.01684%2C2509.03536%2C2509.04018%2C2509.04908%2C2509.05368%2C2509.05831%2C2509.06917%2C2509.07098%2C2509.07553%2C2509.08820%2C2509.10345%2C2509.10540%2C2509.11253%2C2509.12543%2C2509.12987%2C2509.13615%2C2509.14547%2C2509.14744%2C2509.15061%2C2509.15237%2C2509.17336%2C2509.19185%2C2509.19199%2C2509.21072%2C2509.21291%2C2509.21766%2C2509.21799%2C2509.22715%2C2509.22830%2C2509.23738%2C2509.24704%2C2509.25455%2C2509.25693%2C2510.00172%2C2510.00515%2C2510.02190%2C2510.04491%2C2510.05096%2C2510.05156%2C2510.05788%2C2510.07284%2C2510.07915%2C2510.08787%2C2510.09517&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:20:43Z", "role": "primary", "sha256": "b61937e1f046c4158b92c2f9d34dddea52a757f0e49b79f30efd73db24484abe", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/2509.00531v1"}], "id": "arxiv:2509.00531", "identifiers": {"arxiv": "2509.00531"}, "kind": "paper", "last_verified_at": "2026-10-17T11:20:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2509.00531"}], "name": "MobiAgent: A Systematic Framework for Customizable Mobile Agents", "notes": "Reviewed against the exact-version official arXiv abstract page; its complete title, ordered author list, visible version, and normalized abstract SHA match the retained snapshot. The original API response body was not locally available. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2025-08-30", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents MobiAgent, combining MobiMind agent models, the AgentRR acceleration framework, and MobiFlow evaluation. It also introduces an AI-assisted data-collection pipeline for mobile GUI tasks.", "topics": ["mobile-navigation", "efficiency", "data-generation"], "updated_at": "2025-08-30", "url": "https://arxiv.org/abs/2509.00531"}
{"aliases": [], "authors": ["Georgios Papoudakis", "Thomas Coste", "Jianye Hao", "Jun Wang", "Kun Shao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "44c49412776ec9837a08d3d8347214495ffbda14a391c7fa67ad780a0eac9577", "submitted_at": "2025-09-01T18:55:27Z", "updated_at": "2025-11-13T01:26:20Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.01720v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:52Z", "role": "primary", "sha256": "0b730323b2ce85c39aa7d534665901a480ff06540c73f1f80832fcc0735b8789", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2310.08588%2C2402.09205%2C2406.05720%2C2407.21075%2C2410.07166%2C2503.03743%2C2508.04037%2C2508.10833%2C2508.11360%2C2508.13024%2C2508.13186%2C2508.14104%2C2509.01619%2C2509.01720%2C2509.02322%2C2509.04198%2C2509.07764%2C2509.21823%2C2509.22256%2C2509.23263%2C2509.23866%2C2509.25047%2C2509.26539%2C2510.00413%2C2510.00536%2C2510.01524%2C2510.02204%2C2510.02250%2C2510.02418%2C2510.03204%2C2510.03612%2C2510.04039%2C2510.04373%2C2510.04607%2C2510.06223%2C2510.06607%2C2510.09872%2C2510.10666%2C2510.11035%2C2510.11221%2C2510.11892%2C2510.13543%2C2510.15455%2C2510.15863%2C2510.16252%2C2510.18113%2C2510.18314%2C2510.19205%2C2510.22732%2C2511.06101&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:52Z", "role": "primary", "sha256": "0b730323b2ce85c39aa7d534665901a480ff06540c73f1f80832fcc0735b8789", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2310.08588%2C2402.09205%2C2406.05720%2C2407.21075%2C2410.07166%2C2503.03743%2C2508.04037%2C2508.10833%2C2508.11360%2C2508.13024%2C2508.13186%2C2508.14104%2C2509.01619%2C2509.01720%2C2509.02322%2C2509.04198%2C2509.07764%2C2509.21823%2C2509.22256%2C2509.23263%2C2509.23866%2C2509.25047%2C2509.26539%2C2510.00413%2C2510.00536%2C2510.01524%2C2510.02204%2C2510.02250%2C2510.02418%2C2510.03204%2C2510.03612%2C2510.04039%2C2510.04373%2C2510.04607%2C2510.06223%2C2510.06607%2C2510.09872%2C2510.10666%2C2510.11035%2C2510.11221%2C2510.11892%2C2510.13543%2C2510.15455%2C2510.15863%2C2510.16252%2C2510.18113%2C2510.18314%2C2510.19205%2C2510.22732%2C2511.06101&max_results=50"}], "id": "arxiv:2509.01720", "identifiers": {"arxiv": "2509.01720"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2509.01720"}], "name": "Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-09-01", "relations": [], "review_status": "curated", "scope": "core", "summary": "Succeed or Learn Slowly applies direct off-policy updates to successful interactions and more conservative regularized updates to negative examples. Successful Transition Replay prioritizes successful experience during policy learning, with evaluation on AndroidWorld.", "topics": ["reinforcement-learning", "mobile-navigation", "efficiency"], "updated_at": "2025-11-13", "url": "https://arxiv.org/abs/2509.01720"}
{"aliases": [], "authors": ["Jingru Fan", "Yufan Dang", "Jingyao Wu", "Huatao Li", "Runde Yang", "Xiyuan Yang", "Yuheng Wang", "Chen Qian"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "49a887b12b3395821aa100a66e61aac808309ef947ae752475df3d2db9a4fcd8", "submitted_at": "2025-09-02T15:48:21Z", "updated_at": "2025-10-17T00:57:58Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.02444v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:01:10.946679+00:00", "role": "primary", "sha256": "594b5261dd2039777d36c46cdb8525d973ad57a154b902ff1a171bcbed2c64cc", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:01:10.946679+00:00", "role": "primary", "sha256": "594b5261dd2039777d36c46cdb8525d973ad57a154b902ff1a171bcbed2c64cc", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:14:33.619660+00:00", "role": "primary", "sha256": "6c2591dad8893f87cffdea211584a3733dc2137dafa9416c1885d1b0126fd540", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/pdf/2509.02444v2"}], "id": "arxiv:2509.02444", "identifiers": {"arxiv": "2509.02444"}, "kind": "paper", "last_verified_at": "2026-10-18T10:01:10.946679+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2509.02444"}], "name": "AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent", "notes": "Trace reuse assumes stable layouts and fixed tasks. The described function-call routes are user-selected, and coordinate calibration depends on valid detected widgets. No particular operating-system coverage, latency guarantee or reproduced result is asserted. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (4.2 OCR/OR Region Localization; 4.2.2 Coordinate Calibration; 4.3 Multi-Agent Voting; 5.2 Task Decomposition; 6.2 Experience Reuse; 6.3 Function Calling); not an entire-paper reading or reproduction claim.", "published_at": "2025-09-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "Describes a mobile-agent stack combining region-based coordinate correction, hierarchical task planning, multi-agent voting, and reuse of successful interaction traces.", "topics": ["planning", "grounding", "workflow", "mobile-navigation", "long-horizon"], "updated_at": "2025-10-17", "url": "https://arxiv.org/abs/2509.02444"}
{"aliases": [], "authors": ["Gowen Loo", "Chang Liu", "Qinghong Yin", "Xiang Chen", "Jiawei Chen", "Jingyuan Zhang", "Yu Tian"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a8b2db00f62afe350e55e2266b3627de9b0cf089178b0cf80eb13b06275eee15", "submitted_at": "2025-09-04T05:22:42Z", "updated_at": "2025-09-04T05:22:42Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.03891v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}], "id": "arxiv:2509.03891", "identifiers": {"arxiv": "2509.03891"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2509.03891"}], "name": "MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-09-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileRAG combines retrieval and memory components to support mobile tasks that need external knowledge or long action sequences. MobileRAG-Eval is introduced to study these requirements on complex real-world app tasks.", "topics": ["memory", "mobile-navigation", "evaluation", "long-horizon"], "updated_at": "2025-09-04", "url": "https://arxiv.org/abs/2509.03891"}
{"aliases": [], "authors": ["Pengxiang Zhao", "Guangyi Liu", "YaoZhen Liang", "Weiqing He", "Zhengxi Lu", "WenHao Wang", "Yuehao Huang", "Yuxiang Chai", "Zhaolu Kang", "Yaxuan Guo", "Hao Wang", "Kexin Zhang", "Liang Liu", "Yong Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9b1e0e807f5f396bfd9108ab6cfacd48ed4780abfb792589da0b41d7d246c717", "submitted_at": "2025-09-08T09:43:48Z", "updated_at": "2026-04-15T11:26:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.06477v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2509.06477", "identifiers": {"arxiv": "2509.06477"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2509.06477"}], "name": "MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-09-08", "relations": [], "review_status": "curated", "scope": "core", "summary": "MAS-Bench evaluates mobile agents that combine GUI actions with APIs, deep links, and reusable scripts. Its 139 tasks across 11 apps test use of 88 predefined shortcuts as well as the ability to generate new reusable workflows.", "topics": ["evaluation", "mobile-navigation", "tool-integration", "workflow"], "updated_at": "2026-04-15", "url": "https://arxiv.org/abs/2509.06477"}
{"aliases": [], "authors": ["Zhengxi Lu", "Jiabo Ye", "Fei Tang", "Yongliang Shen", "Haiyang Xu", "Ziwei Zheng", "Weiming Lu", "Ming Yan", "Fei Huang", "Jun Xiao", "Yueting Zhuang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1e31638e531aff49fe59bef6e80b35069b1f851ea0cbf1901130557148df4783", "submitted_at": "2025-09-15T03:24:08Z", "updated_at": "2025-09-24T15:05:34Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.11543v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}], "id": "arxiv:2509.11543", "identifiers": {"arxiv": "2509.11543"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2509.11543"}], "name": "UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-09-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "UI-S1 simulates multi-turn online learning over offline trajectories, using a patch module to recover divergences while retaining the model’s own outputs in context. It combines discounted future returns with step- and episode-level advantages and introduces a semi-online performance proxy.", "topics": ["reinforcement-learning", "evaluation", "mobile-navigation"], "updated_at": "2025-09-24", "url": "https://arxiv.org/abs/2509.11543"}
{"aliases": [], "authors": ["Yifan Xu", "Xiao Liu", "Xinghan Liu", "Jiaqi Fu", "Hanchen Zhang", "Bohao Jing", "Shudan Zhang", "Yuting Wang", "Wenyi Zhao", "Yuxiao Dong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "86bce7c1a120e0e953a239f2a9b39a04a844e6f9710525245d643932ec3c3233", "submitted_at": "2025-09-10T13:09:27Z", "updated_at": "2025-10-24T17:13:05Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.18119v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2509.18119", "identifiers": {"arxiv": "2509.18119"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2509.18119"}], "name": "MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-09-10", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileRL adapts GRPO to mobile GUI training with difficulty-dependent replay of successes and filtering of failure curricula. A shortest-path reward adjustment accounts for task length, with evaluations on AndroidWorld and AndroidLab.", "topics": ["reinforcement-learning", "mobile-navigation", "efficiency"], "updated_at": "2025-10-24", "url": "https://arxiv.org/abs/2509.18119"}
{"aliases": [], "authors": ["Ran Xu", "Kaixin Ma", "Wenhao Yu", "Hongming Zhang", "Joyce C. Ho", "Carl Yang", "Dong Yu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e1c6fd3e84212bac4c4c8341ffb3478c97becce08f92dac89e5de77ad42cd07d", "submitted_at": "2025-09-29T02:04:20Z", "updated_at": "2025-09-29T02:04:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.24183v1"}}, "environments": ["web", "android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:20:58+00:00", "role": "primary", "sha256": "fe9f70994c119a85cb8075461174e9699c423d79094e611f1ac95a51666600c1", "supports": ["summary", "environments", "scope"], "url": "https://arxiv.org/html/2509.24183v1"}], "id": "arxiv:2509.24183", "identifiers": {"arxiv": "2509.24183"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2509.24183"}], "name": "Retrieval-augmented GUI Agents with Generative Guidelines", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-09-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "RAG-GUI trains a small guidance adapter to filter and summarize retrieved web tutorials while keeping the acting agent fixed. Supervised and rejection-sampling stages prepare the adapter for inference-time assistance, tested on offline web/mobile tasks and interactive Android tasks.", "topics": ["memory", "planning", "imitation-learning", "web-navigation", "mobile-navigation"], "updated_at": "2025-09-29", "url": "https://arxiv.org/abs/2509.24183"}
{"aliases": [], "authors": ["Zikang Liu", "Junyi Li", "Wayne Xin Zhao", "Dawei Gao", "Yaliang Li", "Ji-rong Wen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "277315ecc1a341c0a511bce84b87190fc0aeeb2306666ea8d4746aa8e9b39984", "submitted_at": "2025-10-01T01:48:39Z", "updated_at": "2025-10-04T15:23:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.00413v2"}}, "environments": ["web", "cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2510.00413", "identifiers": {"arxiv": "2510.00413"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.00413"}], "name": "PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-10-01", "relations": [], "review_status": "curated", "scope": "core", "summary": "PAL-UI combines observation/action summaries with selective retrieval of historical screenshots during planning. It trains mobile navigation models from step-level supervision and evaluates transfer to web navigation without additional training.", "topics": ["memory", "planning", "interaction-history", "mobile-navigation"], "updated_at": "2025-10-04", "url": "https://arxiv.org/abs/2510.00413"}
{"aliases": [], "authors": ["Shang Ma", "Xusheng Xiao", "Yanfang Ye"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4bf0a561460c080b14da6fd13f6d92781e01e52b08dc691fe019e70b88e44c86", "submitted_at": "2025-10-07T15:36:04Z", "updated_at": "2026-09-27T17:25:57Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2510.06042v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:01:10.946679+00:00", "role": "primary", "sha256": "594b5261dd2039777d36c46cdb8525d973ad57a154b902ff1a171bcbed2c64cc", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:01:10.946679+00:00", "role": "primary", "sha256": "594b5261dd2039777d36c46cdb8525d973ad57a154b902ff1a171bcbed2c64cc", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:14:29.861666+00:00", "role": "primary", "sha256": "5e2cb2f053983140904ec15c097d060ff18315c6c3c956bbcacbec26921709c5", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/pdf/2510.06042v3"}], "id": "arxiv:2510.06042", "identifiers": {"arxiv": "2510.06042"}, "kind": "paper", "last_verified_at": "2026-10-18T10:01:10.946679+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.06042"}], "name": "Agent+P: Guiding UI Agents via Symbolic Planning", "notes": "Planning guarantees are relative to the modeled graph and selected target. They do not establish complete graphs, correct grounding or faithful goal translation. The described design depends on static source analysis; no experiments were reproduced. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (3.3 UI Automation to Classical Planning; 4.1 UTG Builder; 4.2 Node Selector; 4.3 Plan Generator; 4.4 UI Explorer; 5.1 Datasets); not an entire-paper reading or reproduction claim.", "published_at": "2025-10-07", "relations": [], "review_status": "curated", "scope": "core", "summary": "Guides UI agents with symbolic planning over a UI transition graph initialized from app-code analysis and updated through online exploration, with evaluation on AndroidWorld.", "topics": ["planning", "long-horizon", "mobile-navigation"], "updated_at": "2026-09-27", "url": "https://arxiv.org/abs/2510.06042"}
{"aliases": [], "authors": ["Renhua Ding", "Xiao Yang", "Zhengwei Fang", "Jun Luo", "Kun He", "Jun Zhu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e80999148931b7485d51ef87887d06240f813747a9739282ed0daf53a912f9f6", "submitted_at": "2025-10-09T05:34:57Z", "updated_at": "2026-04-09T01:41:48Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2510.07809v4"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}], "id": "arxiv:2510.07809", "identifiers": {"arxiv": "2510.07809"}, "kind": "paper", "last_verified_at": "2026-10-18T10:54:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.07809"}], "name": "Invisible to Humans, Triggered by Agents: Stealthy Jailbreak Attacks on Mobile Vision-Language Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-10-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses the near-zero contact-touch signals of automated mobile agents to expose malicious visual content selectively during agent interactions. The paper combines this agent-only perceptual injection with HG-IDA* prompt optimization to study unauthorized cross-app actions.", "topics": ["safety-security", "mobile-navigation", "robustness"], "updated_at": "2026-04-09", "url": "https://arxiv.org/abs/2510.07809"}
{"aliases": [], "authors": ["Haitao Jia", "Ming He", "Zimo Yin", "Likang Wu", "Jianping Fan", "Jitao Sang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9460a0926936d3db23c36c6c0e069d664265a8a9513c08c1a04f5a49970d6567", "submitted_at": "2025-10-09T09:22:05Z", "updated_at": "2025-10-09T09:22:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.07988v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2510.07988", "identifiers": {"arxiv": "2510.07988"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.07988"}], "name": "ReInAgent: A Context-Aware GUI Agent Enabling Human-in-the-Loop Mobile Task Navigation", "notes": "Reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2025-10-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces ReInAgent, coordinating information management, planning, and reflection around a shared memory for mobile tasks. It proactively asks users for information and checks consistency when instructions are ambiguous or change during execution.", "topics": ["human-in-the-loop", "memory", "mobile-navigation"], "updated_at": "2025-10-09", "url": "https://arxiv.org/abs/2510.07988"}
{"aliases": [], "authors": ["Zhe Wu", "Hongjin Lu", "Junliang Xing", "Changhao Zhang", "Yuxuan Li", "Yin Zhu", "Yuhao Yang", "Yuheng Jing", "Kai Li", "Kun Shao", "Jianye Hao", "Jun Wang", "Yuanchun Shi"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "95fd3e1286ed49d569b05644d77f822ea9747cfb4769cb7cb93f39c9271cf57e", "submitted_at": "2025-10-16T07:38:21Z", "updated_at": "2026-02-06T02:04:25Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.14388v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T07:57:59Z", "role": "primary", "sha256": "240e3d6528900f4a3e87f12f5e55cb7654a4d25d4478e291e9bbf725e7013118", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2510.10587%2C2510.10909%2C2510.11144%2C2510.12798%2C2510.14388%2C2510.14513%2C2510.14969%2C2510.16156%2C2510.17017%2C2510.17800%2C2510.19207%2C2510.19247%2C2510.19386%2C2510.19864%2C2510.20333%2C2510.21652%2C2510.22443%2C2510.22936%2C2510.23730%2C2510.23883%2C2510.24702%2C2510.25726%2C2510.26328%2C2510.27135%2C2510.27410%2C2511.00153%2C2511.02650%2C2511.02687%2C2511.03690%2C2511.04220%2C2511.05797%2C2511.06251%2C2511.08319%2C2511.08487%2C2511.10110%2C2511.13725%2C2511.14210%2C2511.14945%2C2511.15705%2C2511.16842%2C2511.17649%2C2511.17775%2C2511.19496%2C2511.19516%2C2511.20636%2C2511.21990%2C2511.22074%2C2512.04302%2C2512.04529%2C2512.06726&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:20:56Z", "role": "primary", "sha256": "fecd42f8ca75572410c354c892734cb8eefbd3fa622064f6bc6db0f535cf5607", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/2510.14388v2"}], "id": "arxiv:2510.14388", "identifiers": {"arxiv": "2510.14388"}, "kind": "paper", "last_verified_at": "2026-10-17T11:20:56Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.14388"}], "name": "Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control", "notes": "Reviewed against the exact-version official arXiv abstract page; its complete title, ordered author list, visible version, and normalized abstract SHA match the retained snapshot. The original API response body was not locally available. Experimental results and artifact availability have not been independently reproduced. This Hi-Agent has a distinct author team and method from the earlier HiAgent working-memory paper; the shared project-name prefix is not treated as an identity match.", "published_at": "2025-10-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Hi-Agent, jointly training a high-level reasoning model and a low-level mobile action model. Execution feedback supplies a foresight advantage for optimizing subgoal decisions, with evaluations on Android control benchmarks.", "topics": ["planning", "reinforcement-learning", "mobile-navigation"], "updated_at": "2026-02-06", "url": "https://arxiv.org/abs/2510.14388"}
{"aliases": [], "authors": ["Yuanyi Song", "Heyuan Huang", "Qiqiang Lin", "Yin Zhao", "Xiangmou Qu", "Jun Wang", "Xingyu Lou", "Weiwen Liu", "Zhuosheng Zhang", "Jun Wang", "Yong Yu", "Weinan Zhang", "Zhaoxiang Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fc45dc62068c971cd831fc3db64bd3d8995d4e5fd60e9c83953476d4fb24f7f3", "submitted_at": "2025-10-16T12:30:05Z", "updated_at": "2025-10-16T12:30:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.14621v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:52Z", "role": "primary", "sha256": "8623b0ff7ef9d2e8ba484cd67359e7b8817e78e9ca22b8f27432c2533f5b90a0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2510.01670%2C2510.04673%2C2510.10073%2C2510.12200%2C2510.14621%2C2510.16051%2C2510.17790%2C2510.18488%2C2510.18596%2C2510.19488%2C2510.19949%2C2510.20286%2C2510.22009%2C2510.24168%2C2510.24411%2C2510.24563%2C2511.00810%2C2511.04307%2C2511.07332%2C2511.09157%2C2511.12254%2C2511.13087%2C2511.15567%2C2511.16590%2C2511.19663%2C2511.20597%2C2511.20766%2C2512.08529%2C2512.10371%2C2512.10962%2C2512.12634%2C2512.14014%2C2512.15431%2C2512.16295%2C2512.16501%2C2512.19432%2C2512.22894%2C2512.24965%2C2601.02399%2C2601.06031%2C2601.07181%2C2601.07262%2C2601.07779%2C2601.08406%2C2601.09923%2C2601.11044%2C2601.11868%2C2601.12822%2C2601.13060%2C2601.15876&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:52Z", "role": "primary", "sha256": "8623b0ff7ef9d2e8ba484cd67359e7b8817e78e9ca22b8f27432c2533f5b90a0", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2510.01670%2C2510.04673%2C2510.10073%2C2510.12200%2C2510.14621%2C2510.16051%2C2510.17790%2C2510.18488%2C2510.18596%2C2510.19488%2C2510.19949%2C2510.20286%2C2510.22009%2C2510.24168%2C2510.24411%2C2510.24563%2C2511.00810%2C2511.04307%2C2511.07332%2C2511.09157%2C2511.12254%2C2511.13087%2C2511.15567%2C2511.16590%2C2511.19663%2C2511.20597%2C2511.20766%2C2512.08529%2C2512.10371%2C2512.10962%2C2512.12634%2C2512.14014%2C2512.15431%2C2512.16295%2C2512.16501%2C2512.19432%2C2512.22894%2C2512.24965%2C2601.02399%2C2601.06031%2C2601.07181%2C2601.07262%2C2601.07779%2C2601.08406%2C2601.09923%2C2601.11044%2C2601.11868%2C2601.12822%2C2601.13060%2C2601.15876&max_results=50"}], "id": "arxiv:2510.14621", "identifiers": {"arxiv": "2510.14621"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.14621"}], "name": "ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-10-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "ColorBench represents mobile tasks as graphs of states collected from real devices, providing a quasi-dynamic environment with multiple valid paths and error paths. It evaluates single-app and cross-app tasks using completion, subtask progress, and atomic diagnostics.", "topics": ["evaluation", "mobile-navigation", "long-horizon", "state-tracking"], "updated_at": "2025-10-16", "url": "https://arxiv.org/abs/2510.14621"}
{"aliases": [], "authors": ["Gucongcong Fan", "Chaoyue Niu", "Chengfei Lyu", "Fan Wu", "Guihai Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8584797a1c12158b20da04c30e3a0f577c63f02f9e906a051579959de2cae480", "submitted_at": "2025-10-17T09:11:05Z", "updated_at": "2025-10-17T09:11:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.15455v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:52Z", "role": "primary", "sha256": "0b730323b2ce85c39aa7d534665901a480ff06540c73f1f80832fcc0735b8789", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2310.08588%2C2402.09205%2C2406.05720%2C2407.21075%2C2410.07166%2C2503.03743%2C2508.04037%2C2508.10833%2C2508.11360%2C2508.13024%2C2508.13186%2C2508.14104%2C2509.01619%2C2509.01720%2C2509.02322%2C2509.04198%2C2509.07764%2C2509.21823%2C2509.22256%2C2509.23263%2C2509.23866%2C2509.25047%2C2509.26539%2C2510.00413%2C2510.00536%2C2510.01524%2C2510.02204%2C2510.02250%2C2510.02418%2C2510.03204%2C2510.03612%2C2510.04039%2C2510.04373%2C2510.04607%2C2510.06223%2C2510.06607%2C2510.09872%2C2510.10666%2C2510.11035%2C2510.11221%2C2510.11892%2C2510.13543%2C2510.15455%2C2510.15863%2C2510.16252%2C2510.18113%2C2510.18314%2C2510.19205%2C2510.22732%2C2511.06101&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:52Z", "role": "primary", "sha256": "0b730323b2ce85c39aa7d534665901a480ff06540c73f1f80832fcc0735b8789", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2310.08588%2C2402.09205%2C2406.05720%2C2407.21075%2C2410.07166%2C2503.03743%2C2508.04037%2C2508.10833%2C2508.11360%2C2508.13024%2C2508.13186%2C2508.14104%2C2509.01619%2C2509.01720%2C2509.02322%2C2509.04198%2C2509.07764%2C2509.21823%2C2509.22256%2C2509.23263%2C2509.23866%2C2509.25047%2C2509.26539%2C2510.00413%2C2510.00536%2C2510.01524%2C2510.02204%2C2510.02250%2C2510.02418%2C2510.03204%2C2510.03612%2C2510.04039%2C2510.04373%2C2510.04607%2C2510.06223%2C2510.06607%2C2510.09872%2C2510.10666%2C2510.11035%2C2510.11221%2C2510.11892%2C2510.13543%2C2510.15455%2C2510.15863%2C2510.16252%2C2510.18113%2C2510.18314%2C2510.19205%2C2510.22732%2C2511.06101&max_results=50"}], "id": "arxiv:2510.15455", "identifiers": {"arxiv": "2510.15455"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.15455"}], "name": "CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental findings and artifact availability have not been independently reproduced. XML screen hierarchies do not by themselves establish Android deployment.", "published_at": "2025-10-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces CORE, which divides mobile UI hierarchies into semantic blocks and shares planning between local and cloud language models. Local ranking limits the screen information sent for cloud-side element selection, with a multi-round mechanism for correcting inadequate context.", "topics": ["safety-security", "mobile-navigation", "efficiency"], "updated_at": "2025-10-17", "url": "https://arxiv.org/abs/2510.15455"}
{"aliases": [], "authors": ["Yangqin Jiang", "Chao Huang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "09bd73dff01641593f31f7d40effd60df42e3d9460ffa010f76c00a32be3593b", "submitted_at": "2025-10-24T20:23:12Z", "updated_at": "2026-10-05T01:17:12Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2510.22009v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:52Z", "role": "primary", "sha256": "8623b0ff7ef9d2e8ba484cd67359e7b8817e78e9ca22b8f27432c2533f5b90a0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2510.01670%2C2510.04673%2C2510.10073%2C2510.12200%2C2510.14621%2C2510.16051%2C2510.17790%2C2510.18488%2C2510.18596%2C2510.19488%2C2510.19949%2C2510.20286%2C2510.22009%2C2510.24168%2C2510.24411%2C2510.24563%2C2511.00810%2C2511.04307%2C2511.07332%2C2511.09157%2C2511.12254%2C2511.13087%2C2511.15567%2C2511.16590%2C2511.19663%2C2511.20597%2C2511.20766%2C2512.08529%2C2512.10371%2C2512.10962%2C2512.12634%2C2512.14014%2C2512.15431%2C2512.16295%2C2512.16501%2C2512.19432%2C2512.22894%2C2512.24965%2C2601.02399%2C2601.06031%2C2601.07181%2C2601.07262%2C2601.07779%2C2601.08406%2C2601.09923%2C2601.11044%2C2601.11868%2C2601.12822%2C2601.13060%2C2601.15876&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:52Z", "role": "primary", "sha256": "8623b0ff7ef9d2e8ba484cd67359e7b8817e78e9ca22b8f27432c2533f5b90a0", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2510.01670%2C2510.04673%2C2510.10073%2C2510.12200%2C2510.14621%2C2510.16051%2C2510.17790%2C2510.18488%2C2510.18596%2C2510.19488%2C2510.19949%2C2510.20286%2C2510.22009%2C2510.24168%2C2510.24411%2C2510.24563%2C2511.00810%2C2511.04307%2C2511.07332%2C2511.09157%2C2511.12254%2C2511.13087%2C2511.15567%2C2511.16590%2C2511.19663%2C2511.20597%2C2511.20766%2C2512.08529%2C2512.10371%2C2512.10962%2C2512.12634%2C2512.14014%2C2512.15431%2C2512.16295%2C2512.16501%2C2512.19432%2C2512.22894%2C2512.24965%2C2601.02399%2C2601.06031%2C2601.07181%2C2601.07262%2C2601.07779%2C2601.08406%2C2601.09923%2C2601.11044%2C2601.11868%2C2601.12822%2C2601.13060%2C2601.15876&max_results=50"}], "id": "arxiv:2510.22009", "identifiers": {"arxiv": "2510.22009"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.22009"}], "name": "OpenPhone: Mobile Agentic Foundation Models", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-10-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "OpenPhone trains a compact mobile policy with supervised learning followed by GRPO on synthetic GUI data, incorporating reasoning and memory management. Its device-cloud design handles routine work locally and delegates complex subtasks, with online evaluation on AndroidLab.", "topics": ["reinforcement-learning", "memory", "efficiency", "mobile-navigation"], "updated_at": "2026-10-05", "url": "https://arxiv.org/abs/2510.22009"}
{"aliases": [], "authors": ["Qiushi Sun", "Mukai Li", "Zhoumianze Liu", "Zhihui Xie", "Fangzhi Xu", "Zhangyue Yin", "Kanzhi Cheng", "Zehao Li", "Zichen Ding", "Qi Liu", "Zhiyong Wu", "Zhuosheng Zhang", "Ben Kao", "Lingpeng Kong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7e3fde732c9e760437f2c60d585f7ba0d2ed13bbe9e051838844a21174159099", "submitted_at": "2025-10-28T13:22:39Z", "updated_at": "2026-07-26T01:16:06Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2510.24411v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2510.24411", "identifiers": {"arxiv": "2510.24411"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.24411"}], "name": "OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows", "notes": "Reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2025-10-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces MobileRisk-Live and OS-Sentinel, combining a formal verifier for system-level violations with a multimodal judge for contextual risks in mobile GUI workflows.", "topics": ["safety-security", "evaluation", "mobile-navigation"], "updated_at": "2026-07-26", "url": "https://arxiv.org/abs/2510.24411"}
{"aliases": [], "authors": ["Chenghao Du", "Quanfeng Huang", "Tingxuan Tang", "Zihao Wang", "Adwait Nadkarni", "Yue Xiao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "61b611712fff54af25aae660f2353fa6c3aaa764b0767831ebf2278c120d9dea", "submitted_at": "2025-10-31T03:35:59Z", "updated_at": "2026-07-07T02:18:26Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2510.27140v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}], "id": "arxiv:2510.27140", "identifiers": {"arxiv": "2510.27140"}, "kind": "paper", "last_verified_at": "2026-10-18T10:54:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.27140"}], "name": "Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-10-31", "relations": [], "review_status": "curated", "scope": "core", "summary": "Measures how untrusted third-party notifications, messages, and app content can hijack mobile LLM agents into executing unauthorized cross-app actions.", "topics": ["safety-security", "mobile-navigation", "evaluation"], "updated_at": "2026-07-07", "url": "https://arxiv.org/abs/2510.27140"}
{"aliases": [], "authors": ["Leyang Yang", "Ziwei Wang", "Xiaoxuan Tang", "Sheng Zhou", "Dajun Chen", "Wei Jiang", "Yong Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dc7f5f0fe1ca373272cda4bbeca3a465e1a7eaec829e8a59bbecbe6049dc7b4a", "submitted_at": "2025-11-12T09:49:31Z", "updated_at": "2025-11-12T09:49:31Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.09157v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2511.09157", "identifiers": {"arxiv": "2511.09157"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2511.09157"}], "name": "ProBench: Benchmarking GUI Agents with Accurate Process Information", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-11-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "ProBench extends mobile GUI evaluation with tasks whose correctness depends on the interaction process as well as the final state. Its ProcessProvider supplies process information for assessing agent behavior and analyzing failure modes.", "topics": ["evaluation", "mobile-navigation", "observability"], "updated_at": "2025-11-12", "url": "https://arxiv.org/abs/2511.09157"}
{"aliases": [], "authors": ["Yuxiang Zhou", "Jichang Li", "Yanhao Zhang", "Haonan Lu", "Guanbin Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ede08df1c10d8eeede43af75d26608b4917dd83becde23f28cd3adf335f79736", "submitted_at": "2025-11-15T15:22:42Z", "updated_at": "2026-03-12T08:45:07Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2511.12254v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:52Z", "role": "primary", "sha256": "8623b0ff7ef9d2e8ba484cd67359e7b8817e78e9ca22b8f27432c2533f5b90a0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2510.01670%2C2510.04673%2C2510.10073%2C2510.12200%2C2510.14621%2C2510.16051%2C2510.17790%2C2510.18488%2C2510.18596%2C2510.19488%2C2510.19949%2C2510.20286%2C2510.22009%2C2510.24168%2C2510.24411%2C2510.24563%2C2511.00810%2C2511.04307%2C2511.07332%2C2511.09157%2C2511.12254%2C2511.13087%2C2511.15567%2C2511.16590%2C2511.19663%2C2511.20597%2C2511.20766%2C2512.08529%2C2512.10371%2C2512.10962%2C2512.12634%2C2512.14014%2C2512.15431%2C2512.16295%2C2512.16501%2C2512.19432%2C2512.22894%2C2512.24965%2C2601.02399%2C2601.06031%2C2601.07181%2C2601.07262%2C2601.07779%2C2601.08406%2C2601.09923%2C2601.11044%2C2601.11868%2C2601.12822%2C2601.13060%2C2601.15876&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:52Z", "role": "primary", "sha256": "8623b0ff7ef9d2e8ba484cd67359e7b8817e78e9ca22b8f27432c2533f5b90a0", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2510.01670%2C2510.04673%2C2510.10073%2C2510.12200%2C2510.14621%2C2510.16051%2C2510.17790%2C2510.18488%2C2510.18596%2C2510.19488%2C2510.19949%2C2510.20286%2C2510.22009%2C2510.24168%2C2510.24411%2C2510.24563%2C2511.00810%2C2511.04307%2C2511.07332%2C2511.09157%2C2511.12254%2C2511.13087%2C2511.15567%2C2511.16590%2C2511.19663%2C2511.20597%2C2511.20766%2C2512.08529%2C2512.10371%2C2512.10962%2C2512.12634%2C2512.14014%2C2512.15431%2C2512.16295%2C2512.16501%2C2512.19432%2C2512.22894%2C2512.24965%2C2601.02399%2C2601.06031%2C2601.07181%2C2601.07262%2C2601.07779%2C2601.08406%2C2601.09923%2C2601.11044%2C2601.11868%2C2601.12822%2C2601.13060%2C2601.15876&max_results=50"}], "id": "arxiv:2511.12254", "identifiers": {"arxiv": "2511.12254"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2511.12254"}], "name": "Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-11-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses separate retrieval systems for high-level mobile-task planning and precise interface operations, with a benchmark for extended cross-app tasks.", "topics": ["mobile-navigation", "memory", "long-horizon"], "updated_at": "2026-03-12", "url": "https://arxiv.org/abs/2511.12254"}
{"aliases": [], "authors": ["Fuyao Zhang", "Jiaming Zhang", "Che Wang", "Xiongtao Sun", "Yurong Hao", "Guowei Guan", "Wenjie Li", "Longtao Huang", "Wei Yang Bryan Lim"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d918a5754fe907fc273639f3277a3566d649c08da244714d0d7737456bede230", "submitted_at": "2025-11-17T11:08:45Z", "updated_at": "2025-11-17T11:08:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.13248v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}], "id": "arxiv:2511.13248", "identifiers": {"arxiv": "2511.13248"}, "kind": "paper", "last_verified_at": "2026-10-18T10:54:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2511.13248"}], "name": "DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-11-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "Applies dual-task adversarial perturbations to mobile screenshots to conceal personally identifiable information from untrusted MLLM routers while preserving agent task utility.", "topics": ["safety-security", "mobile-navigation"], "updated_at": "2025-11-17", "url": "https://arxiv.org/abs/2511.13248"}
{"aliases": [], "authors": ["Sen Chen", "Tong Zhao", "Yi Bin", "Fei Ma", "Wenqi Shao", "Zheng Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1679f7b56c7b60f92195e488c887114bcdcce7975a80fafbf2572c2b1f01ce0b", "submitted_at": "2025-11-20T17:43:46Z", "updated_at": "2025-11-20T17:43:46Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.16590v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2511.16590", "identifiers": {"arxiv": "2511.16590"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2511.16590"}], "name": "D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-11-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "D-GARA evaluates Android GUI agents under runtime anomalies such as permission dialogs, battery warnings, and update prompts. Its modular environment embeds these interruptions in Android applications to study recovery and robustness.", "topics": ["evaluation", "robustness", "mobile-navigation"], "updated_at": "2025-11-20", "url": "https://arxiv.org/abs/2511.16590"}
{"aliases": [], "authors": ["Neeraj Anand", "Rishabh Jain", "Sohan Patnaik", "Balaji Krishnamurthy", "Mausoom Sarkar"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "faad266b89aed9b210a813b69184d7236f9098c0e095cc426402e154cbdd067b", "submitted_at": "2025-11-30T11:32:54Z", "updated_at": "2025-12-11T18:16:38Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2512.00846v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2512.00846", "identifiers": {"arxiv": "2512.00846"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2512.00846"}], "name": "AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2025-11-30", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces AFRAgent, which uses adaptive feature renormalization to combine low-resolution visual embeddings with high-resolution details. The architecture is evaluated for smartphone GUI automation on Meta-GUI and AITW.", "topics": ["grounding", "mobile-navigation", "efficiency"], "updated_at": "2025-12-11", "url": "https://arxiv.org/abs/2512.00846"}
{"aliases": [], "authors": ["Youngmin Im", "Byeongung Jo", "Jaeyoung Wi", "Seungwoo Baek", "Tae Hoon Min", "Joo Hyung Lee", "Sangeun Oh", "Insik Shin", "Sunjae Lee"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5982901598e43dcadf63b4a950b2fff68e85be71d0f483648b535d82d7745bd7", "submitted_at": "2025-12-14T10:41:39Z", "updated_at": "2026-05-31T23:48:10Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2512.12634v4"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2512.12634", "identifiers": {"arxiv": "2512.12634"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2512.12634"}], "name": "MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-12-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobiBench evaluates mobile GUI agents offline while allowing multiple valid action paths. It decomposes agent pipelines into modules to study component contributions, configurations, and performance bottlenecks.", "topics": ["evaluation", "mobile-navigation", "observability"], "updated_at": "2026-05-31", "url": "https://arxiv.org/abs/2512.12634"}
{"aliases": [], "authors": ["Haolong Yan", "Jia Wang", "Xin Huang", "Yeqing Shen", "Ziyang Meng", "Zhimin Fan", "Kaijun Tan", "Jin Gao", "Lieyu Shi", "Mi Yang", "Shiliang Yang", "Zhirui Wang", "Brian Li", "Kang An", "Chenyang Li", "Lei Lei", "Mengmeng Duan", "Danxun Liang", "Guodong Liu", "Hang Cheng", "Hao Wu", "Jie Dong", "Junhao Huang", "Mei Chen", "Renjie Yu", "Shunshan Li", "Xu Zhou", "Yiting Dai", "Yineng Deng", "Yingdan Liang", "Zelin Chen", "Wen Sun", "Chengxu Yan", "Chunqin Xu", "Dong Li", "Fengqiong Xiao", "Guanghao Fan", "Guopeng Li", "Guozhen Peng", "Hongbing Li", "Hang Li", "Hongming Chen", "Jingjing Xie", "Jianyong Li", "Jingyang Zhang", "Jiaju Ren", "Jiayu Yuan", "Jianpeng Yin", "Kai Cao", "Liang Zhao", "Liguo Tan", "Liying Shi", "Mengqiang Ren", "Min Xu", "Manjiao Liu", "Mao Luo", "Mingxin Wan", "Na Wang", "Nan Wu", "Ning Wang", "Peiyao Ma", "Qingzhou Zhang", "Qiao Wang", "Qinlin Zeng", "Qiong Gao", "Qiongyao Li", "Shangwu Zhong", "Shuli Gao", "Shaofan Liu", "Shisi Gao", "Shuang Luo", "Xingbin Liu", "Xiaojia Liu", "Xiaojie Hou", "Xin Liu", "Xuanti Feng", "Xuedan Cai", "Xuan Wen", "Xianwei Zhu", "Xin Liang", "Xin Liu", "Xin Zhou", "Yifan Sui", "Yingxiu Zhao", "Yukang Shi", "Yunfang Xu", "Yuqing Zeng", "Yixun Zhang", "Zejia Weng", "Zhonghao Yan", "Zhiguo Huang", "Zhuoyu Wang", "Zihan Yan", "Zheng Ge", "Jing Li", "Yibo Zhu", "Binxing Jiao", "Xiangyu Zhang", "Daxin Jiang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2fc824bdeabca3451fd895447a0321c507da1ac7bc7cc24184c7768992549daf", "submitted_at": "2025-12-17T13:26:30Z", "updated_at": "2025-12-19T17:36:21Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2512.15431v2"}}, "environments": ["android", "desktop"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:52Z", "role": "primary", "sha256": "8623b0ff7ef9d2e8ba484cd67359e7b8817e78e9ca22b8f27432c2533f5b90a0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2510.01670%2C2510.04673%2C2510.10073%2C2510.12200%2C2510.14621%2C2510.16051%2C2510.17790%2C2510.18488%2C2510.18596%2C2510.19488%2C2510.19949%2C2510.20286%2C2510.22009%2C2510.24168%2C2510.24411%2C2510.24563%2C2511.00810%2C2511.04307%2C2511.07332%2C2511.09157%2C2511.12254%2C2511.13087%2C2511.15567%2C2511.16590%2C2511.19663%2C2511.20597%2C2511.20766%2C2512.08529%2C2512.10371%2C2512.10962%2C2512.12634%2C2512.14014%2C2512.15431%2C2512.16295%2C2512.16501%2C2512.19432%2C2512.22894%2C2512.24965%2C2601.02399%2C2601.06031%2C2601.07181%2C2601.07262%2C2601.07779%2C2601.08406%2C2601.09923%2C2601.11044%2C2601.11868%2C2601.12822%2C2601.13060%2C2601.15876&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:52Z", "role": "primary", "sha256": "8623b0ff7ef9d2e8ba484cd67359e7b8817e78e9ca22b8f27432c2533f5b90a0", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2510.01670%2C2510.04673%2C2510.10073%2C2510.12200%2C2510.14621%2C2510.16051%2C2510.17790%2C2510.18488%2C2510.18596%2C2510.19488%2C2510.19949%2C2510.20286%2C2510.22009%2C2510.24168%2C2510.24411%2C2510.24563%2C2511.00810%2C2511.04307%2C2511.07332%2C2511.09157%2C2511.12254%2C2511.13087%2C2511.15567%2C2511.16590%2C2511.19663%2C2511.20597%2C2511.20766%2C2512.08529%2C2512.10371%2C2512.10962%2C2512.12634%2C2512.14014%2C2512.15431%2C2512.16295%2C2512.16501%2C2512.19432%2C2512.22894%2C2512.24965%2C2601.02399%2C2601.06031%2C2601.07181%2C2601.07262%2C2601.07779%2C2601.08406%2C2601.09923%2C2601.11044%2C2601.11868%2C2601.12822%2C2601.13060%2C2601.15876&max_results=50"}], "id": "arxiv:2512.15431", "identifiers": {"arxiv": "2512.15431"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2512.15431"}], "name": "Step-GUI Technical Report", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-12-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "Step-GUI uses calibrated trajectory rewards to turn generated GUI interaction data into training signals for compact agent models. The report also introduces GUI-MCP for hierarchical GUI operations and local task delegation, and AndroidDaily for static-action and end-to-end mobile evaluation.", "topics": ["data-generation", "reward-models", "tool-integration", "evaluation", "mobile-navigation"], "updated_at": "2025-12-19", "url": "https://arxiv.org/abs/2512.15431"}
{"aliases": [], "authors": ["Runze Li", "Yuwen Zhai", "Bo Xu", "LiWu Xu", "Nian Shi", "Wei Zhang", "Ran Lin", "Liang Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "03cdf8514fa9f036b4614a880d842d49bb9cb0a821858b7215784fba209faa62", "submitted_at": "2025-12-22T13:42:18Z", "updated_at": "2026-04-10T06:20:00Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2512.19396v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2512.19396", "identifiers": {"arxiv": "2512.19396"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2512.19396"}], "name": "EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-12-22", "relations": [], "review_status": "curated", "scope": "core", "summary": "EchoTrail-GUI builds a memory of successful GUI trajectories through autonomous exploration filtered by a reward model. It retrieves relevant trajectories as in-context guidance for new tasks and evaluates the approach on AndroidWorld and AndroidLab.", "topics": ["memory", "data-generation", "reward-models", "mobile-navigation"], "updated_at": "2026-04-10", "url": "https://arxiv.org/abs/2512.19396"}
{"aliases": [], "authors": ["Yue Cao", "Yingyao Wang", "Pi Bu", "Jingxuan Xing", "Wei Jiang", "Zekun Zhu", "Junpeng Ma", "Sashuai Zhou", "Tong Lu", "Jun Song", "Yu Cheng", "Yuning Jiang", "Bo Zheng"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "597935923ce9e59720771f3d92e921f2842f908ad81b3ab31a87ed9d9f5c5774", "submitted_at": "2025-12-24T17:40:42Z", "updated_at": "2025-12-24T17:40:42Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.21302v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2512.21302", "identifiers": {"arxiv": "2512.21302"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2512.21302"}], "name": "AndroidLens: Long-latency Evaluation with Nested Sub-targets for Android GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-12-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "AndroidLens provides 571 extended mobile tasks in Chinese and English, with multiple valid paths and preserved environmental anomalies. Its dynamic evaluation uses nested milestones and Average Task Progress to measure partial completion of long workflows.", "topics": ["evaluation", "long-horizon", "mobile-navigation", "robustness"], "updated_at": "2025-12-24", "url": "https://arxiv.org/abs/2512.21302"}
{"aliases": [], "authors": ["Yilin Cao", "Yufeng Zhong", "Zhixiong Zeng", "Siran Dai", "Liming Zheng", "Jing Huang", "Haibo Qiu", "Peng Shi", "Wenji Mao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c40e3db3f538f089c19d7c8233ea01174d0591c3211a7acc412ee4df28e902a8", "submitted_at": "2026-01-07T15:51:44Z", "updated_at": "2026-08-31T13:27:52Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.04035v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2601.04035", "identifiers": {"arxiv": "2601.04035"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2601.04035"}], "name": "MobileDreamer: Generative Sketch World Model for GUI Agent", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and released artifacts have not been independently reproduced.", "published_at": "2026-01-07", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileDreamer predicts post-action GUI states as task-relevant textual sketches with an order-invariant learning objective. Agents use these predictions for lookahead action selection, evaluated on AndroidWorld.", "topics": ["world-models", "planning", "mobile-navigation"], "updated_at": "2026-08-31", "url": "https://arxiv.org/abs/2601.04035"}
{"aliases": [], "authors": ["Yibo Lyu", "Gongwei Chen", "Rui Shao", "Weili Guan", "Liqiang Nie"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d8b697b91942291403491581a61c135c6bfc8b0f3c2a9b9bab0f926af7208fce", "submitted_at": "2026-01-14T17:12:48Z", "updated_at": "2026-05-13T02:54:19Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.09636v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2601.09636", "identifiers": {"arxiv": "2601.09636"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2601.09636"}], "name": "PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-01-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces AndroidIntent to evaluate how GUI agents infer omitted preferences and recurring routines from long-term user records. Its HIM-Agent maintains hierarchical memory of preferences and routines for personalized execution and proactive suggestions.", "topics": ["memory", "evaluation", "mobile-navigation"], "updated_at": "2026-05-13", "url": "https://arxiv.org/abs/2601.09636"}
{"aliases": [], "authors": ["Mingxian Yu", "Siqi Luo", "Xu Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4ce0909d1c9081f099ae0dc0b0182e0442fd71fd58c62b13d486d154afc2187e", "submitted_at": "2026-01-24T11:35:37Z", "updated_at": "2026-01-24T11:35:37Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.17418v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:55Z", "role": "primary", "sha256": "e6061c8dd9c00a70fcf1d4325b671c50a6912063ecbe2b6359175ae4622983a0", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2511.13091%2C2511.21398%2C2511.22235%2C2512.00756%2C2512.00846%2C2512.01174%2C2512.01763%2C2512.02423%2C2512.04105%2C2512.05941%2C2512.07725%2C2512.09396%2C2512.11611%2C2512.12692%2C2512.17221%2C2512.19396%2C2512.21302%2C2512.22009%2C2512.22047%2C2512.22322%2C2512.23128%2C2601.02371%2C2601.02439%2C2601.03641%2C2601.04035%2C2601.04126%2C2601.04500%2C2601.05787%2C2601.06899%2C2601.08605%2C2601.09636%2C2601.09770%2C2601.11631%2C2601.12349%2C2601.16356%2C2601.17418%2C2601.18197%2C2601.18305%2C2601.19199%2C2601.20732%2C2601.21352%2C2601.21872%2C2601.21961%2C2601.22149%2C2601.22491%2C2601.22528%2C2602.02468%2C2602.05354%2C2602.06090%2C2602.06351&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:55Z", "role": "primary", "sha256": "e6061c8dd9c00a70fcf1d4325b671c50a6912063ecbe2b6359175ae4622983a0", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2511.13091%2C2511.21398%2C2511.22235%2C2512.00756%2C2512.00846%2C2512.01174%2C2512.01763%2C2512.02423%2C2512.04105%2C2512.05941%2C2512.07725%2C2512.09396%2C2512.11611%2C2512.12692%2C2512.17221%2C2512.19396%2C2512.21302%2C2512.22009%2C2512.22047%2C2512.22322%2C2512.23128%2C2601.02371%2C2601.02439%2C2601.03641%2C2601.04035%2C2601.04126%2C2601.04500%2C2601.05787%2C2601.06899%2C2601.08605%2C2601.09636%2C2601.09770%2C2601.11631%2C2601.12349%2C2601.16356%2C2601.17418%2C2601.18197%2C2601.18305%2C2601.19199%2C2601.20732%2C2601.21352%2C2601.21872%2C2601.21961%2C2601.22149%2C2601.22491%2C2601.22528%2C2602.02468%2C2602.05354%2C2602.06090%2C2602.06351&max_results=50"}], "id": "arxiv:2601.17418", "identifiers": {"arxiv": "2601.17418"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:55Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2601.17418"}], "name": "GraphPilot: GUI Task Automation with One-Step LLM Reasoning Powered by Knowledge Graph", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and released artifacts have not been independently reproduced.", "published_at": "2026-01-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "GraphPilot builds app-specific knowledge graphs from explored pages, elements and transitions, then uses them to plan action sequences. It requests additional interface observations when uncertain and checks plans against graph transition rules before correction and execution.", "topics": ["mobile-navigation", "planning", "memory", "efficiency"], "updated_at": "2026-01-24", "url": "https://arxiv.org/abs/2601.17418"}
{"aliases": [], "authors": ["Sijia Li", "Xiaoyu Tan", "Shahir Ali", "Niels Schmidt", "Gengchen Ma", "Xihe Qiu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "223b9a915e5ea9849644318e1e5426e64ad8655ab46d0b007c30e1967130dc50", "submitted_at": "2026-01-27T07:46:05Z", "updated_at": "2026-01-27T07:46:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.19306v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:01:04.629294+00:00", "role": "primary", "sha256": "53521b0a80976320b10efcf7840629e4a2085119710324dd48db2cfd9c5d9cf6", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:01:04.629294+00:00", "role": "primary", "sha256": "53521b0a80976320b10efcf7840629e4a2085119710324dd48db2cfd9c5d9cf6", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:14:20.444793+00:00", "role": "primary", "sha256": "ef3bbc8adcc147239ea910e0c59904d7a26ee1610a7a4d1613be2cb845098536", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/pdf/2601.19306v1"}], "id": "arxiv:2601.19306", "identifiers": {"arxiv": "2601.19306"}, "kind": "paper", "last_verified_at": "2026-10-18T10:01:04.629294+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2601.19306"}], "name": "Curiosity Driven Knowledge Retrieval for Mobile Agents", "notes": "The curiosity signal is a model-based proxy, not a calibrated probability of failure. Accurate external app information is a dependency, and AndroidWorld is the reported evaluation environment. No performance numbers were independently reproduced. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (3.1 Problem Formulation; 3.2 Curiosity-Driven Information Gain Estimation; 3.3 Retrieving and Embedding External Knowledge); not an entire-paper reading or reproduction claim.", "published_at": "2026-01-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses execution uncertainty to trigger retrieval from application documentation, code, and past trajectories, organizing the results into structured AppCards for Android agent planning.", "topics": ["memory", "planning", "mobile-navigation"], "updated_at": "2026-01-27", "url": "https://arxiv.org/abs/2601.19306"}
{"aliases": [], "authors": ["Qinzhuo Wu", "Zhizhuo Yang", "Hanhao Li", "Pengzhi Gao", "Wei Liu", "Jian Luan"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1cbf16dd3c790996758e00c085a9c2bccabf5b24f945bbd8440cc1f953e38568", "submitted_at": "2026-01-28T07:49:48Z", "updated_at": "2026-01-29T02:32:46Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.20335v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2601.20335", "identifiers": {"arxiv": "2601.20335"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2601.20335"}], "name": "MobileBench-OL: A Comprehensive Chinese Benchmark for Evaluating Mobile GUI Agents in Real-World Environment", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-01-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces MobileBench-OL, an online benchmark of Chinese-app tasks spanning execution, reasoning, exploration, and noisy conditions. Its automatic evaluation and reset framework supports repeated testing of mobile GUI agents in real environments.", "topics": ["evaluation", "mobile-navigation", "robustness"], "updated_at": "2026-01-29", "url": "https://arxiv.org/abs/2601.20335"}
{"aliases": [], "authors": ["Wei Minn", "Biniam Fisseha Demissie", "Yan Naing Tun", "Jiakun Liu", "Mariano Ceccato", "Lwin Khin Shar", "David Lo"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ac3f148047f7e63a33780fed3fd1ca461bead2128914c46f353efab4675df444", "submitted_at": "2026-01-29T04:21:11Z", "updated_at": "2026-01-29T04:21:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.21253v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:12Z", "role": "primary", "sha256": "c8c95278aa5dcc6a8f2eda3f3b44d61ec1f35adcb6a4c6c9ab328691a1a4f102", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2601.13462%2C2601.14232%2C2601.15331%2C2601.17548%2C2601.18418%2C2601.18491%2C2601.18827%2C2601.20171%2C2601.20613%2C2601.20742%2C2601.21233%2C2601.21253%2C2601.22037%2C2601.22154%2C2601.22511%2C2601.22607%2C2602.01550%2C2602.03117%2C2602.03361%2C2602.05665%2C2602.05746%2C2602.05877%2C2602.06052%2C2602.07398%2C2602.07458%2C2602.07918%2C2602.09007%2C2602.09463%2C2602.09514%2C2602.10122%2C2602.10525%2C2602.11224%2C2602.12268%2C2602.12430%2C2602.13318%2C2602.13543%2C2602.13692%2C2602.14038%2C2602.14337%2C2602.14364%2C2602.16313%2C2602.16317%2C2602.16666%2C2602.16901%2C2602.16930%2C2602.17547%2C2602.17646%2C2602.18846%2C2602.19320%2C2602.19594&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:12Z", "role": "primary", "sha256": "c8c95278aa5dcc6a8f2eda3f3b44d61ec1f35adcb6a4c6c9ab328691a1a4f102", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2601.13462%2C2601.14232%2C2601.15331%2C2601.17548%2C2601.18418%2C2601.18491%2C2601.18827%2C2601.20171%2C2601.20613%2C2601.20742%2C2601.21233%2C2601.21253%2C2601.22037%2C2601.22154%2C2601.22511%2C2601.22607%2C2602.01550%2C2602.03117%2C2602.03361%2C2602.05665%2C2602.05746%2C2602.05877%2C2602.06052%2C2602.07398%2C2602.07458%2C2602.07918%2C2602.09007%2C2602.09463%2C2602.09514%2C2602.10122%2C2602.10525%2C2602.11224%2C2602.12268%2C2602.12430%2C2602.13318%2C2602.13543%2C2602.13692%2C2602.14038%2C2602.14337%2C2602.14364%2C2602.16313%2C2602.16317%2C2602.16666%2C2602.16901%2C2602.16930%2C2602.17547%2C2602.17646%2C2602.18846%2C2602.19320%2C2602.19594&max_results=50"}], "id": "arxiv:2601.21253", "identifiers": {"arxiv": "2601.21253"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2601.21253"}], "name": "CovAgent: Overcoming the 30% Curse of Mobile Application Coverage with Agentic AI and Dynamic Instrumentation", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified.", "published_at": "2026-01-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "CovAgent augments Android GUI fuzzers by analyzing decompiled app code and component transitions to identify unsatisfied activation conditions. A second agent generates instrumentation that enables otherwise difficult-to-reach activities, with coverage-based evaluation.", "topics": ["automation", "mobile-navigation", "evaluation"], "updated_at": "2026-01-29", "url": "https://arxiv.org/abs/2601.21253"}
{"aliases": [], "authors": ["Linjia Kang", "Zhimin Wang", "Yongkang Zhang", "Duo Wu", "Jinghe Wang", "Ming Ma", "Haopeng Yan", "Zhi Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0d66365682d0ea4cee744c6c59d3a585c9272a31da5f8ff7c27983d719f070a7", "submitted_at": "2026-01-30T10:03:20Z", "updated_at": "2026-01-30T10:03:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.22781v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2601.22781", "identifiers": {"arxiv": "2601.22781"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2601.22781"}], "name": "Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent Training", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and released artifacts have not been independently reproduced.", "published_at": "2026-01-30", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileGen estimates a mobile agent’s strengths across structural and semantic task difficulty, then samples new training targets around that profile. A controllable multi-agent generator creates the corresponding instructions and GUI trajectories.", "topics": ["data-generation", "mobile-navigation", "evaluation"], "updated_at": "2026-01-30", "url": "https://arxiv.org/abs/2601.22781"}
{"aliases": [], "authors": ["Woosung Koh", "Sungjun Han", "Segyu Lee", "Se-Young Yun", "Jamin Shin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7c29d1404b02c4f5ef2cdaf78bdb0f9062b1b85ec1a154408bc8f49446c28d08", "submitted_at": "2026-02-02T03:12:16Z", "updated_at": "2026-05-23T02:41:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.01576v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:56Z", "role": "primary", "sha256": "c22be2d5c6a84b2c367759ce2b8f41f5a178fccd0534e832802c9d57b40918e8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2601.16206%2C2601.17722%2C2601.18113%2C2601.18842%2C2601.20162%2C2601.20335%2C2601.20380%2C2601.20650%2C2601.21123%2C2601.22781%2C2602.00575%2C2602.01576%2C2602.01725%2C2602.02419%2C2602.02548%2C2602.02995%2C2602.03255%2C2602.03792%2C2602.05429%2C2602.05832%2C2602.06075%2C2602.06391%2C2602.07153%2C2602.07624%2C2602.08235%2C2602.08995%2C2602.09082%2C2602.09222%2C2602.09310%2C2602.09662%2C2602.10139%2C2602.11514%2C2602.11724%2C2602.11750%2C2602.14093%2C2602.14276%2C2602.14296%2C2602.14721%2C2602.16855%2C2602.17049%2C2602.17365%2C2602.20502%2C2602.21858%2C2602.22190%2C2603.05044%2C2603.05295%2C2603.07978%2C2603.08533%2C2603.10178%2C2603.12138&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:56Z", "role": "primary", "sha256": "c22be2d5c6a84b2c367759ce2b8f41f5a178fccd0534e832802c9d57b40918e8", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2601.16206%2C2601.17722%2C2601.18113%2C2601.18842%2C2601.20162%2C2601.20335%2C2601.20380%2C2601.20650%2C2601.21123%2C2601.22781%2C2602.00575%2C2602.01576%2C2602.01725%2C2602.02419%2C2602.02548%2C2602.02995%2C2602.03255%2C2602.03792%2C2602.05429%2C2602.05832%2C2602.06075%2C2602.06391%2C2602.07153%2C2602.07624%2C2602.08235%2C2602.08995%2C2602.09082%2C2602.09222%2C2602.09310%2C2602.09662%2C2602.10139%2C2602.11514%2C2602.11724%2C2602.11750%2C2602.14093%2C2602.14276%2C2602.14296%2C2602.14721%2C2602.16855%2C2602.17049%2C2602.17365%2C2602.20502%2C2602.21858%2C2602.22190%2C2603.05044%2C2603.05295%2C2603.07978%2C2603.08533%2C2603.10178%2C2603.12138&max_results=50"}], "id": "arxiv:2602.01576", "identifiers": {"arxiv": "2602.01576"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:56Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.01576"}], "name": "Generative Visual Code Mobile World Models", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and released artifacts have not been independently reproduced.", "published_at": "2026-02-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "gWorld predicts future mobile GUI states as renderable web code and supplies an automated pipeline for code-based training data. The study evaluates visual state prediction and how stronger world models affect downstream mobile policies.", "topics": ["world-models", "data-generation", "screen-understanding", "mobile-navigation"], "updated_at": "2026-05-23", "url": "https://arxiv.org/abs/2602.01576"}
{"aliases": [], "authors": ["Rui Lv", "Juncheng Mo", "Tianyi Chu", "Chen Rao", "Hongyi Jing", "Jiajie Teng", "Jiafu Chen", "Shiqi Zhang", "Liangzi Ding", "Shuo Fang", "Huaizhong Lin", "Ziqiang Dang", "Chenguang Ma", "Lei Zhao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "84d822655c810958cff6035584542d7e151d765734ec7030f841c15561ee5677", "submitted_at": "2026-02-05T08:19:39Z", "updated_at": "2026-02-05T08:19:39Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.05429v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2602.05429", "identifiers": {"arxiv": "2602.05429"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.05429"}], "name": "M$^2$-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and released artifacts have not been independently reproduced.", "published_at": "2026-02-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "M2-Miner uses multi-agent-guided Monte Carlo tree search to collect mobile GUI intent–trajectory pairs. Intent recycling and progressive collector training aim to increase the diversity and usefulness of the mined interaction data.", "topics": ["data-generation", "mobile-navigation", "planning"], "updated_at": "2026-02-05", "url": "https://arxiv.org/abs/2602.05429"}
{"aliases": [], "authors": ["Guangyi Liu", "Pengxiang Zhao", "Yaozhen Liang", "Qinyi Luo", "Shunye Tang", "Yuxiang Chai", "Weifeng Lin", "Han Xiao", "WenHao Wang", "Siheng Chen", "Zhengxi Lu", "Gao Wu", "Hao Wang", "Liang Liu", "Yong Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0692d6936a3e3c20a7ad61c69ae770f5669c3783ff837092254f8b3fb170cd0a", "submitted_at": "2026-02-03T17:01:59Z", "updated_at": "2026-08-27T06:48:18Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2602.06075v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2602.06075", "identifiers": {"arxiv": "2602.06075"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.06075"}], "name": "MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and released artifacts have not been independently reproduced.", "published_at": "2026-02-03", "relations": [], "review_status": "curated", "scope": "core", "summary": "MemGUI-Bench evaluates short-term retention and cross-session experience reuse in mobile GUI agents using paired tasks and repeated-attempt protocols. Its staged evaluator measures memory fidelity, learning and execution efficiency.", "topics": ["memory", "evaluation", "mobile-navigation", "cross-app"], "updated_at": "2026-08-27", "url": "https://arxiv.org/abs/2602.06075"}
{"aliases": [], "authors": ["Venus Team", "Changlong Gao", "Zhangxuan Gu", "Yulin Liu", "Xinyu Qiu", "Shuheng Shen", "Yue Wen", "Tianyu Xia", "Zhenyu Xu", "Zhengwen Zeng", "Beitong Zhou", "Xingran Zhou", "Weizhi Chen", "Sunhao Dai", "Jingya Dou", "Yichen Gong", "Yuan Guo", "Zhenlin Guo", "Feng Li", "Qian Li", "Jinzhen Lin", "Yuqi Zhou", "Linchao Zhu", "Liang Chen", "Zhenyu Guo", "Changhua Meng", "Weiqiang Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "efc4ad8f13d55939abcc783bdd652f276c3ac0164ea35232a3fb9366642d4558", "submitted_at": "2026-02-09T18:43:40Z", "updated_at": "2026-02-24T15:17:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.09082v2"}}, "environments": ["cross-platform", "web", "android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:56Z", "role": "primary", "sha256": "c22be2d5c6a84b2c367759ce2b8f41f5a178fccd0534e832802c9d57b40918e8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2601.16206%2C2601.17722%2C2601.18113%2C2601.18842%2C2601.20162%2C2601.20335%2C2601.20380%2C2601.20650%2C2601.21123%2C2601.22781%2C2602.00575%2C2602.01576%2C2602.01725%2C2602.02419%2C2602.02548%2C2602.02995%2C2602.03255%2C2602.03792%2C2602.05429%2C2602.05832%2C2602.06075%2C2602.06391%2C2602.07153%2C2602.07624%2C2602.08235%2C2602.08995%2C2602.09082%2C2602.09222%2C2602.09310%2C2602.09662%2C2602.10139%2C2602.11514%2C2602.11724%2C2602.11750%2C2602.14093%2C2602.14276%2C2602.14296%2C2602.14721%2C2602.16855%2C2602.17049%2C2602.17365%2C2602.20502%2C2602.21858%2C2602.22190%2C2603.05044%2C2603.05295%2C2603.07978%2C2603.08533%2C2603.10178%2C2603.12138&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:56Z", "role": "primary", "sha256": "c22be2d5c6a84b2c367759ce2b8f41f5a178fccd0534e832802c9d57b40918e8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2601.16206%2C2601.17722%2C2601.18113%2C2601.18842%2C2601.20162%2C2601.20335%2C2601.20380%2C2601.20650%2C2601.21123%2C2601.22781%2C2602.00575%2C2602.01576%2C2602.01725%2C2602.02419%2C2602.02548%2C2602.02995%2C2602.03255%2C2602.03792%2C2602.05429%2C2602.05832%2C2602.06075%2C2602.06391%2C2602.07153%2C2602.07624%2C2602.08235%2C2602.08995%2C2602.09082%2C2602.09222%2C2602.09310%2C2602.09662%2C2602.10139%2C2602.11514%2C2602.11724%2C2602.11750%2C2602.14093%2C2602.14276%2C2602.14296%2C2602.14721%2C2602.16855%2C2602.17049%2C2602.17365%2C2602.20502%2C2602.21858%2C2602.22190%2C2603.05044%2C2603.05295%2C2603.07978%2C2603.08533%2C2603.10178%2C2603.12138&max_results=50"}], "id": "arxiv:2602.09082", "identifiers": {"arxiv": "2602.09082"}, "kind": "paper", "last_verified_at": "2026-10-16T06:31:56Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.09082"}], "name": "UI-Venus-1.5 Technical Report", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-02-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Describes a GUI-agent family combining broad intermediate training, full-trajectory online reinforcement learning, and merging of specialized models.", "topics": ["reinforcement-learning", "grounding", "mobile-navigation"], "updated_at": "2026-02-24", "url": "https://arxiv.org/abs/2602.09082"}
{"aliases": [], "authors": ["Yuhao Zheng", "Li'an Zhong", "Yi Wang", "Rui Dai", "Kaikui Liu", "Xiangxiang Chu", "Linyuan Lv", "Philip Torr", "Kevin Qinghong Lin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "55287e2fe8a5e94671e4aab8e9d4a907ba9b6c83306d9b3f61b74adccd5c5059", "submitted_at": "2026-02-10T14:56:19Z", "updated_at": "2026-02-10T14:56:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.09856v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:59Z", "role": "primary", "sha256": "d494c76e512656f76a5912eac0768bbbdd50014387c779a0618a40c1722c399b", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2602.07008%2C2602.07283%2C2602.07787%2C2602.09856%2C2602.10356%2C2602.10814%2C2602.10915%2C2602.11524%2C2602.11858%2C2602.12276%2C2602.12544%2C2602.12852%2C2602.13559%2C2602.13653%2C2602.14865%2C2602.15384%2C2602.17003%2C2602.17245%2C2602.17588%2C2602.24142%2C2603.00503%2C2603.00676%2C2603.02951%2C2603.04364%2C2603.04949%2C2603.07024%2C2603.07432%2C2603.08013%2C2603.08316%2C2603.08938%2C2603.10268%2C2603.10291%2C2603.10505%2C2603.10577%2C2603.12710%2C2603.14248%2C2603.14448%2C2603.17441%2C2603.17826%2C2603.20278%2C2603.20340%2C2603.22529%2C2603.23007%2C2603.23559%2C2603.24160%2C2603.24533%2C2603.26041%2C2603.26266%2C2604.00073%2C2604.00842&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:59Z", "role": "primary", "sha256": "d494c76e512656f76a5912eac0768bbbdd50014387c779a0618a40c1722c399b", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2602.07008%2C2602.07283%2C2602.07787%2C2602.09856%2C2602.10356%2C2602.10814%2C2602.10915%2C2602.11524%2C2602.11858%2C2602.12276%2C2602.12544%2C2602.12852%2C2602.13559%2C2602.13653%2C2602.14865%2C2602.15384%2C2602.17003%2C2602.17245%2C2602.17588%2C2602.24142%2C2603.00503%2C2603.00676%2C2603.02951%2C2603.04364%2C2603.04949%2C2603.07024%2C2603.07432%2C2603.08013%2C2603.08316%2C2603.08938%2C2603.10268%2C2603.10291%2C2603.10505%2C2603.10577%2C2603.12710%2C2603.14248%2C2603.14448%2C2603.17441%2C2603.17826%2C2603.20278%2C2603.20340%2C2603.22529%2C2603.23007%2C2603.23559%2C2603.24160%2C2603.24533%2C2603.26041%2C2603.26266%2C2604.00073%2C2604.00842&max_results=50"}], "id": "arxiv:2602.09856", "identifiers": {"arxiv": "2602.09856"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:59Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.09856"}], "name": "Code2World: A GUI World Model via Renderable Code Generation", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and released artifacts have not been independently reproduced.", "published_at": "2026-02-10", "relations": [], "review_status": "curated", "scope": "core", "summary": "Code2World predicts future GUI screens through renderable code, trained on AndroidCode trajectories with supervised learning and render-aware reinforcement learning. It evaluates visual prediction and downstream AndroidWorld navigation with the learned world model.", "topics": ["world-models", "data-generation", "reinforcement-learning", "mobile-navigation"], "updated_at": "2026-02-10", "url": "https://arxiv.org/abs/2602.09856"}
{"aliases": [], "authors": ["Lepeng Zhao", "Zhenhua Zou", "Shuo Li", "Zhuotao Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "727279bf83a67f66fa8f173d028936fe0bdae63e9f23800d98476da10201ad0d", "submitted_at": "2026-02-08T15:50:04Z", "updated_at": "2026-04-26T01:34:23Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2602.10139v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2602.10139", "identifiers": {"arxiv": "2602.10139"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.10139"}], "name": "Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-02-08", "relations": [], "review_status": "curated", "scope": "core", "summary": "An anonymization framework replaces sensitive screen content and instructions with consistent, type-preserving placeholders while mediating actions through a local interaction proxy. Experiments on AndroidLab and PrivScreen examine the privacy–utility trade-off when mobile GUI agents operate over these transformed interfaces.", "topics": ["safety-security", "screen-understanding", "mobile-navigation"], "updated_at": "2026-04-26", "url": "https://arxiv.org/abs/2602.10139"}
{"aliases": [], "authors": ["Congmin Zheng", "Xiaoyun Mo", "Xinbei Ma", "Qiqiang Lin", "Yin Zhao", "Jiachen Zhu", "Xingyu Lou", "Jun Wang", "Zhaoxiang Wang", "Weiwen Liu", "Zhuosheng Zhang", "Yong Yu", "Weinan Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ffec5a47e31b541cfdf0fb3c143b55cbb28119463731d9a6f3add0fe116caea9", "submitted_at": "2026-02-12T03:31:40Z", "updated_at": "2026-02-12T03:31:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.11524v1"}}, "environments": ["android", "web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2602.11524", "identifiers": {"arxiv": "2602.11524"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.11524"}], "name": "Adaptive Milestone Reward for GUI Agents", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and released artifacts have not been independently reproduced.", "published_at": "2026-02-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "ADMIRE extracts milestones from successful GUI explorations to provide adaptive intermediate rewards. It assigns credit differently to successful and failed trajectories and evaluates training on AndroidWorld, with additional transfer studies in web and embodied settings.", "topics": ["reinforcement-learning", "reward-models", "mobile-navigation"], "updated_at": "2026-02-12", "url": "https://arxiv.org/abs/2602.11524"}
{"aliases": [], "authors": ["Jiazheng Sun", "Mingxuan Li", "Yingying Zhang", "Jiayang Niu", "Yachen Wu", "Ruihan Jin", "Shuyu Lei", "Pengrongrui Tan", "Zongyu Zhang", "Ruoyi Wang", "Jiachen Yang", "Boyu Yang", "Jiacheng Liu", "Xin Peng"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2bbba09ca845f4fb772516d26d59fc3d99f8e87ba3657bb29c3c062b50925ec5", "submitted_at": "2026-02-12T09:25:15Z", "updated_at": "2026-02-12T09:25:15Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.11750v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2602.11750", "identifiers": {"arxiv": "2602.11750"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.11750"}], "name": "AmbiBench: Benchmarking Mobile GUI Agents Beyond One-Shot Instructions in the Wild", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-02-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "AmbiBench evaluates mobile GUI agents under four levels of instruction clarity, including tasks requiring active clarification. Its MUSE evaluator separately audits outcomes, execution quality and interaction quality to study alignment with user intent.", "topics": ["evaluation", "human-in-the-loop", "mobile-navigation"], "updated_at": "2026-02-12", "url": "https://arxiv.org/abs/2602.11750"}
{"aliases": [], "authors": ["Yiping Xie", "Song Chen", "Jingxuan Xing", "Wei Jiang", "Zekun Zhu", "Yingyao Wang", "Pi Bu", "Jun Song", "Yuning Jiang", "Bo Zheng"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "db31c6ca303f0c7dc43f24dd1eea69621b1e557af33122386945154e8236ab78", "submitted_at": "2026-03-09T16:04:08Z", "updated_at": "2026-03-31T03:08:51Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2603.08533v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2603.08533", "identifiers": {"arxiv": "2603.08533"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2603.08533"}], "name": "SecAgent: Efficient Mobile GUI Agent with Semantic Context", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced. Mobile use is explicit, but the abstract does not identify a mobile operating system.", "published_at": "2026-03-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents a Chinese mobile GUI dataset and navigation benchmark together with SecAgent, which compresses previous screenshots and actions into semantic summaries. The agent is trained with supervised and reinforcement fine-tuning to use this compact interaction context.", "topics": ["mobile-navigation", "memory", "reinforcement-learning"], "updated_at": "2026-03-31", "url": "https://arxiv.org/abs/2603.08533"}
{"aliases": [], "authors": ["Yang Li", "Yuchen Liu", "Haoyu Lu", "Zhiqiang Xia", "Hongzhen Wang", "Kaiyang Han", "Changpeng Yang", "Jinyang Wu", "Jiaming Xu", "Runyu Shi", "Ying Huang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bf6c3df80e405968d9ae2353639f3e039d3fcf8351d89db212bda038e3dfac9b", "submitted_at": "2026-03-16T09:45:33Z", "updated_at": "2026-03-16T09:45:33Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.15039v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2603.15039", "identifiers": {"arxiv": "2603.15039"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:39Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2603.15039"}], "name": "GUI-CEval: A Hierarchical and Comprehensive Chinese Benchmark for Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-03-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "GUI-CEval evaluates Chinese mobile GUI agents through a hierarchy of atomic abilities and application-level tasks collected on physical devices. Its diagnostics cover perception, planning, reflection, execution and post-action evaluation across a broad set of apps.", "topics": ["evaluation", "mobile-navigation", "self-reflection", "screen-understanding"], "updated_at": "2026-03-16", "url": "https://arxiv.org/abs/2603.15039"}
{"aliases": [], "authors": ["Yizhe Zhao", "Yongjian Fu", "Zihao Feng", "Hao Pan", "Yongheng Deng", "Yaoxue Zhang", "Ju Ren"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f25f4999fc9d20433f96e22651311cccf78b5e2ad7cbc5578fe1765ac8be6a00", "submitted_at": "2026-03-20T12:19:41Z", "updated_at": "2026-03-20T12:19:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.20351v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "kind", "scope", "environments", "topics", "summary", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}], "id": "arxiv:2603.20351", "identifiers": {"arxiv": "2603.20351"}, "kind": "paper", "last_verified_at": "2026-10-18T04:21:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2603.20351"}], "name": "MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation", "notes": "Reviewed against the complete official arXiv abstract. Experimental results and linked artifact availability have not been independently reproduced.", "published_at": "2026-03-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "MANA combines visual, temporal and exploration signals to guide navigation toward mobile advertisements. It evaluates ad detection and interaction cost on commercial smartphones, including obfuscated-ad cases.", "topics": ["mobile-navigation", "screen-understanding", "efficiency", "safety-security"], "updated_at": "2026-03-20", "url": "https://arxiv.org/abs/2603.20351"}
{"aliases": [], "authors": ["Zichuan Lin", "Feiyu Liu", "Yijun Yang", "Jiafei Lyu", "Yiming Gao", "Yicheng Liu", "Zhicong Lu", "Yangbin Yu", "Mingyu Yang", "Junyou Li", "Deheng Ye", "Jie Jiang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aa03c8716edf782ce1a86e404107aa2569be63484dfedb472d3710dc82f405d0", "submitted_at": "2026-03-25T17:10:29Z", "updated_at": "2026-03-25T17:10:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.24533v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2603.24533", "identifiers": {"arxiv": "2603.24533"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:39Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2603.24533"}], "name": "UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2026-03-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a two-stage mobile GUI learner that first co-evolves trajectories and policies through rejection fine-tuning. Group Relative Self-Distillation then uses successful rollout branches to provide step-level supervision for failed trajectories, evaluated on AndroidWorld.", "topics": ["imitation-learning", "data-generation", "mobile-navigation"], "updated_at": "2026-03-25", "url": "https://arxiv.org/abs/2603.24533"}
{"aliases": [], "authors": ["Hongyi Nie", "Xunyuan Liu", "Yudong Bai", "Yaqing Wang", "Yang Liu", "Quanming Yao", "Zhen Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1c71b713efd6ea47e7c78f5dd51d06c5cfdba750529bfbcdfc8e1c69897cbcc9", "submitted_at": "2026-03-31T06:37:12Z", "updated_at": "2026-03-31T06:37:12Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.29318v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2603.29318", "identifiers": {"arxiv": "2603.29318"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:39Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2603.29318"}], "name": "PSPA-Bench: A Personalized Benchmark for Smartphone GUI Agent", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-03-31", "relations": [], "review_status": "curated", "scope": "core", "summary": "PSPA-Bench evaluates personalized smartphone GUI behavior using user-specific instructions and a process-aware assessment of interaction traces. Its comparison of GUI agents diagnoses weaknesses in adapting workflows and preferences rather than measuring generic task completion alone.", "topics": ["evaluation", "mobile-navigation"], "updated_at": "2026-03-31", "url": "https://arxiv.org/abs/2603.29318"}
{"aliases": [], "authors": ["Zhengyang Tang", "Ke Ji", "Xidong Wang", "Zihan Ye", "Xinyuan Wang", "Yiduo Guo", "Ziniu Li", "Chenxin Li", "Jingyuan Hu", "Shunian Chen", "Tongxu Luo", "Jiaxi Bi", "Zeyu Qin", "Shaobo Wang", "Xin Lai", "Pengyuan Lyu", "Junyi Li", "Can Xu", "Chengquan Zhang", "Han Hu", "Ming Yan", "Benyou Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3f137028b7608598fb1885a0bf1330e00c9404851571f856665aae1af1d9d63c", "submitted_at": "2026-04-01T14:50:50Z", "updated_at": "2026-04-02T13:51:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2604.00986v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}], "id": "arxiv:2604.00986", "identifiers": {"arxiv": "2604.00986"}, "kind": "paper", "last_verified_at": "2026-10-18T10:54:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.00986"}], "name": "Do Phone-Use Agents Respect Your Privacy?", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-04-01", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces MyPhoneBench to verify whether phone-use agents minimize personal data disclosure when filling forms during benign mobile tasks.", "topics": ["safety-security", "mobile-navigation", "evaluation"], "updated_at": "2026-04-02", "url": "https://arxiv.org/abs/2604.00986"}
{"aliases": [], "authors": ["Yushi Feng", "Junye Du", "Qifan Wang", "Zizhan Ma", "Qian Niu", "Yutaka Matsuo", "Long Feng", "Lequan Yu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e53647528b9ee9d98f93ee665d0d886f9b400a129873e240704041df291f5749", "submitted_at": "2026-04-10T09:41:21Z", "updated_at": "2026-04-10T09:41:21Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.09155v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:00Z", "role": "primary", "sha256": "4d09ebfb093e43a4c44adef86c8fa8374f90d907fc33bd8e12a1315e62d5a583", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2603.12823%2C2603.14707%2C2603.15039%2C2603.17357%2C2603.18429%2C2603.19191%2C2603.24440%2C2603.25226%2C2603.25864%2C2603.26211%2C2603.26648%2C2603.29318%2C2604.01535%2C2604.02947%2C2604.04399%2C2604.05477%2C2604.06126%2C2604.06182%2C2604.06367%2C2604.07429%2C2604.08455%2C2604.08516%2C2604.08523%2C2604.09155%2C2604.09574%2C2604.09587%2C2604.09815%2C2604.09937%2C2604.11259%2C2604.11784%2C2604.12284%2C2604.13019%2C2604.13822%2C2604.14113%2C2604.14262%2C2604.14956%2C2604.15093%2C2604.15309%2C2604.17817%2C2604.17821%2C2604.18860%2C2604.24964%2C2604.25380%2C2604.25562%2C2604.27151%2C2604.27253%2C2604.27776%2C2605.00642%2C2605.06393%2C2605.06664&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:00Z", "role": "primary", "sha256": "4d09ebfb093e43a4c44adef86c8fa8374f90d907fc33bd8e12a1315e62d5a583", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2603.12823%2C2603.14707%2C2603.15039%2C2603.17357%2C2603.18429%2C2603.19191%2C2603.24440%2C2603.25226%2C2603.25864%2C2603.26211%2C2603.26648%2C2603.29318%2C2604.01535%2C2604.02947%2C2604.04399%2C2604.05477%2C2604.06126%2C2604.06182%2C2604.06367%2C2604.07429%2C2604.08455%2C2604.08516%2C2604.08523%2C2604.09155%2C2604.09574%2C2604.09587%2C2604.09815%2C2604.09937%2C2604.11259%2C2604.11784%2C2604.12284%2C2604.13019%2C2604.13822%2C2604.14113%2C2604.14262%2C2604.14956%2C2604.15093%2C2604.15309%2C2604.17817%2C2604.17821%2C2604.18860%2C2604.24964%2C2604.25380%2C2604.25562%2C2604.27151%2C2604.27253%2C2604.27776%2C2605.00642%2C2605.06393%2C2605.06664&max_results=50"}], "id": "arxiv:2604.09155", "identifiers": {"arxiv": "2604.09155"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:00Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.09155"}], "name": "CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced. The annotation describes risk calibration without asserting an unconditional safety guarantee.", "published_at": "2026-04-10", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces CORA, which calibrates a risk model to choose between executing and abstaining from mobile GUI actions, then diagnoses rejected actions to suggest interventions. Phone-Harm provides step-level safety labels for evaluating this safeguarding process.", "topics": ["safety-security", "mobile-navigation", "evaluation"], "updated_at": "2026-04-10", "url": "https://arxiv.org/abs/2604.09155"}
{"aliases": [], "authors": ["Fei Tang", "Zhiqiong Lu", "Boxuan Zhang", "Weiming Lu", "Jun Xiao", "Yueting Zhuang", "Yongliang Shen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "df56b38203bc5ec8d7e871eb2ad9fca9891a049df62b7d72796fe400eb8bce5e", "submitted_at": "2026-04-13T17:52:04Z", "updated_at": "2026-04-13T17:52:04Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.11784v1"}}, "environments": ["android", "harmonyos", "ios"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2604.11784", "identifiers": {"arxiv": "2604.11784"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:39Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.11784"}], "name": "ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2026-04-13", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents ClawGUI, a shared harness for GUI-agent reinforcement learning, benchmark evaluation and deployment on mobile devices. It combines parallel virtual and physical environments, process rewards, and hybrid CLI-GUI execution with persistent memory.", "topics": ["reinforcement-learning", "evaluation", "tool-integration", "mobile-navigation"], "updated_at": "2026-04-13", "url": "https://arxiv.org/abs/2604.11784"}
{"aliases": [], "authors": ["Zhengxi Lu", "Fei Tang", "Guangyi Liu", "Kaitao Song", "Xu Tan", "Jin Ma", "Wenqi Zhang", "Weiming Lu", "Jun Xiao", "Yueting Zhuang", "Yongliang Shen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d6e81b448c9c22e2fd25dce519db3fdc0585b0265b94d448751d7a37ed910dfa", "submitted_at": "2026-04-15T12:55:46Z", "updated_at": "2026-04-15T12:55:46Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.13822v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:00Z", "role": "primary", "sha256": "4d09ebfb093e43a4c44adef86c8fa8374f90d907fc33bd8e12a1315e62d5a583", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2603.12823%2C2603.14707%2C2603.15039%2C2603.17357%2C2603.18429%2C2603.19191%2C2603.24440%2C2603.25226%2C2603.25864%2C2603.26211%2C2603.26648%2C2603.29318%2C2604.01535%2C2604.02947%2C2604.04399%2C2604.05477%2C2604.06126%2C2604.06182%2C2604.06367%2C2604.07429%2C2604.08455%2C2604.08516%2C2604.08523%2C2604.09155%2C2604.09574%2C2604.09587%2C2604.09815%2C2604.09937%2C2604.11259%2C2604.11784%2C2604.12284%2C2604.13019%2C2604.13822%2C2604.14113%2C2604.14262%2C2604.14956%2C2604.15093%2C2604.15309%2C2604.17817%2C2604.17821%2C2604.18860%2C2604.24964%2C2604.25380%2C2604.25562%2C2604.27151%2C2604.27253%2C2604.27776%2C2605.00642%2C2605.06393%2C2605.06664&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:00Z", "role": "primary", "sha256": "4d09ebfb093e43a4c44adef86c8fa8374f90d907fc33bd8e12a1315e62d5a583", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2603.12823%2C2603.14707%2C2603.15039%2C2603.17357%2C2603.18429%2C2603.19191%2C2603.24440%2C2603.25226%2C2603.25864%2C2603.26211%2C2603.26648%2C2603.29318%2C2604.01535%2C2604.02947%2C2604.04399%2C2604.05477%2C2604.06126%2C2604.06182%2C2604.06367%2C2604.07429%2C2604.08455%2C2604.08516%2C2604.08523%2C2604.09155%2C2604.09574%2C2604.09587%2C2604.09815%2C2604.09937%2C2604.11259%2C2604.11784%2C2604.12284%2C2604.13019%2C2604.13822%2C2604.14113%2C2604.14262%2C2604.14956%2C2604.15093%2C2604.15309%2C2604.17817%2C2604.17821%2C2604.18860%2C2604.24964%2C2604.25380%2C2604.25562%2C2604.27151%2C2604.27253%2C2604.27776%2C2605.00642%2C2605.06393%2C2605.06664&max_results=50"}], "id": "arxiv:2604.13822", "identifiers": {"arxiv": "2604.13822"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:00Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.13822"}], "name": "UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-04-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "UI-Copilot separates GUI execution from on-demand memory retrieval and numerical assistance. Its training procedure treats tool selection and multi-turn task execution as distinct optimization targets while keeping persistent observations outside transient context.", "topics": ["tool-integration", "memory", "planning", "long-horizon", "mobile-navigation"], "updated_at": "2026-04-15", "url": "https://arxiv.org/abs/2604.13822"}
{"aliases": [], "authors": ["Kanzhi Cheng", "Zehao Li", "Zheng Ma", "Nuo Chen", "Jialin Cao", "Qiushi Sun", "Zichen Ding", "Fangzhi Xu", "Hang Yan", "Jiajun Chen", "Anh Tuan Luu", "Jianbing Zhang", "Lewei Lu", "Dahua Lin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "12c2e5e2ae9bdc871bb63d195194c5387129accf5e8b26d12b21650b92fe82b6", "submitted_at": "2026-04-16T14:53:08Z", "updated_at": "2026-04-16T14:53:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.15093v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:00Z", "role": "primary", "sha256": "4d09ebfb093e43a4c44adef86c8fa8374f90d907fc33bd8e12a1315e62d5a583", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2603.12823%2C2603.14707%2C2603.15039%2C2603.17357%2C2603.18429%2C2603.19191%2C2603.24440%2C2603.25226%2C2603.25864%2C2603.26211%2C2603.26648%2C2603.29318%2C2604.01535%2C2604.02947%2C2604.04399%2C2604.05477%2C2604.06126%2C2604.06182%2C2604.06367%2C2604.07429%2C2604.08455%2C2604.08516%2C2604.08523%2C2604.09155%2C2604.09574%2C2604.09587%2C2604.09815%2C2604.09937%2C2604.11259%2C2604.11784%2C2604.12284%2C2604.13019%2C2604.13822%2C2604.14113%2C2604.14262%2C2604.14956%2C2604.15093%2C2604.15309%2C2604.17817%2C2604.17821%2C2604.18860%2C2604.24964%2C2604.25380%2C2604.25562%2C2604.27151%2C2604.27253%2C2604.27776%2C2605.00642%2C2605.06393%2C2605.06664&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:00Z", "role": "primary", "sha256": "4d09ebfb093e43a4c44adef86c8fa8374f90d907fc33bd8e12a1315e62d5a583", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2603.12823%2C2603.14707%2C2603.15039%2C2603.17357%2C2603.18429%2C2603.19191%2C2603.24440%2C2603.25226%2C2603.25864%2C2603.26211%2C2603.26648%2C2603.29318%2C2604.01535%2C2604.02947%2C2604.04399%2C2604.05477%2C2604.06126%2C2604.06182%2C2604.06367%2C2604.07429%2C2604.08455%2C2604.08516%2C2604.08523%2C2604.09155%2C2604.09574%2C2604.09587%2C2604.09815%2C2604.09937%2C2604.11259%2C2604.11784%2C2604.12284%2C2604.13019%2C2604.13822%2C2604.14113%2C2604.14262%2C2604.14956%2C2604.15093%2C2604.15309%2C2604.17817%2C2604.17821%2C2604.18860%2C2604.24964%2C2604.25380%2C2604.25562%2C2604.27151%2C2604.27253%2C2604.27776%2C2605.00642%2C2605.06393%2C2605.06664&max_results=50"}], "id": "arxiv:2604.15093", "identifiers": {"arxiv": "2604.15093"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:00Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.15093"}], "name": "OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2026-04-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents OpenMobile, which builds exploration-based environment memory to synthesize task instructions and switches between learner and expert policies during trajectory collection. The resulting data includes recovery behavior and is tested through mobile-agent training and benchmark-overlap analysis.", "topics": ["data-generation", "imitation-learning", "mobile-navigation"], "updated_at": "2026-04-16", "url": "https://arxiv.org/abs/2604.15093"}
{"aliases": [], "authors": ["Shiquan Zhang", "Tianyi Zhang", "Le Fang", "Simon D'Alfonso", "Hong Jia", "Vassilis Kostakos"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "176f4d68e2f5084bee1938ee1399978052cdce2d2250ef06c16ddbf49c977da1", "submitted_at": "2026-04-20T05:15:14Z", "updated_at": "2026-04-20T05:15:14Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.17817v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:32:00Z", "role": "primary", "sha256": "4d09ebfb093e43a4c44adef86c8fa8374f90d907fc33bd8e12a1315e62d5a583", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2603.12823%2C2603.14707%2C2603.15039%2C2603.17357%2C2603.18429%2C2603.19191%2C2603.24440%2C2603.25226%2C2603.25864%2C2603.26211%2C2603.26648%2C2603.29318%2C2604.01535%2C2604.02947%2C2604.04399%2C2604.05477%2C2604.06126%2C2604.06182%2C2604.06367%2C2604.07429%2C2604.08455%2C2604.08516%2C2604.08523%2C2604.09155%2C2604.09574%2C2604.09587%2C2604.09815%2C2604.09937%2C2604.11259%2C2604.11784%2C2604.12284%2C2604.13019%2C2604.13822%2C2604.14113%2C2604.14262%2C2604.14956%2C2604.15093%2C2604.15309%2C2604.17817%2C2604.17821%2C2604.18860%2C2604.24964%2C2604.25380%2C2604.25562%2C2604.27151%2C2604.27253%2C2604.27776%2C2605.00642%2C2605.06393%2C2605.06664&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:32:00Z", "role": "primary", "sha256": "4d09ebfb093e43a4c44adef86c8fa8374f90d907fc33bd8e12a1315e62d5a583", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2603.12823%2C2603.14707%2C2603.15039%2C2603.17357%2C2603.18429%2C2603.19191%2C2603.24440%2C2603.25226%2C2603.25864%2C2603.26211%2C2603.26648%2C2603.29318%2C2604.01535%2C2604.02947%2C2604.04399%2C2604.05477%2C2604.06126%2C2604.06182%2C2604.06367%2C2604.07429%2C2604.08455%2C2604.08516%2C2604.08523%2C2604.09155%2C2604.09574%2C2604.09587%2C2604.09815%2C2604.09937%2C2604.11259%2C2604.11784%2C2604.12284%2C2604.13019%2C2604.13822%2C2604.14113%2C2604.14262%2C2604.14956%2C2604.15093%2C2604.15309%2C2604.17817%2C2604.17821%2C2604.18860%2C2604.24964%2C2604.25380%2C2604.25562%2C2604.27151%2C2604.27253%2C2604.27776%2C2605.00642%2C2605.06393%2C2605.06664&max_results=50"}], "id": "arxiv:2604.17817", "identifiers": {"arxiv": "2604.17817"}, "kind": "paper", "last_verified_at": "2026-10-16T06:32:00Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.17817"}], "name": "Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-04-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "DailyDroid compares text-only and text-plus-screenshot agents on everyday Android tasks across multiple apps and difficulty levels. Its failure analysis examines accessibility, observation modality and agent/application behavior.", "topics": ["evaluation", "mobile-navigation", "screen-understanding", "robustness"], "updated_at": "2026-04-20", "url": "https://arxiv.org/abs/2604.17817"}
{"aliases": [], "authors": ["Haowen Hu", "Pengzhou Cheng", "Zheng Wu", "Lingzhong Dong", "Gongshen Liu", "Zhuosheng Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8738f2584f096c1d54555adcf8bdbbb283f0d3178eb1f5e7b7c8a61b2965c15e", "submitted_at": "2026-05-02T02:54:36Z", "updated_at": "2026-05-02T02:54:36Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.01208v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2605.01208", "identifiers": {"arxiv": "2605.01208"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:39Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.01208"}], "name": "Faithful Mobile GUI Agents with Guided Advantage Estimator", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2026-05-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Faithful-Agent, which first teaches abstention under perturbed evidence and then refines GUI policies with an anchor-based, variance-adaptive advantage estimator. A thought-action consistency reward encourages decisions grounded in displayed evidence and instructions.", "topics": ["reinforcement-learning", "robustness", "mobile-navigation"], "updated_at": "2026-05-02", "url": "https://arxiv.org/abs/2605.01208"}
{"aliases": [], "authors": ["Xiaoming Ren", "Ru Zhen", "Chao Li", "Yang Song", "Qiuxia Hou", "Yanhao Zhang", "Peng Liu", "Qi Qi", "Quanlong Zheng", "Qi Wu", "Zhenyi Liao", "Binqiang Pan", "Haobo Ji", "Haonan Lu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2ece93c00c5556dfe50ddd0ba3f52b725f34d1bee18ea3565951bb78343d8ed0", "submitted_at": "2026-05-07T06:58:34Z", "updated_at": "2026-05-21T06:55:40Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.05765v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:00:51.952206+00:00", "role": "primary", "sha256": "5cd7fb95d5ee8e8c473e0c9d5b892bf50ee425604c6a320e8e9a12eff17120a1", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:00:51.952206+00:00", "role": "primary", "sha256": "5cd7fb95d5ee8e8c473e0c9d5b892bf50ee425604c6a320e8e9a12eff17120a1", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:14:10.101459+00:00", "role": "primary", "sha256": "80375cd810dcda2e9ccca2c6fbee44730de8449972036c548bde312566b20673", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/pdf/2605.05765v2"}], "id": "arxiv:2605.05765", "identifiers": {"arxiv": "2605.05765"}, "kind": "paper", "last_verified_at": "2026-10-18T10:00:51.952206+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.05765"}], "name": "X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction", "notes": "The report presents demonstrations. Its behavior-cloning component captures runtime skills; it does not establish policy-weight imitation training, and literal trace replay is described as future work. No general benchmark result or release completeness is inferred. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (2 Framework; 3 Omni Perception; 4 Omni Memory; 5.1 Omni Action in App Ecosystem; 5.2 Trajectory Cloned Execution); not an entire-paper reading or reproduction claim.", "published_at": "2026-05-07", "relations": [], "review_status": "curated", "scope": "core", "summary": "Describes an Android agent architecture combining multimodal perception, working and personal memory, hybrid XML/visual grounding, and reusable skills captured from user interactions.", "topics": ["mobile-navigation", "memory", "grounding", "workflow"], "updated_at": "2026-05-21", "url": "https://arxiv.org/abs/2605.05765"}
{"aliases": [], "authors": ["Shilong Jin", "Lanjun Wang", "Zhuosheng Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "52c1bf4c614ac05a55f2c2c66d3ac4eeb1bf31743814a45eb9f0ce064b6baaab", "submitted_at": "2026-05-16T08:51:57Z", "updated_at": "2026-05-16T08:51:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.16883v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2605.16883", "identifiers": {"arxiv": "2605.16883"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:36Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.16883"}], "name": "SE-GA: Memory-Augmented Self-Evolution for GUI Agents", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-05-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "SE-GA retrieves hierarchical memories during inference and uses the collected experience in a separate policy-improvement pipeline. Its evaluation includes offline grounding/action tasks and online Android interaction, which measure different capabilities.", "topics": ["memory", "interaction-history", "mobile-navigation", "grounding", "evaluation"], "updated_at": "2026-05-16", "url": "https://arxiv.org/abs/2605.16883"}
{"aliases": [], "authors": ["Felix Henry", "Lihan Lin", "Jiangyou Zhu", "Yangfan", "Bingqian Zhang", "Min Chen", "Shiyu Huang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "99e8e0039ec99ef8f6a6ef3900cb74a62ddd5ae4f8df30629110969290028e6a", "submitted_at": "2026-04-03T08:57:06Z", "updated_at": "2026-09-28T02:42:06Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.18758v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2605.18758", "identifiers": {"arxiv": "2605.18758"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:39Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.18758"}], "name": "OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experiments, reported performance and artifact availability have not been independently reproduced.", "published_at": "2026-04-03", "relations": [], "review_status": "curated", "scope": "core", "summary": "OmniGUI evaluates step-level action prediction from interleaved smartphone screenshots, synchronous audio and video. Expert demonstrations carry multimodal-dependency annotations, and initial baselines use native multimodal models as agent proxies to study temporal and audio-related failures.", "topics": ["evaluation", "action-prediction", "video", "mobile-navigation"], "updated_at": "2026-09-28", "url": "https://arxiv.org/abs/2605.18758"}
{"aliases": [], "authors": ["Runxi Huang", "Liyu Zhang", "Shengzhong Liu", "Xiaomin Ouyang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "97467a9a1d3c456a0078e96ebb128efa43412a3139a7a68beb4e6dd7b5f0674d", "submitted_at": "2026-05-26T04:53:53Z", "updated_at": "2026-05-26T04:53:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.26546v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2605.26546", "identifiers": {"arxiv": "2605.26546"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:36Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.26546"}], "name": "MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Exploration", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-05-26", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileExplorer probes relevant UI elements while an on-device model is reasoning, then supplies the exploration trace as compact context. A two-level rollback mechanism restores the working state when simple backtracking fails.", "topics": ["mobile-navigation", "efficiency", "memory", "robustness"], "updated_at": "2026-05-26", "url": "https://arxiv.org/abs/2605.26546"}
{"aliases": [], "authors": ["Yifan Sui", "Xin Huang", "Hongbing Li", "Fang Xu", "Jiahe Lv", "Haolong Yan", "Yeqing Shen", "Litao Liu", "Zhimin Fan", "Ziyang Meng", "Jia Wang", "Junbo Qi", "Kaijun Tan", "Zheng Ge", "Xiangyu Zhang", "Daxin Jiang", "Osamu Yoshie"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0c89b8b5ef5aa17fe747201285104544648449804cc2229a77577d217763f497", "submitted_at": "2026-05-26T23:19:42Z", "updated_at": "2026-05-26T23:19:42Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.27761v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2605.27761", "identifiers": {"arxiv": "2605.27761"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:36Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.27761"}], "name": "AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experiments, reported performance and artifact availability have not been independently reproduced.", "published_at": "2026-05-26", "relations": [], "review_status": "curated", "scope": "core", "summary": "AndroidDaily evaluates mobile GUI agents on daily workflows in closed-source Android apps. Its GRADE evaluator follows visual trajectories against operational obligations, output-quality requirements and negative constraints, producing process-level diagnostics without hidden app state.", "topics": ["mobile-navigation", "evaluation", "long-horizon", "robustness"], "updated_at": "2026-05-26", "url": "https://arxiv.org/abs/2605.27761"}
{"aliases": [], "authors": ["Yuxiang Chai", "Han Xiao", "Xinyu Fu", "Jinpeng Chen", "Rui Liu", "Hongsheng Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "461790f351a2816004027cc58d07f79ee7c670ed5064c59b1651a4efb84ff2bf", "submitted_at": "2026-05-28T07:49:09Z", "updated_at": "2026-05-28T07:49:09Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.29534v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2605.29534", "identifiers": {"arxiv": "2605.29534"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:36Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.29534"}], "name": "UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-05-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "UI-KOBE explores mobile applications to build graphs of UI states and executable transitions. A lightweight agent then matches its current screenshot to the graph and chooses a transition, local action, completion signal or fallback action.", "topics": ["mobile-navigation", "planning", "state-tracking", "memory", "efficiency"], "updated_at": "2026-05-28", "url": "https://arxiv.org/abs/2605.29534"}
{"aliases": [], "authors": ["Siyu Shen", "Fenghao Xu", "Wenrui Diao", "Kehuan Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fed1c6e109cc5d34aebe3bb333955e8bf792264d4c1ed0893d76534a77649afd", "submitted_at": "2026-06-10T20:48:39Z", "updated_at": "2026-06-16T03:15:00Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.12666v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2606.12666", "identifiers": {"arxiv": "2606.12666"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:36Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2606.12666"}], "name": "CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-06-10", "relations": [], "review_status": "curated", "scope": "core", "summary": "CAPED filters mobile screenshots before upload by combining task requirements, screen context and parsed UI elements to mask incidental private content. AndroidWorld and a controlled seeded privacy evaluation examine leakage reduction alongside task utility and prototype costs.", "topics": ["safety-security", "screen-understanding", "mobile-navigation"], "updated_at": "2026-06-16", "url": "https://arxiv.org/abs/2606.12666"}
{"aliases": [], "authors": ["Chenxin Li", "Zhengyao Fang", "Zhengyang Tang", "Pengyuan Lyu", "Xingran Zhou", "Xin Lai", "Fei Tang", "Liang Wu", "Yiduo Guo", "Weinong Wang", "Junyi Li", "Yi Zhang", "Yang Ding", "Huawen Shen", "Sunqi Fan", "Shangpin Peng", "Zheng Ruan", "Anran Zhang", "Benyou Wang", "Chengquan Zhang", "Han Hu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "280ec12bcb246f1f07cf3627011945e8a9ff4afed93b1fb2937f2d6b1bc1323b", "submitted_at": "2026-06-12T15:01:32Z", "updated_at": "2026-06-12T15:01:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.14832v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:05Z", "role": "primary", "sha256": "2e5722527f8da4b2cf06372d1e2daccd33ef7fdc7151704b411a0bddd734beae", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2606.10423%2C2606.10522%2C2606.10742%2C2606.11078%2C2606.11520%2C2606.12485%2C2606.12666%2C2606.13239%2C2606.13385%2C2606.14106%2C2606.14832%2C2606.15017%2C2606.15034%2C2606.16659%2C2606.16748%2C2606.16802%2C2606.17321%2C2606.17645%2C2606.17929%2C2606.18448%2C2606.18671%2C2606.18890%2C2606.19388%2C2606.19926%2C2606.19930%2C2606.20363%2C2606.20636%2C2606.20717%2C2606.20724%2C2606.20785%2C2606.21654%2C2606.22864%2C2606.22948%2C2606.23449%2C2606.24515%2C2606.24525%2C2606.25705%2C2606.25760%2C2606.27330%2C2606.27595%2C2606.29445%2C2606.29537%2C2606.29705%2C2606.30697%2C2606.31154%2C2606.31270%2C2606.31410%2C2606.31612%2C2607.00502%2C2607.04425&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:33:05Z", "role": "primary", "sha256": "2e5722527f8da4b2cf06372d1e2daccd33ef7fdc7151704b411a0bddd734beae", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2606.10423%2C2606.10522%2C2606.10742%2C2606.11078%2C2606.11520%2C2606.12485%2C2606.12666%2C2606.13239%2C2606.13385%2C2606.14106%2C2606.14832%2C2606.15017%2C2606.15034%2C2606.16659%2C2606.16748%2C2606.16802%2C2606.17321%2C2606.17645%2C2606.17929%2C2606.18448%2C2606.18671%2C2606.18890%2C2606.19388%2C2606.19926%2C2606.19930%2C2606.20363%2C2606.20636%2C2606.20717%2C2606.20724%2C2606.20785%2C2606.21654%2C2606.22864%2C2606.22948%2C2606.23449%2C2606.24515%2C2606.24525%2C2606.25705%2C2606.25760%2C2606.27330%2C2606.27595%2C2606.29445%2C2606.29537%2C2606.29705%2C2606.30697%2C2606.31154%2C2606.31270%2C2606.31410%2C2606.31612%2C2607.00502%2C2607.04425&max_results=50"}], "id": "arxiv:2606.14832", "identifiers": {"arxiv": "2606.14832"}, "kind": "paper", "last_verified_at": "2026-10-16T06:33:05Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2606.14832"}], "name": "PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experiments, reported performance and artifact availability have not been independently reproduced.", "published_at": "2026-06-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "PhoneHarness routes phone workflows across GUI actions, device-side commands and host tools while retaining auditable execution traces. Its accompanying benchmark checks observable task side effects, separating mixed-action execution from plausible final-answer generation.", "topics": ["mobile-navigation", "tool-integration", "evaluation", "workflow"], "updated_at": "2026-06-12", "url": "https://arxiv.org/abs/2606.14832"}
{"aliases": [], "authors": ["Guangyi Liu", "Pengxiang Zhao", "Gao Wu", "Yiwen Yin", "Mading Li", "Liang Liu", "Congxiao Liu", "Zhang Qi", "Mengyan Wang", "Liang Guo", "Jiangning Zhang", "Yong Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cab809618ea4e218da26b4ae11bf937859c3a4bc240c91dd27b3a0d333737069", "submitted_at": "2026-06-18T08:29:33Z", "updated_at": "2026-08-07T03:54:59Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.19930v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:36Z", "role": "primary", "sha256": "aeacc1a41bb90f3d296823356174fe77d1547ffbe7cd56652cf9d98fca09206c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=200&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2606.19930", "identifiers": {"arxiv": "2606.19930"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:36Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2606.19930"}], "name": "MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experiments, reported performance and artifact availability have not been independently reproduced.", "published_at": "2026-06-18", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileForge couples real-app exploration and generated tasks with hierarchical feedback for mobile-agent adaptation. Its optimizer turns trajectory outcomes, step feedback and corrective hints into contextualized GRPO updates, with evaluation on AndroidWorld and a GUI-only MobileWorld split.", "topics": ["mobile-navigation", "reinforcement-learning", "data-generation", "evaluation"], "updated_at": "2026-08-07", "url": "https://arxiv.org/abs/2606.19930"}
{"aliases": [], "authors": ["Daniel Beechey", "Derek Yuen", "Jianheng Liu", "Dezhao Luo", "Tiantian He", "Weilin Luo", "Jun Wang", "Kun Shao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9e761b20caa6882605ecfd6cd001aeda4a2d36b2e702eea9a6d70451fc0ea9eb", "submitted_at": "2026-05-26T13:32:14Z", "updated_at": "2026-05-26T13:32:14Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.20622v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:00:51.952206+00:00", "role": "primary", "sha256": "5cd7fb95d5ee8e8c473e0c9d5b892bf50ee425604c6a320e8e9a12eff17120a1", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:00:51.952206+00:00", "role": "primary", "sha256": "5cd7fb95d5ee8e8c473e0c9d5b892bf50ee425604c6a320e8e9a12eff17120a1", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:14:00.181958+00:00", "role": "primary", "sha256": "e4711466886372760daa83384cb4d129d54fdcfe320be6e91fb7b4971d1a61de", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/pdf/2606.20622v1"}], "id": "arxiv:2606.20622", "identifiers": {"arxiv": "2606.20622"}, "kind": "paper", "last_verified_at": "2026-10-18T10:00:51.952206+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2606.20622"}], "name": "Darwin Mobile Agent: A Roadmap for Self-Evolution", "notes": "The implemented stage uses selected tasks, an external judge and heuristic history management. Autonomous curricula, verification and memory are roadmap directions, not completed capabilities established by this record. No runtime or results were reproduced. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (2 Agent-Environment Interface and Policy Optimisation; 3 Scalable Asynchronous Mobile Environment; 3.2 Persistent State Management; 3.3 Task Lifecycle; 4.2 Rollout and Optimisation; 4.3 Anatomy of the Self-Evolving Agent); not an entire-paper reading or reproduction claim.", "published_at": "2026-05-26", "relations": [], "review_status": "curated", "scope": "core", "summary": "Describes asynchronous reinforcement-learning infrastructure using parallel cloud-hosted Android instances, explicit task lifecycles, and persistent-state management for mobile GUI interaction.", "topics": ["reinforcement-learning", "mobile-navigation", "evaluation"], "updated_at": "2026-05-26", "url": "https://arxiv.org/abs/2606.20622"}
{"aliases": [], "authors": ["Wanxia Cao", "Chengzhen Duan", "Pei Fu", "Pengzhi Gao", "Niu Lian", "Fazhan Liu", "Hui Liu", "Heng Qu", "Qinzhuo Wu", "Zhehao Yu", "Tongbo Chen", "Shiqi Cui", "Anan Du", "Shukai Jia", "Yuanfa Li", "Wei Liu", "Yike Liu", "Wenchao Lu", "Zhenbo Luo", "Haoyuan Sun", "Jiatong Sun", "Cheng Tan", "Yajie Wang", "Changqiao Wu", "Tao Xiong", "Jiahui Yang", "Yuxuan Yuan", "Ruoceng Zhang", "Shaojie Zhang", "Jian Zhu", "Jian Luan", "Cong Zou"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "974d471d25373502914bf0d146d5d4a54a5751281c04921a9d331d83bce64b33", "submitted_at": "2026-06-30T09:36:35Z", "updated_at": "2026-07-01T03:59:21Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.31410v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:05Z", "role": "primary", "sha256": "2e5722527f8da4b2cf06372d1e2daccd33ef7fdc7151704b411a0bddd734beae", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2606.10423%2C2606.10522%2C2606.10742%2C2606.11078%2C2606.11520%2C2606.12485%2C2606.12666%2C2606.13239%2C2606.13385%2C2606.14106%2C2606.14832%2C2606.15017%2C2606.15034%2C2606.16659%2C2606.16748%2C2606.16802%2C2606.17321%2C2606.17645%2C2606.17929%2C2606.18448%2C2606.18671%2C2606.18890%2C2606.19388%2C2606.19926%2C2606.19930%2C2606.20363%2C2606.20636%2C2606.20717%2C2606.20724%2C2606.20785%2C2606.21654%2C2606.22864%2C2606.22948%2C2606.23449%2C2606.24515%2C2606.24525%2C2606.25705%2C2606.25760%2C2606.27330%2C2606.27595%2C2606.29445%2C2606.29537%2C2606.29705%2C2606.30697%2C2606.31154%2C2606.31270%2C2606.31410%2C2606.31612%2C2607.00502%2C2607.04425&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:33:05Z", "role": "primary", "sha256": "2e5722527f8da4b2cf06372d1e2daccd33ef7fdc7151704b411a0bddd734beae", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2606.10423%2C2606.10522%2C2606.10742%2C2606.11078%2C2606.11520%2C2606.12485%2C2606.12666%2C2606.13239%2C2606.13385%2C2606.14106%2C2606.14832%2C2606.15017%2C2606.15034%2C2606.16659%2C2606.16748%2C2606.16802%2C2606.17321%2C2606.17645%2C2606.17929%2C2606.18448%2C2606.18671%2C2606.18890%2C2606.19388%2C2606.19926%2C2606.19930%2C2606.20363%2C2606.20636%2C2606.20717%2C2606.20724%2C2606.20785%2C2606.21654%2C2606.22864%2C2606.22948%2C2606.23449%2C2606.24515%2C2606.24525%2C2606.25705%2C2606.25760%2C2606.27330%2C2606.27595%2C2606.29445%2C2606.29537%2C2606.29705%2C2606.30697%2C2606.31154%2C2606.31270%2C2606.31410%2C2606.31612%2C2607.00502%2C2607.04425&max_results=50"}], "id": "arxiv:2606.31410", "identifiers": {"arxiv": "2606.31410"}, "kind": "paper", "last_verified_at": "2026-10-16T06:33:05Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2606.31410"}], "name": "Xiaomi-GUI-0 Technical Report", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-06-30", "relations": [], "review_status": "curated", "scope": "core", "summary": "Describes a mobile GUI agent trained through real-device interaction, corrected failure trajectories, supervised learning, and reinforcement learning.", "topics": ["mobile-navigation", "reinforcement-learning", "robustness"], "updated_at": "2026-07-01", "url": "https://arxiv.org/abs/2606.31410"}
{"aliases": [], "authors": ["Zidong Zhang", "Zhentao Xie", "Wenrui Diao", "Jianliang Wu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cd4d31e477d5915626d471682e52e5cd6083d9b0c67196f6de5de2a29c6a3058", "submitted_at": "2026-07-01T02:17:19Z", "updated_at": "2026-07-14T03:01:43Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.00333v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}], "id": "arxiv:2607.00333", "identifiers": {"arxiv": "2607.00333"}, "kind": "paper", "last_verified_at": "2026-10-18T10:54:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2607.00333"}], "name": "(A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-07-01", "relations": [], "review_status": "curated", "scope": "core", "summary": "Analyzes cross-app privilege escalation and visual attack surfaces introduced by third-party VLM-powered mobile agents.", "topics": ["safety-security", "mobile-navigation"], "updated_at": "2026-07-14", "url": "https://arxiv.org/abs/2607.00333"}
{"aliases": [], "authors": ["Yunxin Li", "Jinchao Li", "Shibo Su", "Zhenran Xu", "Chenrui Zhao", "Tongshu Bian", "Xiaoman Liang", "Meishan Zhang", "Baotian Hu", "Min Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "281de2bb6e45a58efd047735accc2049deab0f8815931c86abbd38b86b6d23bf", "submitted_at": "2026-07-14T11:04:01Z", "updated_at": "2026-07-15T04:41:47Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.12625v2"}}, "environments": ["desktop", "android", "ios", "harmonyos", "windows"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:09Z", "role": "primary", "sha256": "65cc3856c70a0fb267f9996872e077de10e9f54821ab1ffb1d82f0a92fa11dbf", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2607.05277%2C2607.06118%2C2607.06306%2C2607.07820%2C2607.11185%2C2607.11388%2C2607.12625%2C2607.12640%2C2607.13027%2C2607.14277%2C2607.14443%2C2607.14548%2C2607.15193%2C2607.15550%2C2607.17050%2C2607.18046%2C2607.19865%2C2607.21557%2C2607.22798%2C2607.23263%2C2607.24112%2C2607.24167%2C2607.25904%2C2607.26041%2C2607.27155%2C2607.28074%2C2607.28227%2C2607.28609%2C2607.29320%2C2608.01964%2C2608.02352%2C2608.02643%2C2608.03270%2C2608.03327%2C2608.04530%2C2608.04741%2C2608.05587%2C2608.05784%2C2608.05891%2C2608.06065%2C2608.06171%2C2608.06477%2C2608.09278%2C2608.09654%2C2608.10366%2C2608.10692%2C2608.11588%2C2608.12429%2C2608.15930%2C2608.17310&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:33:09Z", "role": "primary", "sha256": "65cc3856c70a0fb267f9996872e077de10e9f54821ab1ffb1d82f0a92fa11dbf", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2607.05277%2C2607.06118%2C2607.06306%2C2607.07820%2C2607.11185%2C2607.11388%2C2607.12625%2C2607.12640%2C2607.13027%2C2607.14277%2C2607.14443%2C2607.14548%2C2607.15193%2C2607.15550%2C2607.17050%2C2607.18046%2C2607.19865%2C2607.21557%2C2607.22798%2C2607.23263%2C2607.24112%2C2607.24167%2C2607.25904%2C2607.26041%2C2607.27155%2C2607.28074%2C2607.28227%2C2607.28609%2C2607.29320%2C2608.01964%2C2608.02352%2C2608.02643%2C2608.03270%2C2608.03327%2C2608.04530%2C2608.04741%2C2608.05587%2C2608.05784%2C2608.05891%2C2608.06065%2C2608.06171%2C2608.06477%2C2608.09278%2C2608.09654%2C2608.10366%2C2608.10692%2C2608.11588%2C2608.12429%2C2608.15930%2C2608.17310&max_results=50"}], "id": "arxiv:2607.12625", "identifiers": {"arxiv": "2607.12625"}, "kind": "paper", "last_verified_at": "2026-10-16T06:33:09Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2607.12625"}], "name": "KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experiments, reported performance and artifact availability have not been independently reproduced.", "published_at": "2026-07-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "KnowAct-GUIClaw combines a host planner with pluggable GUI subagents, attributable experience memory and an evolving skill library. It uses user profiles and feedback for task decomposition and evaluates transfer across Android, iOS, HarmonyOS and Windows.", "topics": ["memory", "planning", "interaction-history", "mobile-navigation"], "updated_at": "2026-07-15", "url": "https://arxiv.org/abs/2607.12625"}
{"aliases": [], "authors": ["Hy Vision Team", "Huawen Shen", "Zhengyang Tang", "Shangpin Peng", "Liang Wu", "Anran Zhang", "Weinong Wang", "Yiduo Guo", "Chenxin Li", "Zhengyao Fang", "Yang Ding", "Junyi Li", "Fei Tang", "Zheng Ruan", "Yi Zhang", "Xingran Zhou", "Dingchen Yang", "Sunqi Fan", "Zhiyi Wan", "Han Hu", "Xin Lai", "Pengyuan Lyu", "Chengquan Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "151d4882fecc835dfffb9651bd860ebe8c85919a63ff5730e191f9146fbba272", "submitted_at": "2026-07-16T04:12:42Z", "updated_at": "2026-07-16T04:12:42Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.14548v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2607.14548", "identifiers": {"arxiv": "2607.14548"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2607.14548"}], "name": "HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-07-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines GUI perception data, instructional videos, real and simulated devices, and planning with reflection to develop a mobile agent.", "topics": ["mobile-navigation", "data-generation", "planning"], "updated_at": "2026-07-16", "url": "https://arxiv.org/abs/2607.14548"}
{"aliases": [], "authors": ["Zhuohang Fan", "Beichen Zhang", "Yuanfa Li", "Changqiao Wu", "Wei Liu", "Jian Luan", "Weigang Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b85b453a688543477d31a940f9d1da2857b2cb7a8cb9eea91a39a3a2b8a1e1c7", "submitted_at": "2026-07-20T15:16:59Z", "updated_at": "2026-08-18T02:32:56Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.18046v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2607.18046", "identifiers": {"arxiv": "2607.18046"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2607.18046"}], "name": "SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-07-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces SEE, which first explores mobile interfaces to build a screen-and-element transition graph, then composes task trajectories through graph planning and controlled sampling. It studies coverage, loop avoidance, and transfer after training agents on the generated sequences.", "topics": ["data-generation", "long-horizon", "mobile-navigation"], "updated_at": "2026-08-18", "url": "https://arxiv.org/abs/2607.18046"}
{"aliases": [], "authors": ["Weikai Xu", "Yunren Feng", "Haoxiang Lei", "Kun Huang", "Yuxuan Liu", "Kang Zhao", "Xiaolin Hu", "Shuo Shang", "Bo An"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ce37dd8217afbaa07ddea25c0daf78cdbfb449851ca6ab17b7f3ecacd451eb2f", "submitted_at": "2026-08-06T11:15:41Z", "updated_at": "2026-08-06T11:15:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.05891v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2608.05891", "identifiers": {"arxiv": "2608.05891"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2608.05891"}], "name": "AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-08-06", "relations": [], "review_status": "curated", "scope": "core", "summary": "AppDeltaWorld predicts executable code updates for the next mobile UI state, using transition-constrained retrieval and rendered visual assets. It evaluates reconstruction fidelity separately from policy training and adaptation using generated environments.", "topics": ["world-models", "data-generation", "imitation-learning", "reinforcement-learning", "mobile-navigation"], "updated_at": "2026-08-06", "url": "https://arxiv.org/abs/2608.05891"}
{"aliases": [], "authors": ["Weiwei Li", "Junzhuo Liu", "Tong Chu", "Hengfu Yu", "Wen Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bb90627131765746e3a138ab0862dd68ea963106db4055760d78041c856acc8b", "submitted_at": "2026-08-06T14:10:23Z", "updated_at": "2026-08-06T14:10:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.06065v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2608.06065", "identifiers": {"arxiv": "2608.06065"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2608.06065"}], "name": "The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-08-06", "relations": [], "review_status": "curated", "scope": "core", "summary": "Gated Hindsight Distillation gives a teacher access to the next screenshot during training while the student sees only the available trajectory prefix. Distillation is applied when hindsight repairs a student failure, and the resulting policies are evaluated on Android tasks.", "topics": ["imitation-learning", "interaction-history", "mobile-navigation"], "updated_at": "2026-08-06", "url": "https://arxiv.org/abs/2608.06065"}
{"aliases": [], "authors": ["Xiaoou Liu", "Longchao Da", "Hanyang Chen", "Yuan Ling", "Hua Wei"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4d99685a75d2023db5c9ad943e103ec779eebd037fe7a113848d8a31e08fd68b", "submitted_at": "2026-08-07T21:47:43Z", "updated_at": "2026-08-07T21:47:43Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.07775v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:00:40.283922+00:00", "role": "primary", "sha256": "ddd5bd966c7430bd9d4fd0269e7d3d46d8839fa5bfa57d601b97b4dc735cfc9a", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:00:40.283922+00:00", "role": "primary", "sha256": "ddd5bd966c7430bd9d4fd0269e7d3d46d8839fa5bfa57d601b97b4dc735cfc9a", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:10:44.898646+00:00", "role": "primary", "sha256": "d4afe27efcce2a3b9401f9677304db3cdedfa66f537293bb742bd1abfb16ee59", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/pdf/2608.07775v1"}], "id": "arxiv:2608.07775", "identifiers": {"arxiv": "2608.07775"}, "kind": "paper", "last_verified_at": "2026-10-18T10:00:40.283922+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2608.07775"}], "name": "AndroidReality: How Far Are Mobile Agents from the Real World?", "notes": "The reviewed protocol normally activates one perturbation type at a time while preserving task semantics and reward. Results do not establish robustness to arbitrary combined deployment disturbances; experiments were not independently reproduced. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (3.1 Perturbation formulation; 3.2 Injection; 3.3 Evaluation protocol; 4.3 Error analysis); not an entire-paper reading or reproduction claim.", "published_at": "2026-08-07", "relations": [], "review_status": "curated", "scope": "core", "summary": "Extends AndroidWorld with controlled state, transition, and action perturbations to test mobile-agent robustness, and studies a training-free introspective recovery mechanism.", "topics": ["evaluation", "robustness", "self-reflection", "mobile-navigation"], "updated_at": "2026-08-07", "url": "https://arxiv.org/abs/2608.07775"}
{"aliases": [], "authors": ["Rahul Deivasigamani", "Sayeda Faatin Alvi", "Derqui Andrea", "Kaushal Punjabi", "Stjepan Picek"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "64e4845ce85dd67b7790cf5de357f12deb72b71eb72031298e1064809099f063", "submitted_at": "2026-08-09T22:13:55Z", "updated_at": "2026-08-09T22:13:55Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.08939v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}], "id": "arxiv:2608.08939", "identifiers": {"arxiv": "2608.08939"}, "kind": "paper", "last_verified_at": "2026-10-18T10:54:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2608.08939"}], "name": "Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-08-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Demonstrates that unsanitized Android accessibility tree metadata exposes mobile GUI agents to stealthy indirect prompt injection attacks.", "topics": ["safety-security", "mobile-navigation", "screen-understanding"], "updated_at": "2026-08-09", "url": "https://arxiv.org/abs/2608.08939"}
{"aliases": [], "authors": ["Xiaokai Yan", "Jingtao Ding", "Yong Li", "Zhiwen Yu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e2660e01921a78bed7280b34f35a1b587e62339c2e280d6294bbb6d6e666786e", "submitted_at": "2026-08-14T09:36:59Z", "updated_at": "2026-08-14T09:36:59Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.14132v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:00:40.283922+00:00", "role": "primary", "sha256": "ddd5bd966c7430bd9d4fd0269e7d3d46d8839fa5bfa57d601b97b4dc735cfc9a", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:00:40.283922+00:00", "role": "primary", "sha256": "ddd5bd966c7430bd9d4fd0269e7d3d46d8839fa5bfa57d601b97b4dc735cfc9a", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:05:22.211464+00:00", "role": "primary", "sha256": "8d6aa8484ff4a7cbaac589c2c220407ebf6ecd1e216015a248125abdb0f2ed2d", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/html/2608.14132v1"}], "id": "arxiv:2608.14132", "identifiers": {"arxiv": "2608.14132"}, "kind": "paper", "last_verified_at": "2026-10-18T10:00:40.283922+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2608.14132"}], "name": "Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions", "notes": "The benchmark combines real and generated trajectory material. Opportune intervention timing and real-user acceptance are stated limitations. Section 4.2.2 specifies Android emulator instances for generated action trajectories. No results were independently reproduced. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (3 Task definition; 4.1 Raw data collection; 4.2 Trajectory construction; 7 Limitations and future directions); not an entire-paper reading or reproduction claim.", "published_at": "2026-08-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces intention understanding, prediction, and confirmed execution tasks over mobile GUI trajectories, with a proactive agent combining personalized intention models and experience-guided actions.", "topics": ["human-in-the-loop", "planning", "mobile-navigation", "evaluation"], "updated_at": "2026-08-14", "url": "https://arxiv.org/abs/2608.14132"}
{"aliases": [], "authors": ["Mingshuo Wang", "Hanqing Guo", "Huining Li", "Yuliang Fu", "Jing Xu", "Chenhan Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7b17f858c9d6992f6a8d8f21cc79d468b0f1c81fc44084045791d9c3acacd6d0", "submitted_at": "2026-08-30T20:55:21Z", "updated_at": "2026-08-30T20:55:21Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.30038v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:13Z", "role": "primary", "sha256": "ca895b2f0dcd74816fb5e775a7161a0932ff7120a72477791f5e4c0bb1ead88e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2608.17319%2C2608.18307%2C2608.20319%2C2608.20707%2C2608.20797%2C2608.21794%2C2608.21830%2C2608.21832%2C2608.21898%2C2608.22077%2C2608.22533%2C2608.22577%2C2608.22847%2C2608.24015%2C2608.24017%2C2608.24099%2C2608.24174%2C2608.24680%2C2608.24848%2C2608.25777%2C2608.26200%2C2608.26204%2C2608.27477%2C2608.27508%2C2608.27808%2C2608.27866%2C2608.29305%2C2608.30038%2C2608.30207%2C2609.00028%2C2609.00048%2C2609.00524%2C2609.02057%2C2609.02149%2C2609.02154%2C2609.02309%2C2609.02885%2C2609.03438%2C2609.04850%2C2609.04869%2C2609.05374%2C2609.05511%2C2609.05513%2C2609.05535%2C2609.06530%2C2609.06792%2C2609.07603%2C2609.07712%2C2609.09212%2C2609.10031&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:33:13Z", "role": "primary", "sha256": "ca895b2f0dcd74816fb5e775a7161a0932ff7120a72477791f5e4c0bb1ead88e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2608.17319%2C2608.18307%2C2608.20319%2C2608.20707%2C2608.20797%2C2608.21794%2C2608.21830%2C2608.21832%2C2608.21898%2C2608.22077%2C2608.22533%2C2608.22577%2C2608.22847%2C2608.24015%2C2608.24017%2C2608.24099%2C2608.24174%2C2608.24680%2C2608.24848%2C2608.25777%2C2608.26200%2C2608.26204%2C2608.27477%2C2608.27508%2C2608.27808%2C2608.27866%2C2608.29305%2C2608.30038%2C2608.30207%2C2609.00028%2C2609.00048%2C2609.00524%2C2609.02057%2C2609.02149%2C2609.02154%2C2609.02309%2C2609.02885%2C2609.03438%2C2609.04850%2C2609.04869%2C2609.05374%2C2609.05511%2C2609.05513%2C2609.05535%2C2609.06530%2C2609.06792%2C2609.07603%2C2609.07712%2C2609.09212%2C2609.10031&max_results=50"}], "id": "arxiv:2608.30038", "identifiers": {"arxiv": "2608.30038"}, "kind": "paper", "last_verified_at": "2026-10-16T06:33:13Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2608.30038"}], "name": "ActReal: System-Level Mobile Agents Challenge Mobile Automation Detection", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-08-30", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces ActReal, which translates semantic mobile-agent actions into coordinated touch and sensor signals to study automation-detection weaknesses. It evaluates detectors that observe touch events alone or together with inertial measurements under a privileged executor threat model.", "topics": ["safety-security", "mobile-navigation", "evaluation"], "updated_at": "2026-08-30", "url": "https://arxiv.org/abs/2608.30038"}
{"aliases": [], "authors": ["Weide Zhan", "Qumu Shaqu", "Yuanqing Liu", "Peng Zhang", "Jiahao Liu", "Kam Him Lam", "Ning Gu", "Zhan Hu", "Tun Lu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "61587798aefd8e9592ddaef756a13e02f0e4a987e4068ef582d0aaf66e8eb680", "submitted_at": "2026-09-04T08:09:47Z", "updated_at": "2026-09-04T08:09:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.04850v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:13Z", "role": "primary", "sha256": "ca895b2f0dcd74816fb5e775a7161a0932ff7120a72477791f5e4c0bb1ead88e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2608.17319%2C2608.18307%2C2608.20319%2C2608.20707%2C2608.20797%2C2608.21794%2C2608.21830%2C2608.21832%2C2608.21898%2C2608.22077%2C2608.22533%2C2608.22577%2C2608.22847%2C2608.24015%2C2608.24017%2C2608.24099%2C2608.24174%2C2608.24680%2C2608.24848%2C2608.25777%2C2608.26200%2C2608.26204%2C2608.27477%2C2608.27508%2C2608.27808%2C2608.27866%2C2608.29305%2C2608.30038%2C2608.30207%2C2609.00028%2C2609.00048%2C2609.00524%2C2609.02057%2C2609.02149%2C2609.02154%2C2609.02309%2C2609.02885%2C2609.03438%2C2609.04850%2C2609.04869%2C2609.05374%2C2609.05511%2C2609.05513%2C2609.05535%2C2609.06530%2C2609.06792%2C2609.07603%2C2609.07712%2C2609.09212%2C2609.10031&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:33:13Z", "role": "primary", "sha256": "ca895b2f0dcd74816fb5e775a7161a0932ff7120a72477791f5e4c0bb1ead88e", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2608.17319%2C2608.18307%2C2608.20319%2C2608.20707%2C2608.20797%2C2608.21794%2C2608.21830%2C2608.21832%2C2608.21898%2C2608.22077%2C2608.22533%2C2608.22577%2C2608.22847%2C2608.24015%2C2608.24017%2C2608.24099%2C2608.24174%2C2608.24680%2C2608.24848%2C2608.25777%2C2608.26200%2C2608.26204%2C2608.27477%2C2608.27508%2C2608.27808%2C2608.27866%2C2608.29305%2C2608.30038%2C2608.30207%2C2609.00028%2C2609.00048%2C2609.00524%2C2609.02057%2C2609.02149%2C2609.02154%2C2609.02309%2C2609.02885%2C2609.03438%2C2609.04850%2C2609.04869%2C2609.05374%2C2609.05511%2C2609.05513%2C2609.05535%2C2609.06530%2C2609.06792%2C2609.07603%2C2609.07712%2C2609.09212%2C2609.10031&max_results=50"}], "id": "arxiv:2609.04850", "identifiers": {"arxiv": "2609.04850"}, "kind": "paper", "last_verified_at": "2026-10-16T06:33:13Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.04850"}], "name": "ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "ElderBench evaluates mobile GUI agents on smartphone requests elicited from older adults, including indirect and underspecified language. Online and offline tests, instruction normalization and linguistic analyses examine how these request patterns contribute to failures.", "topics": ["evaluation", "human-in-the-loop", "mobile-navigation", "robustness"], "updated_at": "2026-09-04", "url": "https://arxiv.org/abs/2609.04850"}
{"aliases": [], "authors": ["Juyong Lee", "Woogyeol Jin", "Kimin Lee"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "14790f9565861cdba0b24661f6bfe87d7572cbad9d76d9a0b2d7216e9bac7ea7", "submitted_at": "2026-09-06T19:22:53Z", "updated_at": "2026-09-06T19:22:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.06792v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.06792", "identifiers": {"arxiv": "2609.06792"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.06792"}], "name": "Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actions", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-09-06", "relations": [], "review_status": "curated", "scope": "core", "summary": "DroidTool generates application-state tools through proposal, implementation, testing and repair. Relational tests connect the tools’ preconditions and effects, and the resulting tools are evaluated as additions to Android GUI agents.", "topics": ["tool-integration", "automation", "mobile-navigation", "efficiency"], "updated_at": "2026-09-06", "url": "https://arxiv.org/abs/2609.06792"}
{"aliases": [], "authors": ["Jintian Feng", "Long Chen", "Xiao Yu", "Jiayi Dai", "Chenglong Liu", "Haoru Wang", "Zizhen Xue", "Yuxuan Shi", "Ziyang Wang", "Yichen Gong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b4090a2c7e7730ea415564b6b418d85aad77a74a222cef35435b0aa93beafd7f", "submitted_at": "2026-09-07T16:25:13Z", "updated_at": "2026-09-07T16:25:13Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.07712v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.07712", "identifiers": {"arxiv": "2609.07712"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.07712"}], "name": "APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-07", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces controlled simulated mobile apps with deterministic backend data and outcome checks for reproducible evaluation of realistic interactions.", "topics": ["evaluation", "sandbox", "mobile-navigation"], "updated_at": "2026-09-07", "url": "https://arxiv.org/abs/2609.07712"}
{"aliases": [], "authors": ["Xiaolei Li", "Jialun Cao", "Zhijian Hou", "Yuzhi Zhao", "Yepang Liu", "Shing-Chi Cheung"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3307d90ef09c16afaee160eacc9d2994d142be9b9a26ce9c4a57f61345e2e8ec", "submitted_at": "2026-09-09T11:04:53Z", "updated_at": "2026-09-09T11:04:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.10031v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:13Z", "role": "primary", "sha256": "ca895b2f0dcd74816fb5e775a7161a0932ff7120a72477791f5e4c0bb1ead88e", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2608.17319%2C2608.18307%2C2608.20319%2C2608.20707%2C2608.20797%2C2608.21794%2C2608.21830%2C2608.21832%2C2608.21898%2C2608.22077%2C2608.22533%2C2608.22577%2C2608.22847%2C2608.24015%2C2608.24017%2C2608.24099%2C2608.24174%2C2608.24680%2C2608.24848%2C2608.25777%2C2608.26200%2C2608.26204%2C2608.27477%2C2608.27508%2C2608.27808%2C2608.27866%2C2608.29305%2C2608.30038%2C2608.30207%2C2609.00028%2C2609.00048%2C2609.00524%2C2609.02057%2C2609.02149%2C2609.02154%2C2609.02309%2C2609.02885%2C2609.03438%2C2609.04850%2C2609.04869%2C2609.05374%2C2609.05511%2C2609.05513%2C2609.05535%2C2609.06530%2C2609.06792%2C2609.07603%2C2609.07712%2C2609.09212%2C2609.10031&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:33:13Z", "role": "primary", "sha256": "ca895b2f0dcd74816fb5e775a7161a0932ff7120a72477791f5e4c0bb1ead88e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2608.17319%2C2608.18307%2C2608.20319%2C2608.20707%2C2608.20797%2C2608.21794%2C2608.21830%2C2608.21832%2C2608.21898%2C2608.22077%2C2608.22533%2C2608.22577%2C2608.22847%2C2608.24015%2C2608.24017%2C2608.24099%2C2608.24174%2C2608.24680%2C2608.24848%2C2608.25777%2C2608.26200%2C2608.26204%2C2608.27477%2C2608.27508%2C2608.27808%2C2608.27866%2C2608.29305%2C2608.30038%2C2608.30207%2C2609.00028%2C2609.00048%2C2609.00524%2C2609.02057%2C2609.02149%2C2609.02154%2C2609.02309%2C2609.02885%2C2609.03438%2C2609.04850%2C2609.04869%2C2609.05374%2C2609.05511%2C2609.05513%2C2609.05535%2C2609.06530%2C2609.06792%2C2609.07603%2C2609.07712%2C2609.09212%2C2609.10031&max_results=50"}], "id": "arxiv:2609.10031", "identifiers": {"arxiv": "2609.10031"}, "kind": "paper", "last_verified_at": "2026-10-16T06:33:13Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.10031"}], "name": "GraphDroid: Asynchronous LLM-Based Mobile App GUI Testing via History-Aware Exploration and Hybrid Intent Fulfillment", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experiments, reported performance and artifact availability have not been independently reproduced.", "published_at": "2026-09-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "GraphDroid combines clustered memory of visited GUI states with asynchronous test-intent generation. A hybrid executor reserves LLM calls for complex intents and uses heuristics for simpler ones, evaluated through Android app coverage, bug discovery and crash detection.", "topics": ["evaluation", "mobile-navigation", "memory", "interaction-history", "efficiency"], "updated_at": "2026-09-09", "url": "https://arxiv.org/abs/2609.10031"}
{"aliases": [], "authors": ["Tong Ye", "Kunyang Han", "Guozhi Wang", "Longqiang Luo", "Zhifeng Ding", "Yongxiang Zhang", "Xiaolei Shen", "Yuxuan Zhang", "Zhuping Zhang", "Tao Xu", "Yue Pan", "Yucheng Zhao", "Yupei Hu", "Yuanjiang Ouyang", "Danfeng Shen", "Runqi Lin", "Hongda Cai", "Zhaoxiong Wang", "Mengjia Yan", "Yingjie Zhong", "Chen Zhou", "Zeyu Zhang", "Xuwen Zhu", "Penggang Shi", "Mingcheng Luo", "Ziyang Wu", "Min Jin", "Mingfu Shen", "Zairong Xu", "Fan Zhang", "Hao Wang", "Liang Liu", "Zhulin Xie", "Lijun Yao", "Xiao Liang", "Liangmin Wen", "Liqiang Feng", "Feilong Wu", "Min Hu", "Min Chen", "Guanjing Xiong", "Xiaohu Ruan", "Xiaoxin Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cc15573bca49d453001ec22061f190e429704a5318751b041550e3610c469f4e", "submitted_at": "2026-09-11T03:36:35Z", "updated_at": "2026-09-15T06:36:04Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2609.12394v3"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.12394", "identifiers": {"arxiv": "2609.12394"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.12394"}], "name": "BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-11", "relations": [], "review_status": "curated", "scope": "core", "summary": "Describes a mobile-agent training pipeline centered on real-device rollouts, recovery of useful supervision from failures, and evolving evaluation tasks.", "topics": ["mobile-navigation", "reinforcement-learning", "data-generation"], "updated_at": "2026-09-15", "url": "https://arxiv.org/abs/2609.12394"}
{"aliases": [], "authors": ["Qihang Cen", "Tianshuo Cong", "Da Song", "Xinlei He", "Jiaxing Song", "Ke Xu", "Qi Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1eda33b358d4c4caf8c1fb0b1bd92698c3b37cee995d820f40ecffe82010edb4", "submitted_at": "2026-09-12T10:55:54Z", "updated_at": "2026-09-12T10:55:54Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.13873v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.13873", "identifiers": {"arxiv": "2609.13873"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.13873"}], "name": "PriMobiBench: Characterizing Visual Privacy Leakage in VLM-Driven Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "PriMobiBench evaluates direct privacy leakage and user profiling from mobile GUI screenshot trajectories, supported by the MobiLeak trace dataset. It also tests masking sensitive, task-irrelevant interface elements before cloud processing and measures the resulting privacy and utility trade-off.", "topics": ["evaluation", "safety-security", "screen-understanding", "mobile-navigation"], "updated_at": "2026-09-12", "url": "https://arxiv.org/abs/2609.13873"}
{"aliases": [], "authors": ["Yan Zhang", "Daiqing Wu", "Huawen Shen", "Liang Li", "Gang Cao", "Zhi Gong", "Wei Dai", "Xiaode Zhang", "Can Ma", "Yu Zhou"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0ae6c83c017a05c2916f31e388f6584cc2cab7b87e1eb0038c33a707bbd66e24", "submitted_at": "2026-09-23T03:38:11Z", "updated_at": "2026-09-23T03:38:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.27307v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.27307", "identifiers": {"arxiv": "2609.27307"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.27307"}], "name": "Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-09-23", "relations": [], "review_status": "curated", "scope": "core", "summary": "GUI-SD-v2 extends on-policy self-distillation from grounding to multi-turn GUI interaction. It first strengthens responses to privileged guidance, then selectively distills step-specific reasoning and memory support for later actions.", "topics": ["imitation-learning", "memory", "interaction-history", "mobile-navigation"], "updated_at": "2026-09-23", "url": "https://arxiv.org/abs/2609.27307"}
{"aliases": [], "authors": ["Tingyu Qu", "Weigao Sun", "Yuecheng Liu", "Yucheng Zhao", "Yi Zhu", "Yifeng Ding", "Qiyi Wang", "Sihan Cao", "Pengkun Jiao", "Hanlei Xie", "Xiongwei Wu", "Qichao Wang", "Haodong Zhang", "Jiajun Liu", "Yuhao Wang", "Yuqing Xie", "Junpeng Zhao", "Long Chen", "Ming Ma", "Sihan Yang", "Ziwang Zhao", "Yanhao Jia", "Liangquan Gong", "Feida Zhu", "Yiran Zhong", "Steven Hoi"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "572ba5397fc1e4bb138febc3e7004e6e4f244e0ba8b628fb91debef4a854561f", "submitted_at": "2026-09-24T14:38:08Z", "updated_at": "2026-09-24T14:38:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.29892v1"}, "license_review": {"document": {"evidence_urls": ["https://arxiv.org/html/2609.29892v1"], "reason": "Record the paper-specific arXiv document declaration; it does not establish code, data or model-weight permissions."}}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:17Z", "role": "primary", "sha256": "5d7c9ff24833b254d33a41a7c4247e830e4d9c371881a1e16151bad5c71cc8b3", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2609.10297%2C2609.10451%2C2609.12394%2C2609.12404%2C2609.13287%2C2609.13491%2C2609.13548%2C2609.13873%2C2609.14239%2C2609.15134%2C2609.15307%2C2609.15364%2C2609.15457%2C2609.16251%2C2609.16635%2C2609.16732%2C2609.16900%2C2609.17653%2C2609.17885%2C2609.18411%2C2609.18690%2C2609.19125%2C2609.19523%2C2609.19843%2C2609.22083%2C2609.22724%2C2609.24277%2C2609.24890%2C2609.25769%2C2609.27273%2C2609.27307%2C2609.27353%2C2609.27461%2C2609.29892%2C2609.30186%2C2609.30604%2C2609.30887%2C2609.31957%2C2609.32036%2C2609.32130%2C2609.32166%2C2609.32351%2C2609.32385%2C2609.32600%2C2609.32679%2C2609.32750%2C2609.32915%2C2609.33304%2C2609.33646%2C2609.34113&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T15:43:20.402537Z", "role": "primary", "sha256": "d4385231cea2965a48895eeebd2dd6000265dd7b43731a0ad88b0373a21d0308", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "licenses.document"], "url": "https://arxiv.org/html/2609.29892v1"}], "id": "arxiv:2609.29892", "identifiers": {"arxiv": "2609.29892"}, "kind": "paper", "last_verified_at": "2026-10-20T15:43:20.402537Z", "licenses": {"code": null, "data": null, "document": {"basis": "The exact-v1 arXiv HTML infobox (#license-tr) declares License: CC BY 4.0 for this paper. This declaration is document-only.", "declared": "CC-BY-4.0", "retrieved_at": "2026-10-20T15:43:20.402537Z", "url": "https://arxiv.org/html/2609.29892v1"}, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.29892"}], "name": "Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents", "notes": "Primarily typed tool actions and structured feedback, not pixel-coordinate GUI control; backends combine programmatic sandboxes, LLM simulation and selected real-device sessions. No specific OS is established. Model/harness updates are reviewed offline, not autonomous serving-time changes. Co-evolution scores use an evolve/development set; output-cost estimates exclude input, tools, devices and harness processing. Memory comparisons differ in history access and processing cost; user authorization relies on trusted upstream services. No independent reproduction.", "published_at": "2026-09-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "Trains a mobile planner with supervised trajectories and competence-adaptive RL, then couples typed tool execution with memory, skills and offline model-harness refinement.", "topics": ["planning", "data-generation", "reinforcement-learning", "memory", "mobile-navigation", "efficiency"], "updated_at": "2026-09-24", "url": "https://arxiv.org/abs/2609.29892"}
{"aliases": [], "authors": ["Linghua Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b387c1cfe77f6e06477415944b3923189a1f0ca30be0680f01815cb65b0067bc", "submitted_at": "2026-09-24T17:30:32Z", "updated_at": "2026-09-24T17:30:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.30186v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.30186", "identifiers": {"arxiv": "2609.30186"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.30186"}], "name": "Jev-Mobile: Jev as an Executor for Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "Separates occasional visual-language planning from frequent lightweight action selection over an accessibility-tree-based action space.", "topics": ["mobile-navigation", "efficiency", "planning"], "updated_at": "2026-09-24", "url": "https://arxiv.org/abs/2609.30186"}
{"aliases": [], "authors": ["Yuchen Sun", "Chenglin Cai", "Gongjie Zhang", "Tianyu Xia", "Quyu Kong", "Panrong Tong", "Zhengwen Zeng", "Long Chen", "Steven Hoi", "Chongyang Zhang", "Yue Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "838635f067b706c7b36a948c8100b30bf4cacd218470aaed6970e5186fa44fb9", "submitted_at": "2026-09-25T06:50:04Z", "updated_at": "2026-09-25T06:50:04Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.30887v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T08:27:30.162100+00:00", "role": "primary", "sha256": "096098b62f82867ee39dfd7cf44095edc5c6a9307351265592e485d82eadf111", "supports": ["name", "kind", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agent%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22browser+agents%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22mobile+agents%22+OR+ti%3A%22desktop+agent%22%29+AND+submittedDate%3A%5B202609200000+TO+202610192359%5D&start=0&max_results=200&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T10:53:44.035673+00:00", "role": "primary", "sha256": "2b6b8147cf7b0e1fcded85f397c272bcf535ed179789e76c3ff4f15aa3fe53a7", "supports": ["summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/html/2609.30887v1"}], "id": "arxiv:2609.30887", "identifiers": {"arxiv": "2609.30887"}, "kind": "paper", "last_verified_at": "2026-10-20T08:27:30.162100+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.30887"}], "name": "From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks", "notes": "Reviewed the complete retained Atom abstract and selected exact-v1 full text. The Atom has incomplete clauses; its text/hash remain unchanged and this annotation uses the explicit methods. Evaluation is Android-only, with a selected real-app subset. Landing-Activity verification is not task completion. Model/catalog release is prospective in the paper. No independent reproduction.", "published_at": "2026-09-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "GUI-Hopper combines verified Android deeplinks with GUI actions, using landing-screen descriptions, hybrid trajectory training and reinforcement learning to select navigation shortcuts and recover through GUI control.", "topics": ["mobile-navigation", "tool-integration", "data-generation", "imitation-learning", "reinforcement-learning", "efficiency"], "updated_at": "2026-09-25", "url": "https://arxiv.org/abs/2609.30887"}
{"aliases": [], "authors": ["Beining Wu", "Jun Huang", "Yanxiao Zhao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "719385c97b9d174bbebc34ac4a196971af61521489f7bf032a7d807ae3c8d4c1", "submitted_at": "2026-09-26T01:13:44Z", "updated_at": "2026-09-26T01:13:44Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.32130v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.32130", "identifiers": {"arxiv": "2609.32130"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.32130"}], "name": "REBASE: Device-Cloud Experience Coherence for GUI Agents Across App Updates", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-26", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces REBASE, a device–cloud protocol for repairing cached GUI experience after app updates. It combines cloud replay, device-side step verification, and progressively richer failure reports to produce repairs tied to application versions.", "topics": ["memory", "robustness", "efficiency", "mobile-navigation"], "updated_at": "2026-09-26", "url": "https://arxiv.org/abs/2609.32130"}
{"aliases": [], "authors": ["Taehwan Park", "Changmin Lee", "Hayeon Lee", "Taesik Gong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f343a941e12c0fb8c4e12dc156e7c8b37f753d74836d8e42542d504bee883e51", "submitted_at": "2026-09-26T02:41:56Z", "updated_at": "2026-09-26T02:41:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.32166v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.32166", "identifiers": {"arxiv": "2609.32166"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.32166"}], "name": "PastForward: Faster On-Device GUI Agents via Computational Experience Reuse", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-26", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces PastForward, which reuses earlier output sequences as verified decoding proposals and starts future action computation from predicted GUI transitions. Screen checks determine whether speculative computation and cached model states can be retained.", "topics": ["memory", "efficiency", "mobile-navigation"], "updated_at": "2026-09-26", "url": "https://arxiv.org/abs/2609.32166"}
{"aliases": [], "authors": ["Tien Tran", "Namho Koh", "Daiki E. Matsunaga", "Ayush Jain", "Kee Eung Kim"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0ee7ddc170afcd2fa09d1c8d12a07bbd6aac692bc12ffc27bd39f1de0c912dfa", "submitted_at": "2026-09-28T02:21:13Z", "updated_at": "2026-09-28T02:21:13Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.34139v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.34139", "identifiers": {"arxiv": "2609.34139"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.34139"}], "name": "Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize?", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces AnyAppBench, a live Android benchmark that holds user goals fixed while changing the application used to achieve them. It combines category-controlled task pairs with failure annotations to distinguish task understanding from application-specific execution skill.", "topics": ["evaluation", "robustness", "mobile-navigation"], "updated_at": "2026-09-28", "url": "https://arxiv.org/abs/2609.34139"}
{"aliases": [], "authors": ["Yangqin Jiang", "Lingrui Xu", "Chao Huang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4ffb5951994cbccef0700ce850a1fae096a59b87334070750caf0b7b42d61c4b", "submitted_at": "2026-09-28T17:26:56Z", "updated_at": "2026-10-05T01:08:41Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2609.35671v2"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:20Z", "role": "primary", "sha256": "c420ee40cc87a574ae2554556843f27f2eda43af553f88e95affd6319b1dae33", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2609.34321%2C2609.34769%2C2609.34974%2C2609.35026%2C2609.35671%2C2609.35814%2C2609.35904%2C2609.36201%2C2609.36488%2C2609.36923%2C2609.36927%2C2609.36939%2C2609.37053%2C2609.37176%2C2609.37686%2C2609.38008%2C2609.38397%2C2609.38778%2C2609.38867%2C2609.39306%2C2609.39547%2C2609.39903%2C2609.40253%2C2609.40284%2C2610.00948%2C2610.01215%2C2610.01491%2C2610.01787%2C2610.02320%2C2610.02932%2C2610.03036%2C2610.03089%2C2610.03574%2C2610.03818%2C2610.04116%2C2610.04800%2C2610.04906%2C2610.05185%2C2610.05437%2C2610.05861%2C2610.06829%2C2610.07118%2C2610.07127%2C2610.07444%2C2610.07972%2C2610.08699%2C2610.08773%2C2610.09240%2C2610.09469%2C2610.11050&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:33:20Z", "role": "primary", "sha256": "c420ee40cc87a574ae2554556843f27f2eda43af553f88e95affd6319b1dae33", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2609.34321%2C2609.34769%2C2609.34974%2C2609.35026%2C2609.35671%2C2609.35814%2C2609.35904%2C2609.36201%2C2609.36488%2C2609.36923%2C2609.36927%2C2609.36939%2C2609.37053%2C2609.37176%2C2609.37686%2C2609.38008%2C2609.38397%2C2609.38778%2C2609.38867%2C2609.39306%2C2609.39547%2C2609.39903%2C2609.40253%2C2609.40284%2C2610.00948%2C2610.01215%2C2610.01491%2C2610.01787%2C2610.02320%2C2610.02932%2C2610.03036%2C2610.03089%2C2610.03574%2C2610.03818%2C2610.04116%2C2610.04800%2C2610.04906%2C2610.05185%2C2610.05437%2C2610.05861%2C2610.06829%2C2610.07118%2C2610.07127%2C2610.07444%2C2610.07972%2C2610.08699%2C2610.08773%2C2610.09240%2C2610.09469%2C2610.11050&max_results=50"}], "id": "arxiv:2609.35671", "identifiers": {"arxiv": "2609.35671"}, "kind": "paper", "last_verified_at": "2026-10-16T06:33:20Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.35671"}], "name": "PhoneCLI: From App Interfaces to Callable Commands for Mobile Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces PhoneCLI, which explores mobile app interfaces and compiles navigation paths into reusable commands without internal app APIs or instrumentation. At execution time it verifies compiled paths and falls back to a visual agent for open-ended interaction or failed navigation.", "topics": ["automation", "efficiency", "mobile-navigation"], "updated_at": "2026-10-05", "url": "https://arxiv.org/abs/2609.35671"}
{"aliases": [], "authors": ["Yongxin Ning", "Runliang Niu", "Qianli Xing", "Zhiyi Duan", "Qingzu He", "Pan Wang", "Qi Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "43845ad64843a0b019c1988d4ba861eccee3c48a7b2c09d0bae7794e5e86347a", "submitted_at": "2026-10-05T06:28:58Z", "updated_at": "2026-10-05T06:28:58Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.05861v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2610.05861", "identifiers": {"arxiv": "2610.05861"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.05861"}], "name": "Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent Training", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-10-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Infinite-Dreamer, which learns action-conditioned screenshot editing from structured descriptions of GUI changes and uses it to synthesize robustness examples and multi-step trajectories. The synthetic data trains a mobile GUI agent evaluated on AndroidWorld, MobileWorld, and AndroidControl-Curated.", "topics": ["world-models", "data-generation", "mobile-navigation"], "updated_at": "2026-10-05", "url": "https://arxiv.org/abs/2610.05861"}
{"aliases": [], "authors": ["Li Hu", "Kanghua Mo", "Yingbin Jin", "Qingqing Ye", "Haibo Hu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5afea9414462386ee921b9ead9381c0204963c710c9f616a96f4bc47079f059e", "submitted_at": "2026-09-29T03:03:00Z", "updated_at": "2026-09-29T03:03:00Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.06898v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:00:31.520084+00:00", "role": "primary", "sha256": "f053c4c65f6443acbda26e25cf36f7b6e8ea45f2916535604229f7c4e62ed679", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:00:31.520084+00:00", "role": "primary", "sha256": "f053c4c65f6443acbda26e25cf36f7b6e8ea45f2916535604229f7c4e62ed679", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:10:35.098754+00:00", "role": "primary", "sha256": "73f83c27e58e46086dbd5f32f108df2c5faa9ab2bd968d48062f39d94b2cc14b", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/pdf/2610.06898v1"}], "id": "arxiv:2610.06898", "identifiers": {"arxiv": "2610.06898"}, "kind": "paper", "last_verified_at": "2026-10-18T10:00:31.520084+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.06898"}], "name": "DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections", "notes": "The commercial-app protocol uses fixed screenshots and context for selection decisions, rather than live end-to-end transactions. Android is supported by the paper's emulator setup. Completion and integrity are distinct measures; no reported scores were reproduced. Basis: complete retained abstract and source-reviewed sections of the exact-version paper (3.1 Benchmark components; 3.2 Instance generation; 3.3 Paired protocol/metrics; 5 Limitations/Ethics; Appendix B (Android emulator setup)); not an entire-paper reading or reproduction claim.", "published_at": "2026-09-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "Evaluates whether deceptive UI content steers mobile agents away from instruction-consistent choices, using paired benign and injected decision states and decision-integrity metrics.", "topics": ["evaluation", "safety-security", "mobile-navigation"], "updated_at": "2026-09-29", "url": "https://arxiv.org/abs/2610.06898"}
{"aliases": [], "authors": ["Yeji Park", "Jaeyun Shim", "Taesik Gong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b792cc0355a0947c61014c471c482aef173f761f7396a939c14816ac644abe66", "submitted_at": "2026-10-06T08:38:30Z", "updated_at": "2026-10-06T08:38:30Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.07972v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2610.07972", "identifiers": {"arxiv": "2610.07972"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.07972"}], "name": "Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-10-06", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces PAIR for controlled evaluation of mobile GUI agents across user-conditioned application states and RePAIR for training from cross-user subgoal outcomes. The study examines failures when personalized interfaces change which items an agent must identify.", "topics": ["evaluation", "robustness", "mobile-navigation", "reinforcement-learning"], "updated_at": "2026-10-06", "url": "https://arxiv.org/abs/2610.07972"}
{"aliases": [], "authors": ["Yudong Bai", "Yihong Chen", "Quanming Yao", "Yaqing Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2627960a5698d4c2f245e91ca5033be8c09e8a1ddea02490fcc1ed9f3d42217d", "submitted_at": "2026-10-08T11:12:57Z", "updated_at": "2026-10-08T11:12:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.11707v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2610.11707", "identifiers": {"arxiv": "2610.11707"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.11707"}], "name": "DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-10-08", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces DeltaReplay, which stores mobile GUI trajectories as transition graphs and decides at each step whether to reuse an action, substitute task-specific parameters, or defer to the base agent. This supports reuse of partially matching experiences without rewriting stored memory.", "topics": ["memory", "mobile-navigation", "planning"], "updated_at": "2026-10-08", "url": "https://arxiv.org/abs/2610.11707"}
{"aliases": [], "authors": ["Yuchen Ling", "Shengcheng Yu", "Zhenyu Chen", "Chunrong Fang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fb5f0220266a43b74e7a5f547abbe78a54a2ef993fee5d27f67827cb9715f5dc", "submitted_at": "2026-10-09T06:45:23Z", "updated_at": "2026-10-09T06:45:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.13092v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-20T15:06:37Z", "role": "primary", "sha256": "a3d753815e82190ee2de6f322cd816c32f2dd391f862845305fc7e57300303a6", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28abs%3A%22desktop+agent%22+OR+abs%3A%22computer+interaction%22+OR+abs%3A%22GUI+automation%22+OR+abs%3A%22web+navigation%22+OR+abs%3A%22browser+automation%22+OR+abs%3A%22visual+grounding%22+OR+abs%3A%22screen+understanding%22+OR+abs%3A%22mobile+agents%22%29+AND+submittedDate%3A%5B202609200000+TO+202610200000%5D&start=0&max_results=200&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T15:08:54Z", "role": "primary", "sha256": "3db7474953cbe5a3052fb22793038f2383bdd0e7c775af06494a5e8501646d18", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/html/2610.13092v1"}], "id": "arxiv:2610.13092", "identifiers": {"arxiv": "2610.13092"}, "kind": "paper", "last_verified_at": "2026-10-20T15:08:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.13092"}], "name": "When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows", "notes": "The mobile evaluation uses text UI observations and one fixed instance for each of 116 AndroidWorld task types; three repeats share seed 0. Five agent families use different budgets, with candidate-interface and tool-call granularity changes in some variants. Reported costs use fixed experimental prices, and outcome-selected trace labels are not population failure rates. Faster selection does not imply faster or more reliable task completion. Selected sections were source-read; no independent reproduction.", "published_at": "2026-10-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Evaluates Jev as a bounded action selector inside three AndroidWorld agents and two text-based ALFWorld agents, separating decision savings from task success, recovery and resources per delivered outcome.", "topics": ["efficiency", "action-prediction", "evaluation", "mobile-navigation", "self-reflection"], "updated_at": "2026-10-09", "url": "https://arxiv.org/abs/2610.13092"}
{"aliases": [], "authors": ["Chenyang Yan", "Yingying Zhang", "Kanzhi Cheng", "Qiushi Sun", "Zhengyuan Pan", "Zheng Ma", "Hang Yan", "Yian Wang", "Nuo Chen", "Jialin Cao", "Xingdong Gong", "Wenpo Song", "Han Chen", "Zichen Ding", "Fangzhi Xu", "Shujian Huang", "Xinyu Dai", "Yichen Liu", "Tiankuo Yao", "Bo Wang", "Ben Kao", "Jianbing Zhang", "Lewei Lu", "Dahua Lin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f7d940d3e341fd8c9f23a4829a5ab1150fc07ee231ccda9b108a3f0d785efb9", "submitted_at": "2026-10-09T17:26:38Z", "updated_at": "2026-10-09T17:26:38Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.14157v1"}}, "environments": ["android", "web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:24Z", "role": "primary", "sha256": "9641755401e0e8ec9613f7c4509029d968ab4f10751ba4d43cab57e7d27c1da1", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2610.11655%2C2610.11707%2C2610.11942%2C2610.12611%2C2610.12823%2C2610.12866%2C2610.12984%2C2610.13268%2C2610.13416%2C2610.13703%2C2610.14157%2C2610.14228%2C2610.15138%2C2610.15765%2C2610.16234%2C2610.16319%2C2610.16720%2C2610.16778%2C2610.17457%2C2610.17710%2C2610.17792%2C2610.17895%2C2610.17928%2C2610.18508%2C2610.18784%2C2610.18868%2C2610.19100%2C2610.19128%2C2610.20584&max_results=29"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:33:24Z", "role": "primary", "sha256": "9641755401e0e8ec9613f7c4509029d968ab4f10751ba4d43cab57e7d27c1da1", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2610.11655%2C2610.11707%2C2610.11942%2C2610.12611%2C2610.12823%2C2610.12866%2C2610.12984%2C2610.13268%2C2610.13416%2C2610.13703%2C2610.14157%2C2610.14228%2C2610.15138%2C2610.15765%2C2610.16234%2C2610.16319%2C2610.16720%2C2610.16778%2C2610.17457%2C2610.17710%2C2610.17792%2C2610.17895%2C2610.17928%2C2610.18508%2C2610.18784%2C2610.18868%2C2610.19100%2C2610.19128%2C2610.20584&max_results=29"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:46:06Z", "role": "primary", "sha256": "9b385e9f6aa2f7169f616a76887df3b76df605cb2bea071d99ee7ca3f9b659cc", "supports": ["environments"], "url": "https://os-copilot.github.io/OpenMobile2-Home/"}], "id": "arxiv:2610.14157", "identifiers": {"arxiv": "2610.14157"}, "kind": "paper", "last_verified_at": "2026-10-16T06:33:24Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.14157"}], "name": "OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-10-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces OpenMobile-2, combining simulated mobile apps, emulator tasks, released training data, and policies that can alternate GUI interaction with app-native tools.", "topics": ["mobile-navigation", "tool-integration", "data-generation", "reinforcement-learning"], "updated_at": "2026-10-09", "url": "https://arxiv.org/abs/2610.14157"}
{"aliases": [], "authors": ["Zian Yuan", "Wei Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c5a2743a18bae1deeed13fbd1dd7379c3f21c67488627057ccb466ffe51d09dc", "submitted_at": "2026-10-12T13:34:52Z", "updated_at": "2026-10-12T13:34:52Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.16778v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2610.16778", "identifiers": {"arxiv": "2610.16778"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.16778"}], "name": "PrivacyGuard: Source-Linked Sanitization and Locally Resolvable PII References for Cloud GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-10-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces PrivacyGuard, which sanitizes source-linked personal information and maintains locally resolvable references across mobile-agent turns to reduce exposure to remote planners.", "topics": ["safety-security", "mobile-navigation", "evaluation"], "updated_at": "2026-10-12", "url": "https://arxiv.org/abs/2610.16778"}
{"aliases": [], "authors": ["Taeyun Roh", "Suhyeong Park", "Gijin Kim", "Wonjune Jang", "Jaewoo Kang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "551f198c0976c75693c6298400800cc66ce1b1b5ee304965155a6bb3ca9d68fe", "submitted_at": "2026-10-13T08:15:52Z", "updated_at": "2026-10-13T08:15:52Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.17928v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:46:05Z", "role": "primary", "sha256": "3fb5aabfb07df620955f0b74347f9d5926a1cd3d506b1098eccba9477627269f", "supports": ["environments", "notes"], "url": "https://raw.githubusercontent.com/dmis-lab/SwitchMem/HEAD/README.md"}], "id": "arxiv:2610.17928", "identifiers": {"arxiv": "2610.17928"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.17928"}], "name": "Learning How to Remember: Memory Modality Selection for GUI Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced. Android platform tagging is additionally supported by the primary project documentation.", "published_at": "2026-10-13", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces SwitchMem, which chooses a textual or visual representation of retrieved experience at each GUI interaction step instead of fixing one memory modality for a task.", "topics": ["memory", "mobile-navigation"], "updated_at": "2026-10-13", "url": "https://arxiv.org/abs/2610.17928"}
{"aliases": [], "authors": ["Ridong Zhang", "Shuxian Liang", "Chaoqun Wan", "Zhen Huang", "Xian-Sheng Hua"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "50d5cb78e6715f0749c5973e900745ecdb3672febc2c8e090da94cb708127352", "submitted_at": "2026-10-14T09:58:40Z", "updated_at": "2026-10-14T09:58:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.19900v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:46:06Z", "role": "primary", "sha256": "652e8369ef11334d76c0eb67afeaa5c9f7841fd31ca02243b0dfb1493316849a", "supports": ["environments", "notes"], "url": "https://iaie-physicalai.github.io/GraceBench"}], "id": "arxiv:2610.19900", "identifiers": {"arxiv": "2610.19900"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.19900"}], "name": "How GUI Agents Fail: GraceBench for Execution Stability Diagnosis", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced. Android platform tagging is additionally supported by the primary project documentation.", "published_at": "2026-10-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces GraceBench, using application transition graphs and recorded interaction evidence to diagnose deviations, loops, and recovery that final task-success scores can hide.", "topics": ["evaluation", "mobile-navigation", "robustness"], "updated_at": "2026-10-14", "url": "https://arxiv.org/abs/2610.19900"}
{"aliases": [], "authors": ["Adamo Orsini", "Seyed Mehdi Ayyoubzadeh", "Sadman Rakib Pinon", "Hannuo Zhang", "Koosha Gholipour Baradari", "Yuanhao Yu", "Xinxin Zuo", "Yang Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "caaf24ef4d8b86c8aaebc852235d0fe947a5ed859dc1ba8329ce07a2f7be9aa1", "submitted_at": "2026-10-15T21:40:34Z", "updated_at": "2026-10-15T21:40:34Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.22672v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-20T05:52:01Z", "role": "primary", "sha256": "63e37cd26bfe69455a3fa835f3d6ba4cfcc5bb7dc91f90505920d37b1e08f0b6", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2610.19384%2C2610.22672%2C2610.22697%2C2610.23303%2C2610.23307%2C2610.24729&max_results=6"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T12:56:56.464343+00:00", "role": "primary", "sha256": "5fd9d7926e99d068fa8fb7238a9e7811e3f8c55d00e6b89d5672754cb3e619bc", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/html/2610.22672v1"}], "id": "arxiv:2610.22672", "identifiers": {"arxiv": "2610.22672"}, "kind": "paper", "last_verified_at": "2026-10-20T12:56:56.464343+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.22672"}], "name": "Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation", "notes": "The controlled cohort has 84 tasks across six apps; the broader inventory spans 20 apps. Main results use human destination labels. DroidTask and SPA-Bench are converted to navigation-only protocols. Some comparison cells received another graph condition’s memory, with sensitivity analyses reported. Cross-family runs differ in app versions, state and denominators. A small stale-graph probe does not establish robustness. Models, code, artifacts and performance were not independently reproduced.", "published_at": "2026-10-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "TAG-Nav supplies Android GUI agents with destination and route memory distilled from offline app exploration. DestBench measures arrival at a reference pre-action screen, separately from downstream task execution.", "topics": ["mobile-navigation", "memory", "evaluation"], "updated_at": "2026-10-15", "url": "https://arxiv.org/abs/2610.22672"}
{"aliases": [], "authors": ["Songping Wang", "Borui Li", "Qinglong Liu", "Yueming Lyu", "Yi Huang", "Fengting Li", "Chao Feng", "Caifeng Shan"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ea753c1cb0666950d89f2781511f26872e3d5b1c2fd2434896248214160fa22c", "submitted_at": "2026-10-16T11:06:37Z", "updated_at": "2026-10-16T11:06:37Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.23303v1"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-20T05:52:01Z", "role": "primary", "sha256": "63e37cd26bfe69455a3fa835f3d6ba4cfcc5bb7dc91f90505920d37b1e08f0b6", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2610.19384%2C2610.22672%2C2610.22697%2C2610.23303%2C2610.23307%2C2610.24729&max_results=6"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T08:27:26.236797+00:00", "role": "primary", "sha256": "80bed80786f939973d0d13b4f892300fee02a6110e326247131fc83d257796de", "supports": ["name", "kind", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agent%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22browser+agents%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22mobile+agents%22+OR+ti%3A%22desktop+agent%22%29+AND+submittedDate%3A%5B202610130000+TO+202610192359%5D&start=0&max_results=200&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T10:42:09.967883+00:00", "role": "primary", "sha256": "ec9d647818be346ddbf7807be87b4789cd53e50c5d3d7a7904ad4f49bc71c38e", "supports": ["summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/html/2610.23303v1"}], "id": "arxiv:2610.23303", "identifiers": {"arxiv": "2610.23303"}, "kind": "paper", "last_verified_at": "2026-10-20T08:27:26.236797+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.23303"}], "name": "MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents", "notes": "Reviewed the complete retained abstract and selected exact-v1 threat-model, construction and evaluation sections. Execution uses a browser-based Android-like simulator, not real Android isolation or live services. The attacker controls instructions and designated carriers, not privileged simulator state/APIs or system/model/harness internals. Rates depend on release, budget and adjudication coverage. SAF labels track observable expressions and actions, not latent reasoning; unresolved episodes are excluded from rate denominators. No independent reproduction.", "published_at": "2026-10-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileJailBench evaluates mobile-agent jailbreaks in a browser-based Android-like simulator, combining feedback-driven attack evolution, separately admitted task expansions and evidence-grounded outcome adjudication.", "topics": ["safety-security", "mobile-navigation", "evaluation", "observability", "cross-app"], "updated_at": "2026-10-16", "url": "https://arxiv.org/abs/2610.23303"}
{"aliases": [], "authors": ["Songping Wang", "Peiyang Li", "Yi Huang", "Fengting Li", "Xuhao Ran", "Yueming Lyu", "Chao Feng", "Caifeng Shan"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3fc22fbeda19ac2947b00af73801f0674c550e0d7c78919f811cae754b06128c", "submitted_at": "2026-10-16T11:10:30Z", "updated_at": "2026-10-16T11:10:30Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.23307v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-20T05:52:01Z", "role": "primary", "sha256": "63e37cd26bfe69455a3fa835f3d6ba4cfcc5bb7dc91f90505920d37b1e08f0b6", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2610.19384%2C2610.22672%2C2610.22697%2C2610.23303%2C2610.23307%2C2610.24729&max_results=6"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T08:27:26.236797+00:00", "role": "primary", "sha256": "80bed80786f939973d0d13b4f892300fee02a6110e326247131fc83d257796de", "supports": ["name", "kind", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agent%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22browser+agents%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22mobile+agents%22+OR+ti%3A%22desktop+agent%22%29+AND+submittedDate%3A%5B202610130000+TO+202610192359%5D&start=0&max_results=200&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T09:17:36.223826+00:00", "role": "primary", "sha256": "3803984a185b6258276b87b87ac1991583878fb41dc22618ff743f6f69c7bc7e", "supports": ["summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/html/2610.23307v1"}], "id": "arxiv:2610.23307", "identifiers": {"arxiv": "2610.23307"}, "kind": "paper", "last_verified_at": "2026-10-20T08:27:26.236797+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.23307"}], "name": "MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection", "notes": "Reviewed the complete abstract and selected v1 construction, threat-model and evaluation sections. The attacker modifies observation surfaces, not system instructions, model parameters or the OS. State oracles are distinct from emitted-rationale diagnoses, whose labels include outcome-dependent constraints. Those diagnostics are not independent evidence of hidden-reasoning causality. No reproduction or release verification.", "published_at": "2026-10-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "MobileInject evaluates visual/textual observation injection in stateful Android workflows using resettable emulators, benign/adversarial state oracles and trace-based diagnosis of emitted rationales and actions.", "topics": ["safety-security", "mobile-navigation", "evaluation", "observability", "cross-app"], "updated_at": "2026-10-16", "url": "https://arxiv.org/abs/2610.23307"}
{"aliases": [], "authors": ["Fuyao Zhang", "Wenwen He", "Jiaming Zhang", "Yurong Hao", "Xuan Wang", "Guowei Guan", "Che Wang", "Longtao Huang", "Wei Yang Bryan Lim"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "41178d19a23653c0f49423b8f725584bded7ab8819a1a46e83a062794460b4cb", "submitted_at": "2026-10-19T11:30:48Z", "updated_at": "2026-10-19T11:30:48Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.26203v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-20T05:52:00Z", "role": "primary", "sha256": "af310824eea97aac8209023ff53bad7bea77778816586b10bb94110148347af9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agent%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B202610060000+TO+202610200000%5D&start=0&max_results=200&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T08:27:26.236797+00:00", "role": "primary", "sha256": "80bed80786f939973d0d13b4f892300fee02a6110e326247131fc83d257796de", "supports": ["name", "kind", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agent%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22browser+agents%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22mobile+agents%22+OR+ti%3A%22desktop+agent%22%29+AND+submittedDate%3A%5B202610130000+TO+202610192359%5D&start=0&max_results=200&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T09:17:23.872790+00:00", "role": "primary", "sha256": "28848f8f597b2a8865ad98f5aa1e4401e15a49f92b33f7bce4d4f044c168ada0", "supports": ["summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/html/2610.26203v1"}], "id": "arxiv:2610.26203", "identifiers": {"arxiv": "2610.26203"}, "kind": "paper", "last_verified_at": "2026-10-20T08:27:26.236797+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.26203"}], "name": "Focused Omni-Modal GUI Agents", "notes": "Reviewed the complete retained abstract and selected v1 method/evaluation sections. OmniGUI uses episode-disjoint reference-action evaluation; Type Match, Exact Match and Goal Progress are not presented as independently demonstrated live task-success gains. The Android role is explicit in Appendix D.1. No reproduction or artifact-release verification.", "published_at": "2026-10-19", "relations": [], "review_status": "curated", "scope": "core", "summary": "FocusGUI learns step-specific weights over screenshot, audio, video and interaction-context channels, injecting a compact residual into a frozen decoder without pruning its inputs.", "topics": ["screen-understanding", "grounding", "imitation-learning", "interaction-history", "mobile-navigation"], "updated_at": "2026-10-19", "url": "https://arxiv.org/abs/2610.26203"}
{"aliases": [], "authors": ["Zhuomin Chen", "Jingchao Ni", "Xu Zheng", "Yong Chen", "Mo Sha", "Wei Cheng", "Dongsheng Luo"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e91c0f0ab28f7f2da89bdff5f9ce3dc592469a8606f35137144f514e70c96f78", "submitted_at": "2026-10-19T16:18:16Z", "updated_at": "2026-10-19T16:18:16Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.26660v1"}}, "environments": ["android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-20T05:52:00Z", "role": "primary", "sha256": "af310824eea97aac8209023ff53bad7bea77778816586b10bb94110148347af9", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agent%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B202610060000+TO+202610200000%5D&start=0&max_results=200&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T08:27:26.236797+00:00", "role": "primary", "sha256": "80bed80786f939973d0d13b4f892300fee02a6110e326247131fc83d257796de", "supports": ["name", "kind", "scope"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agent%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22+OR+ti%3A%22browser+agents%22+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22mobile+agents%22+OR+ti%3A%22desktop+agent%22%29+AND+submittedDate%3A%5B202610130000+TO+202610192359%5D&start=0&max_results=200&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T09:17:26.960480+00:00", "role": "primary", "sha256": "7cb553f8230cfb203df446f08e29d48b676addfe9b076d35171d09970d1970bf", "supports": ["summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/html/2610.26660v1"}], "id": "arxiv:2610.26660", "identifiers": {"arxiv": "2610.26660"}, "kind": "paper", "last_verified_at": "2026-10-20T08:27:26.236797+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.26660"}], "name": "Tandem: Serving Hybrid Linear-Attention GUI Agents on Mobile NPUs", "notes": "Reviewed the complete abstract and selected v1 system/evaluation sections. Main latency measurements replay recorded requests and exclude app execution; the paper also reports instrumented real tasks. These are serving-time, energy and action-fidelity results, not a claimed task-success improvement. Hardware, cooling and model configurations matter. No independent reproduction.", "published_at": "2026-10-19", "relations": [], "review_status": "curated", "scope": "core", "summary": "Tandem serves hybrid GUI-agent models on Android NPUs using divergence-point state checkpoints, rollback-aware speculative decoding and idle power release between request bursts.", "topics": ["efficiency", "mobile-navigation"], "updated_at": "2026-10-19", "url": "https://arxiv.org/abs/2610.26660"}
{"aliases": [], "authors": [], "details": {"dataset_profile": {"counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_control/README.md", "population": "AndroidControl collection", "qualifier": "more-than", "unit": "demonstrations", "value": 15000}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_control/README.md", "population": "AndroidControl collection", "qualifier": "exact", "unit": "applications", "value": 833}], "evidence_urls": ["https://raw.githubusercontent.com/google-research/google-research/master/android_control/README.md"], "formats": ["GZIP-compressed TFRecord"], "modalities": ["screenshots", "accessibility trees", "instructions", "JSON actions"], "notes": "Step instructions can be repeated across multiple actions. Each episode has one more screenshot than action; do not count repeated step instructions as independent task goals.", "splits": ["publisher split file"], "supervision": ["interaction trajectories", "high- and low-level action instruction"]}, "modalities": ["screenshot", "accessibility-tree", "instruction", "action"], "reported_scale": {"comparison": ">", "unit": "demonstrations", "value": 15000}, "sample_count": null, "sample_unit": "demonstrations"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:38:29Z", "role": "primary", "sha256": "e4f8baa15441fb63cad07220cc5a4de177a1f785d4fe1fed5cfcbf3c3867faf1", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details.sample_count", "details.sample_unit", "details.reported_scale", "details.modalities", "details.dataset_profile"], "url": "https://raw.githubusercontent.com/google-research/google-research/master/android_control/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:06Z", "role": "primary", "sha256": "cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/google-research/google-research/HEAD/LICENSE"}], "id": "component:google-research/android_control", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-16T06:38:29Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T06:42:06Z", "url": "https://raw.githubusercontent.com/google-research/google-research/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/google-research/google-research/tree/master/android_control"}], "name": "AndroidControl", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_control/README.md", "target_id": "arxiv:2406.03679", "type": "introduced_by"}], "review_status": "curated", "scope": "core", "summary": "Android demonstrations with high-level goals, step instructions, screenshots, and accessibility trees.", "topics": ["data-generation", "mobile-navigation"], "updated_at": null, "url": "https://github.com/google-research/google-research/tree/master/android_control"}
{"aliases": [], "authors": [], "details": {"access": "public download referenced by publisher", "dataset_profile": {"counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_in_the_wild/README.md", "population": "sum of the five published AitW subsets", "qualifier": "exact", "unit": "episodes", "value": 715142}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_in_the_wild/README.md", "population": "sum of the five published AitW subsets", "qualifier": "exact", "unit": "action examples", "value": 5689993}], "evidence_urls": ["https://raw.githubusercontent.com/google-research/google-research/master/android_in_the_wild/README.md"], "formats": ["GZIP-compressed TFRecord"], "modalities": ["screenshots", "instructions", "actions"], "notes": "Episodes and action examples are different units. The collection combines multi-step subsets and hindsight-labeled single-step tasks; preserve subset and split choices.", "splits": [], "supervision": ["interaction trajectories", "action prediction"]}, "download_url": "https://console.cloud.google.com/storage/browser/gresearch/android-in-the-wild", "example_count": 5689993, "modalities": ["screenshot", "action", "instruction"], "sample_count": 715142, "sample_unit": "episodes"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:38:29Z", "role": "primary", "sha256": "6d8964c95db41dada1d5867e50a5ec61f6cb90595965d0e72e010b8e4a12dcb2", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details.sample_count", "details.sample_unit", "details.example_count", "details.modalities", "details.access", "details.download_url", "details.dataset_profile"], "url": "https://raw.githubusercontent.com/google-research/google-research/master/android_in_the_wild/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:06Z", "role": "primary", "sha256": "cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/google-research/google-research/HEAD/LICENSE"}], "id": "component:google-research/android_in_the_wild", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-16T06:38:29Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T06:42:06Z", "url": "https://raw.githubusercontent.com/google-research/google-research/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/google-research/google-research/tree/master/android_in_the_wild"}], "name": "Android in the Wild", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_in_the_wild/README.md", "target_id": "arxiv:2307.10088", "type": "introduced_by"}], "review_status": "curated", "scope": "core", "summary": "Human demonstrations of Android tasks with screenshots and touch actions.", "topics": ["data-generation", "mobile-navigation"], "updated_at": null, "url": "https://github.com/google-research/google-research/tree/master/android_in_the_wild"}
{"aliases": [], "authors": [], "details": {"component_path": "Mobile-Agent-E", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/LICENSE"], "reason": "Reviewed repository license declaration for code; third-party dependencies, data, weights and executable environment images are separate."}}, "repository_tree_sha": "11cea575561fb7800b5fb6b6cafa56f7a91de11f", "repository_url": "https://github.com/X-PLUG/MobileAgent"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:27:15Z", "role": "primary", "sha256": "f8515fbce73ea0ef3d1d558d4567bb949244e6384e61c956ba3ddbc27294f0ae", "supports": ["name", "kind", "environments", "scope", "notes", "relations"], "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/Mobile-Agent-E/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T15:37:03Z", "role": "primary", "sha256": "d403251020124bebcd9f180f800c8ea9f18a3f117c82fcf04c3cbe9ffe0e35f9", "supports": ["identity"], "url": "https://api.github.com/repos/X-PLUG/MobileAgent"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:25:21Z", "role": "primary", "sha256": "7293efadde7c96b64ff8483b2157241e17d0b0fbfff4839de9c7b11485b07cbb", "supports": ["identity", "release_status", "details.repository_tree_sha", "relations"], "url": "https://api.github.com/repos/X-PLUG/MobileAgent/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["summary", "topics"], "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:42:03Z", "role": "primary", "sha256": "961819a89dacd1f4f161e1d2ebf616b538bf095a2eecfa3ef40b7ccec633fac4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/LICENSE"}], "id": "component:x-plug/mobileagent/mobile-agent-e", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-18T04:27:15Z", "licenses": {"code": {"basis": "Reviewed repository license declaration for code; third-party dependencies, data, weights and executable environment images are separate.", "declared": "MIT", "retrieved_at": "2026-10-16T06:42:03Z", "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/X-PLUG/MobileAgent/tree/main/Mobile-Agent-E"}], "name": "Mobile-Agent-E code component", "notes": "The inspected README explicitly supports Android only, with experiments on Samsung Galaxy A15; host-machine macOS/Linux instructions do not imply control of those operating systems. Agent code, launch scripts and benchmark definitions are present. The root MIT code license does not establish terms for the separately published task dataset or external models.", "published_at": null, "relations": [{"evidence_url": "https://api.github.com/repos/X-PLUG/MobileAgent/git/trees/main?recursive=1", "target_id": "github:x-plug/mobileagent", "type": "component_of"}, {"evidence_url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/Mobile-Agent-E/README.md", "target_id": "arxiv:2501.11733", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Android automation component with hierarchical planning, reflection and persistent tips/shortcuts learned across task sequences.", "topics": ["planning", "memory", "self-reflection", "mobile-navigation"], "updated_at": null, "url": "https://github.com/X-PLUG/MobileAgent/tree/main/Mobile-Agent-E"}
{"aliases": [], "authors": [], "details": {"dataset_profile": {"counts": [], "evidence_urls": ["https://raw.githubusercontent.com/aburns4/MoTIF/HEAD/README.md"], "formats": ["JSON metadata", "screen images"], "modalities": ["screenshots", "view hierarchies", "language", "interaction sequences", "feasibility labels"], "notes": "The raw collection mixes action, language, exploration, and unusable/other traces. These groups have different annotation coverage; not every raw trace is a valid task demonstration.", "splits": [], "supervision": ["interaction trajectories", "task feasibility"]}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "4b2f5a23dc28e96b671272380b953e7fabaf34f4b1e83f3513643846718e3389", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details.dataset_profile"], "url": "https://raw.githubusercontent.com/aburns4/MoTIF/HEAD/README.md"}], "id": "github:aburns4/motif", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-16T06:36:01Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/aburns4/MoTIF"}], "name": "MoTIF", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/aburns4/MoTIF/HEAD/README.md", "target_id": "arxiv:2202.02312", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile task demonstrations and natural-language instructions.", "topics": ["mobile-navigation"], "updated_at": null, "url": "https://github.com/aburns4/MoTIF"}
{"aliases": [], "authors": [], "details": {"benchmark_protocol": {"actions": ["agent-specific Android actions"], "counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/README.md", "population": "complete README task collection", "qualifier": "exact", "unit": "tasks", "value": 340}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/README.md", "population": "single-app subset", "qualifier": "exact", "unit": "tasks", "value": 300}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/README.md", "population": "cross-app subset", "qualifier": "exact", "unit": "tasks", "value": 40}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/README.md", "population": "README total including third-party, Google, and system apps", "qualifier": "exact", "unit": "applications", "value": 66}], "evaluation": "A multimodal evaluator and annotated key-component matching assess completion; the framework also reports resource-use metrics.", "evidence_urls": ["https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/README.md", "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/Documentation.md"], "focus": ["mobile task completion", "resource use", "cross-app workflows"], "notes": "The two task subsets partition the 340 tasks. The integrated agent and evaluator modes must accompany results. The preconfigured emulator snapshot is still marked coming soon in the inspected documentation.", "observations": ["screenshot trajectories"], "setting": "interactive"}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:35:58Z", "role": "primary", "sha256": "5294a67728072a3658cb2073bdf9a084fe3c00d87a848923dff68adb35213072", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:35:58Z", "role": "primary", "sha256": "5294a67728072a3658cb2073bdf9a084fe3c00d87a848923dff68adb35213072", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:03:23Z", "role": "primary", "sha256": "a55290d62f8823097c73d74bac4eb08853a3caff724382e60a6a9364e7ced987", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/Documentation.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:41:58Z", "role": "primary", "sha256": "6962bfc8ee16c6e985e4fb680b8fe46d5b34d30f7cb8a1e61fd4c55c93120ddf", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/LICENSE"}], "id": "github:ai-agents-2030/spa-bench", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-16T06:35:58Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T06:41:58Z", "url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/ai-agents-2030/SPA-Bench"}], "name": "SPA-Bench", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/ai-agents-2030/SPA-Bench/HEAD/README.md", "target_id": "arxiv:2410.15164", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "340 single-app and cross-app tasks over 66 Chinese and English Android apps, with plug-in support for 11 smartphone agents and automatic coarse-to-fine success detection.", "topics": ["evaluation", "mobile-navigation"], "updated_at": null, "url": "https://github.com/ai-agents-2030/SPA-Bench"}
{"aliases": [], "authors": [], "details": {"availability": "Public Android automation source and setup instructions; external models/services required.", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/AkimotoAyako/VisionTasker/HEAD/LICENSE"], "reason": "Repository GNU GPL version 3 license; pretrained models and linked data retain separate terms."}}, "repository_revision": "d31b50e98bde28c0d1cfbc7d7ee2528d10b3fbb0"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:20:18Z", "role": "primary", "sha256": "816981b343628c53188fd27041d62f52854fcfe83c976a125b84545f5e010274", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations"], "url": "https://raw.githubusercontent.com/AkimotoAyako/VisionTasker/HEAD/readme.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:23Z", "role": "primary", "sha256": "94d8e95d302160e3c581015267dcfbb9f61c41ad1f04e470fcd71f5ee1ffa25d", "supports": ["identity"], "url": "https://api.github.com/repos/AkimotoAyako/VisionTasker"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:19:48Z", "role": "primary", "sha256": "54a1c08d44e0ad1d60bee57e3db2842518e014db3be8b08362e484315f3a6a6f", "supports": ["release_status", "details.repository_revision"], "url": "https://api.github.com/repos/AkimotoAyako/VisionTasker/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:03Z", "role": "primary", "sha256": "3972dc9744f6499f0f9b2dbf76696f2ae7ad8af9b23dde66d6af86c9dfb36986", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/AkimotoAyako/VisionTasker/HEAD/LICENSE"}], "id": "github:akimotoayako/visiontasker", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-17T11:20:18Z", "licenses": {"code": {"basis": "Repository GNU GPL version 3 license; pretrained models and linked data retain separate terms.", "declared": "GPL-3.0", "retrieved_at": "2026-10-17T11:23:03Z", "url": "https://raw.githubusercontent.com/AkimotoAyako/VisionTasker/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/AkimotoAyako/VisionTasker"}], "name": "VisionTasker", "notes": "The official lowercase readme.md and source tree expose automatic and step-by-step entry points. The documented setup uses a Windows host and an Android phone connected through ADB; it also requires separately obtained detection/CLIP models and model/OCR services. GPL-3.0 is recorded for the code only. External model download links were not used to infer weight licenses or verify a separate checkpoint release.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/AkimotoAyako/VisionTasker/HEAD/readme.md", "target_id": "arxiv:2312.11190", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "An Android automation implementation that translates screenshot-based UI understanding into language descriptions for step-by-step LLM planning and action execution.", "topics": ["mobile-navigation", "screen-understanding", "planning"], "updated_at": null, "url": "https://github.com/AkimotoAyako/VisionTasker"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:09:28Z", "role": "primary", "sha256": "c4da2b089f97296ac6c7b3ef7273db57b650d12cf3595f6f6ea74c901e5277b8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/alipay/mobile-agent/HEAD/README.md"}], "id": "github:alipay/mobile-agent", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T11:09:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/alipay/mobile-agent"}], "name": "MobileAgent (Alipay)", "notes": "Distinct from the X-PLUG/MobileAgent project despite the similar name.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/alipay/mobile-agent/HEAD/README.md", "target_id": "arxiv:2401.04124", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile-control research implementation combining operating-procedure context with human interaction for personalized task execution.", "topics": ["mobile-navigation", "workflow", "human-in-the-loop"], "updated_at": null, "url": "https://github.com/alipay/mobile-agent"}
{"aliases": [], "authors": [], "details": {"benchmark_protocol": {"actions": ["app launch/stop", "click/double-click/long-click", "text input", "swipe/drag and Android navigation", "finish"], "counts": [], "evaluation": "The released evaluator compares trajectories with reference actions using longest-common-subsequence-based task reward and completion. Its reversed redundancy metric is the reference/predicted action-length ratio (with 1e-6 denominator smoothing), multiplied by the LLM success flag. LLM success judgments and instruction-constraint checks are separate metrics. Full reference-dependent evaluation coverage cannot be assumed because complete annotated action sequences are not released.", "evidence_urls": ["https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/README.md", "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/android_env2/README.md", "https://api.github.com/repos/AndroidArenaAgent/AndroidArena/git/trees/main?recursive=1", "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/android_env2/observation.py", "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/android_env2/actions.py", "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/run_evaluator.py"], "focus": ["multi-step Android tasks", "cross-app workflows and instruction constraints"], "notes": "README states that task instructions are released but annotated action sequences, apart from the calendar example, will come later. Environment setup targets Android API 33 with uiautomator2 and manual Google-account setup. Public task YAML and evaluator code exist, but benchmark execution and full reference coverage were not verified. No task total is derived from app YAML file counts. Code and data licenses remain unknown.", "observations": ["UI hierarchy text", "screenshots", "combined text/image observations"], "setting": "interactive"}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:35:58Z", "role": "primary", "sha256": "206bd0dc5220cf754cffc97767cce6a3cd27660ef050a569366bef2331241c60", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:21:10Z", "role": "primary", "sha256": "a1e7dc0c5facae030c2cf19aad6511996e7e1198d8d6619268d10c29a1b57bcf", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/android_env2/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:14:05Z", "role": "primary", "sha256": "edc03388b67143644db4a412e4c888f8c796068daff29f63615f0b6a3a04262a", "supports": ["details.benchmark_protocol"], "url": "https://api.github.com/repos/AndroidArenaAgent/AndroidArena/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:24:52Z", "role": "primary", "sha256": "cfa9d272c85398f54c18d6e7445d680009e8c16d128962235d899592d3094c2f", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/android_env2/observation.py"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:24:53Z", "role": "primary", "sha256": "d25f2edf9202f59615341b62fc6046ac23a6f4cb072a6038ac562506cbdc891c", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/android_env2/actions.py"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:21:10Z", "role": "primary", "sha256": "257c42e980a0b14bd74bfcc381a0ecbef2b538c0f1cc1a94d22925efe354fb8e", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/run_evaluator.py"}], "id": "github:androidarenaagent/androidarena", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-16T06:35:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/AndroidArenaAgent/AndroidArena"}], "name": "AndroidArena", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/AndroidArenaAgent/AndroidArena/HEAD/README.md", "target_id": "arxiv:2402.06596", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Android environment for evaluating language-model-driven agents.", "topics": ["evaluation", "mobile-navigation"], "updated_at": null, "url": "https://github.com/AndroidArenaAgent/AndroidArena"}
{"aliases": ["github:cooelf/auto-ui", "cooelf/Auto-UI", "https://github.com/cooelf/Auto-UI"], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:42:12Z", "role": "primary", "sha256": "13f045fa84dc0ad68dcceea95fc7e0e34a45bcda866d589132351559b87a8e30", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/cooelf/Auto-GUI/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T10:48:41Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/cooelf/Auto-GUI/HEAD/LICENSE"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-17T14:13:59Z", "role": "primary", "sha256": "569f3c779e6a0b8210a764c9096e49e8a5199c107a64f7fcfb7a011257bf2a12", "supports": ["aliases"], "url": "https://api.github.com/repos/cooelf/Auto-UI"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-17T14:14:00Z", "role": "primary", "sha256": "569f3c779e6a0b8210a764c9096e49e8a5199c107a64f7fcfb7a011257bf2a12", "supports": ["aliases"], "url": "https://api.github.com/repos/cooelf/Auto-GUI"}], "id": "github:cooelf/auto-gui", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T10:42:12Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T10:48:41Z", "url": "https://raw.githubusercontent.com/cooelf/Auto-GUI/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/cooelf/Auto-GUI"}], "name": "Auto-GUI / Auto-UI", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/cooelf/Auto-GUI/HEAD/README.md", "target_id": "arxiv:2309.11436", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Screenshot-based mobile agent implementation with training and inference code for chain-of-action prediction.", "topics": ["mobile-navigation", "planning"], "updated_at": null, "url": "https://github.com/cooelf/Auto-GUI"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:46:05Z", "role": "primary", "sha256": "3fb5aabfb07df620955f0b74347f9d5926a1cd3d506b1098eccba9477627269f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/dmis-lab/SwitchMem/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:10Z", "role": "primary", "sha256": "cec8e4679c883f13983915e9f77d175a84a234d69386e78f9ea75157cefbdcb4", "supports": ["relations"], "url": "https://txxnrd.github.io/switchmem/"}], "id": "github:dmis-lab/switchmem", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-17T01:46:05Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/dmis-lab/SwitchMem"}], "name": "SwitchMem", "notes": "The implementation distinguishes step-level AITW/LearnGUI scores from terminal task success on MobileMiniWoB++. Benchmark outcomes and local smoke-test outputs are different claims; neither was independently reproduced here.", "published_at": null, "relations": [{"evidence_url": "https://txxnrd.github.io/switchmem/", "target_id": "arxiv:2610.17928", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Memory-routing implementation that chooses text or image demonstrations for a frozen GUI actor, with offline evaluation and Android transfer experiments.", "topics": ["memory", "mobile-navigation"], "updated_at": null, "url": "https://github.com/dmis-lab/SwitchMem"}
{"aliases": ["Droidrun"], "authors": [], "details": {"availability": "Published source; official release metadata inspected", "release_tag": "v0.7.0"}, "environments": ["android", "ios"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "80052560e06db353277a55f3f8f6a4b5231aa6dc1376d5182559b72adcb5c3a1", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/droidrun/mobilerun/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:56Z", "role": "primary", "sha256": "e48b9154a58b4b7021a4707ca185af32b9dd81c828d53ba36a86f195c1720344", "supports": ["identity"], "url": "https://api.github.com/repos/droidrun/mobilerun"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "7f40d42acd62b4405b5077a0f594a35aae73fb057589346afa5f6fb22d710a0c", "supports": ["release_status"], "url": "https://api.github.com/repos/droidrun/mobilerun/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:00:56Z", "role": "primary", "sha256": "f85c8b766edc107c455a86e363c56af3d1f7fce669b55377f4010982aa3a7e44", "supports": ["release_status"], "url": "https://api.github.com/repos/droidrun/mobilerun/releases/latest"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:00:57Z", "role": "primary", "sha256": "b3ebb19fda8286efa415d457529eafff41e1b1a27fe4e00d99f34e1559b6cdd9", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/droidrun/mobilerun/HEAD/LICENSE"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "e48b9154a58b4b7021a4707ca185af32b9dd81c828d53ba36a86f195c1720344", "supports": ["identity", "aliases", "notes"], "url": "https://api.github.com/repos/droidrun/droidrun"}, {"method": "license_header", "retrieved_at": "2026-10-17T04:00:57Z", "role": "primary", "sha256": "b3ebb19fda8286efa415d457529eafff41e1b1a27fe4e00d99f34e1559b6cdd9", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/droidrun/mobilerun/HEAD/LICENSE"}], "id": "github:droidrun/mobilerun", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-17T03:59:53Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-17T04:00:57Z", "url": "https://raw.githubusercontent.com/droidrun/mobilerun/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/droidrun/mobilerun"}], "name": "Mobilerun (formerly Droidrun)", "notes": "The former droidrun/droidrun repository resolves to droidrun/mobilerun through the official API. Source and release v0.7.0 are public. Android and iOS setup paths differ, and the companion Portal app is a separate device bridge. MIT applies to framework code; model-provider and cloud-service terms are separate.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "A framework that combines screenshots and accessibility state with agent tools for mobile-device tasks through command-line and Python interfaces.", "topics": ["mobile-navigation", "tool-integration", "planning"], "updated_at": null, "url": "https://github.com/droidrun/mobilerun"}
{"aliases": ["Droidrun Portal"], "authors": [], "details": {"availability": "Published source; official release metadata inspected", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/droidrun/mobilerun-portal/HEAD/LICENSE"], "reason": "GitHub classifies this license as NOASSERTION, but the actual program-specific notice is explicit. Do not reduce the permission to a generic unknown or silently transfer the framework MIT declaration."}}, "release_tag": "v0.7.25"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:54Z", "role": "primary", "sha256": "fd2257dd735dbb755f2de36b44e425e5862004a04130e53e92b330f1419479a0", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/droidrun/mobilerun-portal/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:56Z", "role": "primary", "sha256": "be519be28e277bd979717996e9587879c6a5d9235b95944305252b18595da413", "supports": ["identity"], "url": "https://api.github.com/repos/droidrun/mobilerun-portal"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:54Z", "role": "primary", "sha256": "65e81cfc9f227350e33da9e09030a7098e82a6021aa9b04cf0485ed2acee95a0", "supports": ["release_status"], "url": "https://api.github.com/repos/droidrun/mobilerun-portal/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:01Z", "role": "primary", "sha256": "31b8d75541bbfb7dba2f80adc83aa099ef83ca057b467eb2cb98b586f6d9d045", "supports": ["release_status"], "url": "https://api.github.com/repos/droidrun/mobilerun-portal/releases/latest"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:01Z", "role": "primary", "sha256": "945331c1cfa589694eb6ccc51574a72ee215a01b10bd5556f1b8be8d11bd71ab", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/droidrun/mobilerun-portal/HEAD/LICENSE"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:54Z", "role": "primary", "sha256": "be519be28e277bd979717996e9587879c6a5d9235b95944305252b18595da413", "supports": ["identity", "aliases", "notes"], "url": "https://api.github.com/repos/droidrun/droidrun-portal"}], "id": "github:droidrun/mobilerun-portal", "identifiers": {}, "kind": "tool", "last_verified_at": "2026-10-17T03:59:54Z", "licenses": {"code": {"basis": "The program-specific copyright notice explicitly permits GNU AGPL version 3 or any later version.", "declared": "AGPL-3.0-or-later", "retrieved_at": "2026-10-17T04:01:01Z", "url": "https://raw.githubusercontent.com/droidrun/mobilerun-portal/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/droidrun/mobilerun-portal"}], "name": "Mobilerun Portal (formerly Droidrun Portal)", "notes": "The official API resolves the former Droidrun Portal path to mobilerun-portal. Release metadata lists a v0.7.25 Android APK. Although GitHub labels its license NOASSERTION, the inspected LICENSE explicitly grants AGPL version 3 or later for the program. Accessibility-dependent UI functions require the service; no permissions were granted or device operated.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "An Android accessibility service that exposes UI-element inspection, device-control interfaces and screen feedback to mobile automation agents.", "topics": ["mobile-navigation", "screen-understanding", "tool-integration"], "updated_at": null, "url": "https://github.com/droidrun/mobilerun-portal"}
{"aliases": ["github:mobilegptsys/mobilegpt", "mobilegptsys/MobileGPT", "https://github.com/mobilegptsys/MobileGPT"], "authors": [], "details": {"availability": "Public Android client, Python server and manual offline-explorer source.", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/fclab-skku/MobileGPT/HEAD/LICENSE"], "reason": "Repository source license; linked benchmark data and external models retain separate terms."}}, "repository_revision": "7945048e6c05849aff1633744cbdf653c58bece2"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:07Z", "role": "primary", "sha256": "8683cff296d21c1a7a38bc372efaf004b8af644030fac77a4dc9d2b2e21d894b", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://raw.githubusercontent.com/fclab-skku/MobileGPT/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:55Z", "role": "primary", "sha256": "3d3ceb084d374b706842cff1f4ec986fde50c13cba141dc4619d5afe8b631d55", "supports": ["identity"], "url": "https://api.github.com/repos/mobilegptsys/MobileGPT"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:06Z", "role": "primary", "sha256": "2a8f30b3422a033b345c2054d55adff0836b7dac163e600583ba0db1b4423320", "supports": ["release_status", "details.repository_revision"], "url": "https://api.github.com/repos/fclab-skku/MobileGPT/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["relations"], "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:34:10Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/fclab-skku/MobileGPT/HEAD/LICENSE"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-17T14:14:04Z", "role": "primary", "sha256": "3d3ceb084d374b706842cff1f4ec986fde50c13cba141dc4619d5afe8b631d55", "supports": ["aliases"], "url": "https://api.github.com/repos/mobilegptsys/MobileGPT"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-17T14:14:06Z", "role": "primary", "sha256": "3d3ceb084d374b706842cff1f4ec986fde50c13cba141dc4619d5afe8b631d55", "supports": ["aliases"], "url": "https://api.github.com/repos/fclab-skku/MobileGPT"}], "id": "github:fclab-skku/mobilegpt", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-17T12:32:07Z", "licenses": {"code": {"basis": "Repository source license; linked benchmark data and external models retain separate terms.", "declared": "Apache-2.0", "retrieved_at": "2026-10-17T12:34:10Z", "url": "https://raw.githubusercontent.com/fclab-skku/MobileGPT/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/fclab-skku/MobileGPT"}], "name": "MobileGPT", "notes": "The old mobilegptsys repository resolves to fclab-skku/MobileGPT. Public Android client and Python server sources require Android SDK 33+, Accessibility Service setup and external service credentials. The README explicitly omits the random explorer and human-in-the-loop memory repair from the open-source version. Its benchmark description differs from the retained arXiv snapshot, so no dataset counts or reproduction claim are merged into this code record. External benchmark data was not approved as a separate release.", "published_at": null, "relations": [{"evidence_url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50", "target_id": "arxiv:2312.03003", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "An Android client and Python-server agent that learns reusable app subtasks through exploration, selection, derivation and memory recall.", "topics": ["mobile-navigation", "memory", "planning", "workflow"], "updated_at": null, "url": "https://github.com/fclab-skku/MobileGPT"}
{"aliases": [], "authors": [], "details": {"benchmark_protocol": {"actions": ["Android device interactions"], "counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/android_world/HEAD/README.md", "population": "parameterized AndroidWorld tasks", "qualifier": "exact", "unit": "task definitions", "value": 116}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/android_world/HEAD/README.md", "population": "documented AndroidWorld app set", "qualifier": "exact", "unit": "applications", "value": 20}], "evaluation": "Programmatic task-specific initialization, system-state success checks, and teardown.", "evidence_urls": ["https://raw.githubusercontent.com/google-research/android_world/HEAD/README.md", "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"], "focus": ["mobile task completion"], "notes": "Random parameters produce many instances from the same task definitions. Preserve seeds and parameterization; 116 is not a count of all possible task instances.", "observations": ["screenshots", "accessibility information"], "setting": "interactive"}, "evaluation_type": "programmatic state checks", "leaderboard_url": "https://docs.google.com/spreadsheets/d/1cchzP9dlTZ3WXQTfYNhh3avxoLipqHN75v1Tb86uhHo/edit?gid=0#gid=0", "metrics": ["task success"], "task_count": 116, "task_unit": "parameterized task definitions"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:35:57Z", "role": "primary", "sha256": "93201de5e21f2b12283a75b1e2c357781b2e6cc27eab20cc7dd7aa0f5919d839", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details.task_count", "details.task_unit", "details.metrics", "details.evaluation_type", "details.benchmark_protocol", "details.leaderboard_url"], "url": "https://raw.githubusercontent.com/google-research/android_world/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": ["details.benchmark_protocol"], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:41:57Z", "role": "primary", "sha256": "b09fcaf4fbc265223c2479c410beef2b98c5e687c78ecedf3452aa12ffc465f1", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/google-research/android_world/HEAD/LICENSE"}], "id": "github:google-research/android_world", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-16T06:35:57Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T06:41:57Z", "url": "https://raw.githubusercontent.com/google-research/android_world/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/google-research/android_world"}], "name": "AndroidWorld", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/google-research/android_world/HEAD/README.md", "target_id": "arxiv:2405.14573", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Android environment with programmatic task evaluation for mobile agents.", "topics": ["evaluation", "mobile-navigation"], "updated_at": null, "url": "https://github.com/google-research/android_world"}
{"aliases": [], "authors": [], "details": {"availability": "Public CoAT prompting/action-prediction and evaluation source.", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/IMNearth/CoAT/HEAD/README.md", "https://api.github.com/repos/IMNearth/CoAT/git/trees/main?recursive=1"], "reason": "Apache-2.0 badge alone does not establish component-scoped source terms; the inspected non-truncated tree has no license file."}}, "repository_revision": "9ab1a9f0e76581c50c84f8ebc6ada1a2084a0c71"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:53Z", "role": "primary", "sha256": "7a9fb905b64f2760a137cd267a5e38dd343df1821eda8172b606ab7500d27731", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "licenses.code"], "url": "https://raw.githubusercontent.com/IMNearth/CoAT/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:53Z", "role": "primary", "sha256": "d0c5056c9a74913f84a4f809bf01d9fd9ea325ac0a91b4c4a0a51220b2da9d68", "supports": ["identity"], "url": "https://api.github.com/repos/IMNearth/CoAT"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:04Z", "role": "primary", "sha256": "29d84ed12dc25035fd539604b06f6cc113080b389edeb9aa605cfa55c5f28151", "supports": ["release_status", "details.repository_revision", "licenses.code"], "url": "https://api.github.com/repos/IMNearth/CoAT/git/trees/main?recursive=1"}], "id": "github:imnearth/coat", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-17T12:30:53Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/IMNearth/CoAT"}], "name": "CoAT research implementation", "notes": "The tree contains run_coat.py and coat/agent.py, model.py and evaluate.py, with API-backed model configuration. This verifies a released annotation/prediction implementation, not a live phone controller or a released checkpoint. AiTZ screens/annotations are linked through external Drive/Baidu bundles whose complete download inventory was not verified here. The README has an Apache-2.0 badge, but no license file or explicit component grant is present; code/data/weight rights remain unestablished.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/IMNearth/CoAT/HEAD/README.md", "target_id": "arxiv:2403.02713", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Research scripts that generate screen descriptions, action reasoning and expected outcomes, then predict Android GUI actions using the resulting Chain-of-Action-Thought context.", "topics": ["planning", "mobile-navigation", "action-prediction"], "updated_at": null, "url": "https://github.com/IMNearth/CoAT"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:40:51Z", "role": "primary", "sha256": "dfcbaa088cc21dd4e3c67d6eb3b3a1dc476217165ce2ca0daa2facfda71b5a38", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://github.com/jacklishufan/MobileWorld"}], "id": "github:jacklishufan/mobileworld", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-16T06:40:51Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/jacklishufan/MobileWorld"}], "name": "MobileWorldBench", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://github.com/jacklishufan/MobileWorld", "target_id": "arxiv:2512.14014", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Benchmark of semantic world modeling for mobile agents, with question-answering tasks and GPT-judged generation tasks, plus training data built on AitW and AndroidControl screens.", "topics": ["evaluation", "mobile-navigation"], "updated_at": null, "url": "https://github.com/jacklishufan/MobileWorld"}
{"aliases": [], "authors": [], "details": {"license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/kwai/MobileForge/main/LICENSE", "https://raw.githubusercontent.com/kwai/MobileForge/main/README.md"], "reason": "The complete root LICENSE declares Apache-2.0 for repository code. Linked data and model weights, and third-party dependencies, retain separate licensing requirements."}}, "repository_id": 1278021888}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-20T03:55:04.230792+00:00", "role": "primary", "sha256": "f78f58a6e3b8dd2ae3e8c49a15473782ae258ecd70719f7eeddfa43a10441adf", "supports": ["name", "kind", "summary", "topics", "scope", "relations", "notes", "environments", "licenses.code"], "url": "https://raw.githubusercontent.com/kwai/MobileForge/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T03:55:29.533431+00:00", "role": "primary", "sha256": "58187fe25d8398ef2ae31de02debd4bc3b932ff1925db86a87f5de65b016aed1", "supports": ["summary", "environments", "topics", "scope", "notes"], "url": "https://raw.githubusercontent.com/kwai/MobileForge/main/training/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T03:55:07.420029+00:00", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code", "notes"], "url": "https://raw.githubusercontent.com/kwai/MobileForge/main/LICENSE"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-19T19:10:26.954787+00:00", "role": "primary", "sha256": "0ae4477b885b0915e43874399c2a6b91f7d07954697370204550df931f7db82c", "supports": ["details.repository_id"], "url": "https://api.github.com/search/repositories?q=topic%3Agui-agent+is%3Apublic+fork%3Afalse+created%3A2008-01-01..2026-10-18&per_page=100&page=1&sort=updated&order=asc"}], "id": "github:kwai/mobileforge", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-20T03:55:04.230792+00:00", "licenses": {"code": {"basis": "Complete repository root Apache License 2.0 text; code declaration only, not linked datasets or weights.", "declared": "Apache-2.0", "retrieved_at": "2026-10-20T03:55:07.420029+00:00", "url": "https://raw.githubusercontent.com/kwai/MobileForge/main/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/kwai/MobileForge"}], "name": "MobileForge", "notes": "The root README describes MobileGym exploration/feedback and HiFPO optimization. The training README limits its public training path to the Qwen3-VL-8B experiment. Linked model and dataset collections, executable source completeness and benchmark results were not independently verified; the repository code license is not a model or dataset license.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/kwai/MobileForge/main/README.md", "target_id": "arxiv:2606.19930", "type": "introduced_by"}], "review_status": "curated", "scope": "core", "summary": "Android GUI-agent adaptation framework combining app exploration, generated curricula and rollout feedback with hint-conditioned step-level GRPO; the documented public training path targets Qwen3-VL-8B.", "topics": ["mobile-navigation", "data-generation", "reinforcement-learning", "evaluation"], "updated_at": null, "url": "https://github.com/kwai/MobileForge"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:02Z", "role": "primary", "sha256": "9b4b945f4514d261373ec08d4c3e4e86b6623f95f95b9469bec2b8e7e93d9807", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/LaoKuiZe/AppAgent-Pro/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:03Z", "role": "primary", "sha256": "f13a0d1aaaec0f7e32f034197b31b2bc0537685aff11af653381454288c75794", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/LaoKuiZe/AppAgent-Pro/HEAD/LICENSE"}], "id": "github:laokuize/appagent-pro", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T06:36:02Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T06:42:03Z", "url": "https://raw.githubusercontent.com/LaoKuiZe/AppAgent-Pro/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/LaoKuiZe/AppAgent-Pro"}], "name": "AppAgent Pro", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/LaoKuiZe/AppAgent-Pro/HEAD/README.md", "target_id": "arxiv:2508.18689", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Proactive Android agent built on AppAgent that uses GPT-4o to decide whether YouTube or Amazon content would help, operates those apps over ADB, and merges what it finds into its answer.", "topics": ["mobile-navigation"], "updated_at": null, "url": "https://github.com/LaoKuiZe/AppAgent-Pro"}
{"aliases": [], "authors": [], "details": {}, "environments": ["unspecified"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:59:56Z", "role": "primary", "sha256": "95184255b6ec021aac8ca062b944f3ed76d1e01405e5771d9e31368021523eec", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "notes"], "url": "https://raw.githubusercontent.com/lgy0404/LearnAct/HEAD/README.md"}], "id": "github:lgy0404/learnact", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-18T10:59:56Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/lgy0404/LearnAct"}], "name": "LearnAct", "notes": "At the retained README snapshot, LearnGUI-Online code and the real-world deployment implementation were marked coming soon. The mobile operating system is not established by the reviewed release instructions; no code was executed.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/lgy0404/LearnAct/HEAD/README.md", "target_id": "arxiv:2504.13805", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Released inference and evaluation code for demonstration-conditioned mobile GUI agents on LearnGUI-Offline. The repository describes a multi-agent adaptation method and links the LearnGUI demonstrations.", "topics": ["mobile-navigation", "imitation-learning", "evaluation"], "updated_at": null, "url": "https://github.com/lgy0404/LearnAct"}
{"aliases": [], "authors": [], "details": {"availability": "Public graph/task manifests, evaluation source and ungated screenshot archive manifest.", "benchmark_protocol": {"actions": ["mobile GUI operations along graph transitions"], "counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/README.md", "population": "reported ColorBench benchmark", "qualifier": "exact", "unit": "tasks", "value": 175}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/README.md", "population": "reported ColorBench benchmark", "qualifier": "exact", "unit": "cross-app tasks", "value": 101}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/README.md", "population": "reported ColorBench benchmark", "qualifier": "exact", "unit": "single-app tasks", "value": 74}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/README.md", "population": "reported ColorBench benchmark", "qualifier": "exact", "unit": "mobile applications", "value": 21}], "evaluation": "The publisher reports success rate, completion rate and atomic-capability diagnostics using graph-based evaluation.", "evidence_urls": ["https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/README.md"], "focus": ["long-horizon mobile task completion", "multi-path graph interaction"], "notes": "The interaction environment replays graph states rather than running real user accounts. The 101 and 74 subsets partition the reported 175 tasks; do not add the three counts.", "observations": ["mobile screenshots represented as graph states"], "setting": "interactive"}, "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/LICENSE"], "reason": "Repository source LICENSE."}, "data": {"evidence_urls": ["https://huggingface.co/datasets/Norsheep/ColorBench/raw/main/README.md"], "reason": "Publisher metadata for the separately hosted screenshot archive; underlying third-party content retains applicable rights."}}, "repository_revision": "1f26a84230d26f99d84eab97d05032582b39018e"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:16Z", "role": "primary", "sha256": "5c0190fffb68b91c1855a408f6a5e252871d94000b95fa258504a3c100600cec", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:16Z", "role": "primary", "sha256": "2f6940503cc0d6cb97bdf142d6b8c6ab116de82227f2fa6d97fd56d7e5aebec0", "supports": ["identity"], "url": "https://api.github.com/repos/MadeAgents/ColorBench"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:22:54Z", "role": "primary", "sha256": "6a00c093a6794ec4a172d30b70fdabc17400584a9e25a157a47a7661dbdd20fa", "supports": ["release_status", "details.repository_revision"], "url": "https://api.github.com/repos/MadeAgents/ColorBench/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:06Z", "role": "primary", "sha256": "c0c3286b5150e128e55034ba0393ef85f7fcf73e4b73f4276389a04c9bcec919", "supports": ["identity", "release_status"], "url": "https://huggingface.co/api/datasets/Norsheep/ColorBench"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:06Z", "role": "primary", "sha256": "4bcf87ecfbbb8e07a01b21415a970c8b53a5283bf6872b657040d3f45c9241f7", "supports": ["licenses.data"], "url": "https://huggingface.co/datasets/Norsheep/ColorBench/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:22:54Z", "role": "primary", "sha256": "130976c026bcafa9dcc479697fe6595dbefb73cdb375fc47b8478acc16e6ea73", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/LICENSE"}], "id": "github:madeagents/colorbench", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-17T11:18:16Z", "licenses": {"code": {"basis": "Repository source LICENSE.", "declared": "Apache-2.0", "retrieved_at": "2026-10-17T11:22:54Z", "url": "https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/LICENSE"}, "data": {"basis": "Publisher metadata for the separately hosted screenshot archive; underlying third-party content retains applicable rights.", "declared": "apache-2.0", "retrieved_at": "2026-10-17T11:23:06Z", "url": "https://huggingface.co/datasets/Norsheep/ColorBench/raw/main/README.md"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/MadeAgents/ColorBench"}], "name": "ColorBench", "notes": "The source tree contains graph and task JSON files plus construction/evaluation code; the linked ungated Hub provides the screenshot archive. The environment is static but interactive and graph-based, not a live-device deployment. Counts are publisher-reported task/app inventories. Apache-2.0 declarations for repository code and the Hub dataset are separately retained; third-party application visuals are not granted additional rights by this catalog.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/MadeAgents/ColorBench/HEAD/README.md", "target_id": "arxiv:2510.14621", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A graph-based mobile GUI benchmark that evaluates long tasks through screenshot states and multiple valid or erroneous transitions, including reflection, replanning and backtracking.", "topics": ["evaluation", "mobile-navigation", "long-horizon", "cross-app"], "updated_at": null, "url": "https://github.com/MadeAgents/ColorBench"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:03Z", "role": "primary", "sha256": "101595fa1f62d30271b0560f8aaa54286d7f6fc006e2aa9d8b73086583b27656", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/MadeAgents/mobile-use/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:04Z", "role": "primary", "sha256": "806f2d2c84a015f221f39691c95f7bdd0ff18f134e563d1155caa787076653fe", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/MadeAgents/mobile-use/HEAD/LICENSE"}], "id": "github:madeagents/mobile-use", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T06:36:03Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T06:42:04Z", "url": "https://raw.githubusercontent.com/MadeAgents/mobile-use/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/MadeAgents/mobile-use"}], "name": "Mobile Use", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/MadeAgents/mobile-use/HEAD/README.md", "target_id": "arxiv:2507.16853", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Android GUI agent that operates real phones through ADB with hierarchical reflection and a multi-agent framework, run from a web interface or Python and evaluated on AndroidWorld and AndroidLab.", "topics": ["mobile-navigation"], "updated_at": null, "url": "https://github.com/MadeAgents/mobile-use"}
{"aliases": [], "authors": [], "details": {"availability": "Public training and evaluation source; trained checkpoints are generated by the documented workflow.", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/microsoft/GUI-Agent-RL/HEAD/LICENSE"], "reason": "Repository LICENSE grants MIT for code; linked training imagery and pretrained model licenses remain separate."}}, "repository_revision": "6d2381ef549d980452a828471221a2ce8023bf41"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:12:14Z", "role": "primary", "sha256": "d21a1ae4359296c0f3034ac655888dce43448d10afe0b1909d6b6520678c2526", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details"], "url": "https://raw.githubusercontent.com/microsoft/GUI-Agent-RL/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:12:13Z", "role": "primary", "sha256": "791c6e56e62ce5e803a4ba313557bac0a39dfeba27499a3865ad444a860b426a", "supports": ["identity"], "url": "https://api.github.com/repos/microsoft/GUI-Agent-RL"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:06Z", "role": "primary", "sha256": "5b799a5bdae78ff50652c0b464b6cad12d9dda265d4752e5d5f9eab65e9d5c6f", "supports": ["release_status"], "url": "https://api.github.com/repos/microsoft/GUI-Agent-RL/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:06Z", "role": "primary", "sha256": "c2cfccb812fe482101a8f04597dfc5a9991a6b2748266c47ac91b6a5aae15383", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/microsoft/GUI-Agent-RL/HEAD/LICENSE"}], "id": "github:microsoft/gui-agent-rl", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-17T09:12:14Z", "licenses": {"code": {"basis": "Repository LICENSE grants MIT for code; linked training imagery and pretrained model licenses remain separate.", "declared": "MIT", "retrieved_at": "2026-10-17T09:14:06Z", "url": "https://raw.githubusercontent.com/microsoft/GUI-Agent-RL/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/microsoft/GUI-Agent-RL"}], "name": "VEM GUI-Agent-RL", "notes": "The public tree includes critic-training configurations, policy training and offline/online evaluation scripts. The README obtains base models and AITW imagery separately, then instructs users to train critic and policy checkpoints locally; this entry does not claim that VEM-trained weights are released. MIT applies to repository code only.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/microsoft/GUI-Agent-RL/HEAD/README.md", "target_id": "arxiv:2502.18906", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Training code that learns a value environment model from offline Android interaction data and uses its frozen value estimates to guide GUI policy optimization.", "topics": ["reinforcement-learning", "reward-models", "mobile-navigation"], "updated_at": null, "url": "https://github.com/microsoft/GUI-Agent-RL"}
{"aliases": [], "authors": [], "details": {}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T17:18:21Z", "role": "primary", "sha256": "8aaf8feff6e1d5a533c01afd8afc0cfc0700f0c1c73ba47949b56c11fb8ab5be", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/microsoft/Magma/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-17T17:18:56Z", "role": "primary", "sha256": "c2cfccb812fe482101a8f04597dfc5a9991a6b2748266c47ac91b6a5aae15383", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/microsoft/Magma/HEAD/LICENSE"}], "id": "github:microsoft/magma", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-17T17:18:21Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-17T17:18:56Z", "url": "https://raw.githubusercontent.com/microsoft/Magma/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/microsoft/Magma"}], "name": "Magma", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Microsoft foundation model for multimodal agents, pretrained with Set-of-Mark and Trace-of-Mark objectives on UI, robotics and video data and fine-tunable for web and mobile UI navigation.", "topics": ["grounding", "planning", "mobile-navigation"], "updated_at": null, "url": "https://github.com/microsoft/Magma"}
{"aliases": [], "authors": [], "details": {"availability": "Published source; official release metadata inspected", "release_tag": "1.0.11"}, "environments": ["android", "ios"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "bc24fa665d1a49fa806d58ec569d93e134058e0cb1a7bc9324339ba0e35ff107", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/mobile-next/mobile-mcp/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "80e8ad254f71f5c80b91a6b80edd09f96116ef4967ae4e6832e5960357f7b99a", "supports": ["identity"], "url": "https://api.github.com/repos/mobile-next/mobile-mcp"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "49684448428c28afd4bf191f695c3d45fbe46910fa93951d2a02f6b8afcf9f16", "supports": ["release_status"], "url": "https://api.github.com/repos/mobile-next/mobile-mcp/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:00:57Z", "role": "primary", "sha256": "43a5c02407afe86b6f1fedb4299f28420778ce21825cd87516deafe05507a7bc", "supports": ["release_status"], "url": "https://api.github.com/repos/mobile-next/mobile-mcp/releases/latest"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:00:58Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/mobile-next/mobile-mcp/HEAD/LICENSE"}, {"method": "license_header", "retrieved_at": "2026-10-17T04:00:58Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/mobile-next/mobile-mcp/HEAD/LICENSE"}], "id": "github:mobile-next/mobile-mcp", "identifiers": {}, "kind": "tool", "last_verified_at": "2026-10-17T03:59:53Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-17T04:00:58Z", "url": "https://raw.githubusercontent.com/mobile-next/mobile-mcp/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/mobile-next/mobile-mcp"}], "name": "Mobile Next MCP", "notes": "Source and release 1.0.11 are public. The README specifies iOS and Android device setup and supports local devices as well as a separate cloud offering. Apache-2.0 is declared for this code; no cloud-service pricing or permissions are inferred.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "An MCP server exposing mobile accessibility snapshots, screenshots and device interactions across real devices, simulators and emulators.", "topics": ["mobile-navigation", "tool-integration", "automation"], "updated_at": null, "url": "https://github.com/mobile-next/mobile-mcp"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:35:58Z", "role": "primary", "sha256": "e1d75e8a196f19af6050c53694383f069561244c810ca259c5f8075ee91f72b1", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/MobileAgentBench/mobile-agent-bench/HEAD/README.md"}], "id": "github:mobileagentbench/mobile-agent-bench", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-16T06:35:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/MobileAgentBench/mobile-agent-bench"}], "name": "MobileAgentBench", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Automated benchmark for mobile LLM agents whose default tasks use ten Simple Mobile Tools Android apps, installed as a Python library that detects task completion.", "topics": ["evaluation", "mobile-navigation"], "updated_at": null, "url": "https://github.com/MobileAgentBench/mobile-agent-bench"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:02Z", "role": "primary", "sha256": "4a79eb2e14b6da67ded536c127d41f865d5b43620d60d0d950d291c8956564fc", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid/HEAD/README.md"}], "id": "github:mobilellm/autodroid", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T06:36:02Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/MobileLLM/AutoDroid"}], "name": "AutoDroid", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid/HEAD/README.md", "target_id": "arxiv:2308.15272", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "LLM-powered Android task automation built on DroidBot, released with DroidTask, a dataset of per-app screenshots, view hierarchies, exploration records and ground-truth task files.", "topics": ["mobile-navigation"], "updated_at": null, "url": "https://github.com/MobileLLM/AutoDroid"}
{"aliases": [], "authors": [], "details": {"availability": "Public source and minimal-experiment documentation are released; default README path is absent.", "repository_revision": "b1a02a52a6c94b96f63016ac12d3a4ab6a410b8e"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:58Z", "role": "primary", "sha256": "74508100843f8db6db6bb151e77ac1cc604a6b7ebd16d3225266d73434465136", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details"], "url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/README_minimal.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:12:10Z", "role": "primary", "sha256": "f349963f2ea3f7b81f1c04ee875654382929b1f93d99d0168d6e086155f41d72", "supports": ["identity"], "url": "https://api.github.com/repos/MobileLLM/AutoDroid-V2"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:03Z", "role": "primary", "sha256": "70354b856b75bc4a2aca0a7274321637039ec5d083523ca2f677cd11d475b386", "supports": ["release_status", "licenses.code"], "url": "https://api.github.com/repos/MobileLLM/AutoDroid-V2/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:58Z", "role": "primary", "sha256": "8ba37983a2c2da53d96a52696c07e4bdbea4e987a1a07b557935d614c3be46d2", "supports": ["summary", "details", "relations"], "url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/step_3_training/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:58Z", "role": "primary", "sha256": "cfed016e038d09ce7c9e829273fffa4a6c618bf8e9043312e4690fbe1f40d247", "supports": ["environments", "details"], "url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/step_0_installation/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:58Z", "role": "primary", "sha256": "f5534771f68770ed2e45daf94fbf80304ba2904387571c34c5d80a152bef0a00", "supports": ["summary"], "url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/step_1_doc_generation/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:59Z", "role": "primary", "sha256": "0564f566fde97360496bea4a6eb023c4c84e03cdfdf5201c5b27235c36e32b18", "supports": ["summary", "details"], "url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/step_4_accuracy_validation/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "github:mobilellm/autodroid-v2", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-17T09:14:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/MobileLLM/AutoDroid-V2"}], "name": "AutoDroid V2", "notes": "The repository uses README_minimal.md rather than README.md and includes a documented App Launcher experiment, training setup and DroidTask/LlamaTouch evaluation scripts. Its supplied emulator setup targets x86_64 Linux and Android API 31. No repository-level code license was found; code, APK, data and weight terms are not inferred from one another. Dependencies, external evaluation files and model service are still required; no software was run.", "published_at": null, "relations": [{"evidence_url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending", "target_id": "arxiv:2412.18116", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "An Android automation implementation that builds app documentation from exploration traces and evaluates language-model-generated execution code in emulator workflows.", "topics": ["mobile-navigation", "tool-integration", "data-generation"], "updated_at": null, "url": "https://github.com/MobileLLM/AutoDroid-V2"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:00Z", "role": "primary", "sha256": "2cf79e21b5438bf6a2e6bd450ba8c4d86404560dfb61836f7e300112ce74a59d", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/OpenBMB/AgentCPM-GUI/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:01Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/OpenBMB/AgentCPM-GUI/HEAD/LICENSE"}], "id": "github:openbmb/agentcpm-gui", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-16T06:36:00Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T06:42:01Z", "url": "https://raw.githubusercontent.com/OpenBMB/AgentCPM-GUI/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/OpenBMB/AgentCPM-GUI"}], "name": "AgentCPM-GUI", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/OpenBMB/AgentCPM-GUI/HEAD/README.md", "target_id": "arxiv:2506.01391", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "8B on-device smartphone agent built on MiniCPM-V that operates Chinese and English apps from screenshots, trained with reinforcement fine-tuning and a compact JSON action space.", "topics": ["grounding", "mobile-navigation"], "updated_at": null, "url": "https://github.com/OpenBMB/AgentCPM-GUI"}
{"aliases": [], "authors": [], "details": {"availability": "Public Android executor, agents, prompts and setup documentation.", "license_review": {"code": {"evidence_urls": ["https://api.github.com/repos/OpenDFM/MobA/git/trees/main?recursive=1"], "reason": "No repository source-license declaration established from the current public tree."}}, "repository_revision": "05cd237d80fcd23ad0dd6096cdb144117ecb3471"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:53Z", "role": "primary", "sha256": "49c096e5ee6a87205497d693b5248817ea98cad0f7e5254793660007ef4292f7", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations"], "url": "https://raw.githubusercontent.com/OpenDFM/MobA/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:53Z", "role": "primary", "sha256": "0ecd1833a1b6840441769e1cc26a55268f2de7beb61bc3e783a851dd7cff45f1", "supports": ["identity"], "url": "https://api.github.com/repos/OpenDFM/MobA"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:04Z", "role": "primary", "sha256": "302f324fce2884c5948cf62c75f2f839cd40c301faff6ccf4b6eb5dd29f953a3", "supports": ["release_status", "details.repository_revision", "licenses.code"], "url": "https://api.github.com/repos/OpenDFM/MobA/git/trees/main?recursive=1"}], "id": "github:opendfm/moba", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-17T12:30:53Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/OpenDFM/MobA"}], "name": "MobA", "notes": "The repository releases a configurable Python executor and Android ADB integration; its setup documents a Windows host, but the controlled interface is Android. The source is marked under continuing development and requires external model credentials. The inspected repository has no license file; the separately hosted MobBench data declaration is not transferred to this code.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/OpenDFM/MobA/HEAD/README.md", "target_id": "arxiv:2410.13757", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "An Android agent that combines global task planning and memory with a local action executor, using reflection to revise mobile interaction steps.", "topics": ["mobile-navigation", "memory", "planning", "self-reflection"], "updated_at": null, "url": "https://github.com/OpenDFM/MobA"}
{"aliases": [], "authors": [], "details": {"benchmark_protocol": {"actions": ["GUI gestures", "foreground-app tool calls in hybrid mode"], "counts": [{"basis": "computed", "evidence_url": "https://raw.githubusercontent.com/OpenMobile2/MobileGym-plusplus/HEAD/bench_env/benchmark/official.json", "population": "official.json", "qualifier": "exact", "unit": "task definitions", "value": 215}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/OpenMobile2/MobileGym-plusplus/HEAD/README.md", "population": "complete simulator installation", "qualifier": "exact", "unit": "simulated clients", "value": 63}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/OpenMobile2/MobileGym-plusplus/HEAD/README.md", "population": "new clients in this release", "qualifier": "exact", "unit": "simulated clients", "value": 35}], "evaluation": "Programmatic checkers inspect changes in application state; both modes share task definitions and initial states.", "evidence_urls": ["https://raw.githubusercontent.com/OpenMobile2/MobileGym-plusplus/HEAD/README.md", "https://raw.githubusercontent.com/OpenMobile2/MobileGym-plusplus/HEAD/bench_env/benchmark/official.json"], "focus": ["task completion", "cross-application workflows", "GUI and app-native tool comparison"], "notes": "The task count was checked against unique task_id values in the published manifest. The 35 new clients are a subset of 63 total clients. This simulator runs in a browser; Android-emulator apps are a separate part of OpenMobile-2.", "observations": ["screenshots"], "setting": "interactive"}}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:10Z", "role": "primary", "sha256": "d9f850ec196e715650e679cb81515adaa64ddc5a60a882bfe97b0f6a098ddc83", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/OpenMobile2/MobileGym-plusplus/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:46:06Z", "role": "primary", "sha256": "9b385e9f6aa2f7169f616a76887df3b76df605cb2bea071d99ee7ca3f9b659cc", "supports": ["relations"], "url": "https://os-copilot.github.io/OpenMobile2-Home/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:50:11Z", "role": "primary", "sha256": "35c1641b349201c68917fbe4c4036814487678e9588d9b1c903af26917800316", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/OpenMobile2/MobileGym-plusplus/HEAD/bench_env/benchmark/official.json"}, {"method": "license_header", "retrieved_at": "2026-10-17T01:52:51Z", "role": "primary", "sha256": "7618cd7de039c264759ca8ca0b9130c6de63a4536dcf436baedd4cfbf639073e", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/OpenMobile2/MobileGym-plusplus/HEAD/LICENSE"}], "id": "github:openmobile2/mobilegym-plusplus", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-17T01:48:10Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-17T01:52:51Z", "url": "https://raw.githubusercontent.com/OpenMobile2/MobileGym-plusplus/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/OpenMobile2/MobileGym-plusplus"}], "name": "MobileGym++ / MobileGym++ Bench", "notes": "These clients simulate named commercial applications and are not those commercial products. The code and simulator data have distinct license files. No benchmark run was performed. The README describes a phone that runs in the browser, and the Android-emulator playground is a separate OpenMobile2 release, so the platform facet is web rather than a mobile operating system.", "published_at": null, "relations": [{"evidence_url": "https://os-copilot.github.io/OpenMobile2-Home/", "target_id": "arxiv:2610.14157", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Browser-rendered mobile simulation with resettable app state and a shared task suite for GUI-only and GUI-plus-tool agents.", "topics": ["mobile-navigation", "evaluation", "cross-app", "tool-integration"], "updated_at": null, "url": "https://github.com/OpenMobile2/MobileGym-plusplus"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android", "web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:10Z", "role": "primary", "sha256": "485279038266d9454df75e27a80a0a0d71c24e90700126d2dcfa0da921b1273d", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/OpenMobile2/OpenMobile2-Code/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-17T01:52:51Z", "role": "primary", "sha256": "b09fcaf4fbc265223c2479c410beef2b98c5e687c78ecedf3452aa12ffc465f1", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/OpenMobile2/OpenMobile2-Code/HEAD/LICENSE"}], "id": "github:openmobile2/openmobile2-code", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-17T01:48:10Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-17T01:52:51Z", "url": "https://raw.githubusercontent.com/OpenMobile2/OpenMobile2-Code/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/OpenMobile2/OpenMobile2-Code"}], "name": "OpenMobile-2 code", "notes": "The README marks evaluation code, checkpoints, environments, and data as released; data-construction scripts and other resources remain pending. Each benchmark runtime is started separately. Code terms do not establish dataset permissions.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/OpenMobile2/OpenMobile2-Code/HEAD/README.md", "target_id": "arxiv:2610.14157", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Evaluation adapters and training guidance for OpenMobile-2 across Android emulators and browser-rendered mobile simulation.", "topics": ["mobile-navigation", "tool-integration", "evaluation"], "updated_at": null, "url": "https://github.com/OpenMobile2/OpenMobile2-Code"}
{"aliases": [], "authors": [], "details": {"availability": "Public simulator, task/judge and online-RL source, plus official release metadata for the companion data archive.", "benchmark_protocol": {"actions": ["tap", "type", "swipe", "back", "home", "drag", "complete"], "counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/README.md", "population": "publisher benchmark overview", "qualifier": "exact", "unit": "task templates", "value": 416}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/README.md", "population": "publisher benchmark overview", "qualifier": "exact", "unit": "simulated apps", "value": 28}, {"basis": "computed", "evidence_url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/bench_env/splits/train.txt", "population": "bench_env/splits/train.txt", "qualifier": "exact", "unit": "task identifiers", "value": 160}, {"basis": "computed", "evidence_url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/bench_env/splits/test.txt", "population": "bench_env/splits/test.txt", "qualifier": "exact", "unit": "task identifiers", "value": 256}], "evaluation": "Deterministic task judges inspect state changes; reported metrics distinguish success, progress, false completion and unexpected side effects.", "evidence_urls": ["https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/README.md", "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/bench_env/splits/train.txt", "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/bench_env/splits/test.txt"], "focus": ["mobile GUI task completion in simulation", "state verification and parallel training"], "notes": "The split-ID inventory is not a count of sampled trajectories, live Android apps or real user accounts. Extra runtime/data dependencies and third-party content terms remain distinct.", "observations": ["simulated mobile screenshots", "structured simulator state for judges"], "setting": "interactive"}, "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/LICENSE"], "reason": "Core source LICENSE; mobilegym-rl has a separate matching Apache-2.0 license and retains vendored notices."}, "data": {"evidence_urls": ["https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/LICENSE-DATA"], "reason": "Limited to maintainers’ dataset compilation/curation and authored synthetic content; third-party user content remains subject to platform terms and its authors’ rights."}}, "release_tag": "v0.1.0", "repository_revision": "5fbd3f34be0e9780ae4b1e9d5089963ddbd05d38"}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:19Z", "role": "primary", "sha256": "815294dd2aa4bf8264978c3bfedee85a3a2c835c511860c732314a4c282a974a", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:18Z", "role": "primary", "sha256": "48df04a2fbf479f956d5c7f22d7006c22f591b8857cab8a1d64c196349045495", "supports": ["identity"], "url": "https://api.github.com/repos/Purewhiter/mobilegym"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:22:56Z", "role": "primary", "sha256": "68f1fa16c0999079bccc3aa1b6c3c22b72b570a5b971837c5026ea5408853375", "supports": ["release_status", "details.repository_revision"], "url": "https://api.github.com/repos/Purewhiter/mobilegym/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:08Z", "role": "primary", "sha256": "cb1057b0a0a2ef7ab781414c168bb41f0f3da88afc042ce266d6063493561bde", "supports": ["release_status", "details.release_tag"], "url": "https://api.github.com/repos/Purewhiter/mobilegym/releases/tags/v0.1.0"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:09Z", "role": "primary", "sha256": "ad0c86a6cdde2caba8bd1f98b121803817d93718319a863b0b833da2760c23aa", "supports": ["release_status"], "url": "https://api.github.com/repos/Purewhiter/mobilegym/releases/tags/data-v0.1.0"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:22:59Z", "role": "primary", "sha256": "7618cd7de039c264759ca8ca0b9130c6de63a4536dcf436baedd4cfbf639073e", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/LICENSE"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:27:50Z", "role": "primary", "sha256": "58d1e17ffe5109a7ae296caafcadfdbe6a7d176f0bc4ab01e12a689b0499d8bd", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/mobilegym-rl/LICENSE"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:22:59Z", "role": "primary", "sha256": "e222fa518c5003d425ee9b371e987c95ba10e52b54fea078571254ae6a8eaf23", "supports": ["licenses.data", "notes"], "url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/LICENSE-DATA"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:27:49Z", "role": "primary", "sha256": "0ecef460fecfd8aa91dcbb2cd4cca17b033f620f85a50d7f0b598ed19a27c0eb", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/bench_env/splits/train.txt"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:27:48Z", "role": "primary", "sha256": "a3d485015d480f4f1ebbd12dbbf02c25c0aa667d1afcf5f6fa35f0263a82c567", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/bench_env/splits/test.txt"}], "id": "github:purewhiter/mobilegym", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-17T11:18:19Z", "licenses": {"code": {"basis": "Core source LICENSE; mobilegym-rl has a separate matching Apache-2.0 license and retains vendored notices.", "declared": "Apache-2.0", "retrieved_at": "2026-10-17T11:22:59Z", "url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/LICENSE"}, "data": {"basis": "Limited to maintainers’ dataset compilation/curation and authored synthetic content; third-party user content remains subject to platform terms and its authors’ rights.", "declared": "CC-BY-NC-4.0", "retrieved_at": "2026-10-17T11:22:59Z", "url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/LICENSE-DATA"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/Purewhiter/mobilegym"}], "name": "MobileGym", "notes": "The inspected code release is v0.1.0, with a separately listed data-v0.1.0 archive. The interaction target is a browser-hosted Android-like simulation; real-device transfer results are separate publisher-reported experiments. Source split manifests contain 160 training IDs and 256 test IDs with no duplicates or overlap. Platform/training code declares Apache-2.0. LICENSE-DATA applies CC-BY-NC-4.0 only to maintainer-created compilation, curation and synthetic content, and explicitly leaves third-party UGC/API terms and author rights separate. No runtime, archive or model was executed/downloaded.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/Purewhiter/mobilegym/HEAD/README.md", "target_id": "arxiv:2605.26114", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A browser-hosted mobile-app simulator with programmable state, parameterized tasks and deterministic state-checking judges for parallel GUI-agent evaluation and online reinforcement learning.", "topics": ["evaluation", "mobile-navigation", "reinforcement-learning", "sandbox"], "updated_at": null, "url": "https://github.com/Purewhiter/mobilegym"}
{"aliases": [], "authors": [], "details": {"license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/RadishSoftware/mobster/738cecdd3eacb9df88d48efb9efa53507bb4aeb4/LICENSE"], "reason": "Complete root MIT license text inspected at the pinned commit. Applies to repository software; data, weights, external WebDriverAgent code and separately distributed products do not inherit this declaration."}}, "repository_revision": "738cecdd3eacb9df88d48efb9efa53507bb4aeb4"}, "environments": ["ios"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:57:18.994340+00:00", "role": "primary", "sha256": "dfffdc4b5850ed6bfe0bcfe705fa5918d61420f8c80df2e38f61b7d1fb3819ec", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://raw.githubusercontent.com/RadishSoftware/mobster/738cecdd3eacb9df88d48efb9efa53507bb4aeb4/README.md"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-20T11:06:00.276978+00:00", "role": "primary", "sha256": "01f97a863952373bd10a1f849d79706344be63f5774fe7e0cfe9ba774e41d213", "supports": ["identity"], "url": "https://api.github.com/search/repositories?q=topic%3Amobile-agent+is%3Apublic+fork%3Afalse+created%3A2008-01-01..2026-10-20&per_page=100&page=1&sort=updated&order=asc"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:54:17.260430+00:00", "role": "primary", "sha256": "fde31e2fdae142655f09fa14fb3114bf39a22cc1ff7994204a66622f5cbfe2c7", "supports": ["identity", "details.repository_revision"], "url": "https://api.github.com/repos/RadishSoftware/mobster/commits/main"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:56:37.457839+00:00", "role": "primary", "sha256": "8c2b9647b33a93b1a33e9256307e09b0f3e6aa62608019defa6dcdc5d7bff3dc", "supports": ["identity", "details.repository_revision", "notes"], "url": "https://api.github.com/repos/RadishSoftware/mobster/git/trees/81f2c1990c07a3aaf001a5c3eb4f37a457f0fb3d?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:57:25.539870+00:00", "role": "primary", "sha256": "f9ad743798f16491100ea692069e346f82bbdb5a5df91e4e01c1d6168f2513cf", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/RadishSoftware/mobster/738cecdd3eacb9df88d48efb9efa53507bb4aeb4/LICENSE"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T12:05:06.711971+00:00", "role": "primary", "sha256": "4296a186cc2c00b9de93ababae490dc99cba596d858eff195e40283d58d73a0a", "supports": ["summary", "environments", "topics", "scope", "notes"], "url": "https://raw.githubusercontent.com/RadishSoftware/mobster/738cecdd3eacb9df88d48efb9efa53507bb4aeb4/mobile_agent/drivers.py"}], "id": "github:radishsoftware/mobster", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-20T11:57:18.994340+00:00", "licenses": {"code": {"basis": "Complete root MIT license text inspected at the pinned commit. Applies to repository software; data, weights, external WebDriverAgent code and separately distributed products do not inherit this declaration.", "declared": "MIT", "retrieved_at": "2026-10-20T11:57:25.539870+00:00", "url": "https://raw.githubusercontent.com/RadishSoftware/mobster/738cecdd3eacb9df88d48efb9efa53507bb4aeb4/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/RadishSoftware/mobster"}], "name": "Mobster engine", "notes": "This entry covers the published engine, not the separate Mobster for Mac product. The documented reference example requires an already-serving WebDriverAgent runner for an iPhone and a model-service key; it performs a fixed read-only Settings task and declines approvals. The repository lists benchmark/evaluation tooling, but dated simulator subsets, real-device trials and earlier engine results are different evaluation populations. The README explicitly places several product modules outside this repository. Source inspection confirms WDA dispatch paths, not task success, security guarantees or reproducible performance; no phone, simulator, model or benchmark was run. MIT applies to the inspected repository software, not automatically to external WDA code, images or other data.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "iOS agent engine organized around an observe, decide, verify and act loop, using WebDriverAgent screen state and phone actions such as taps, typing, swipes and app switches.", "topics": ["mobile-navigation", "evaluation"], "updated_at": null, "url": "https://github.com/RadishSoftware/mobster"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android", "ios", "cross-platform"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:59:55Z", "role": "primary", "sha256": "cb3d2329571a80b6edeab98c04f8b63c7f4e976929788d6a8283238b0b7fdadc", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "notes"], "url": "https://raw.githubusercontent.com/runamu/monday/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-18T11:03:47Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/runamu/monday/HEAD/LICENSE"}], "id": "github:runamu/monday", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-18T10:59:55Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-18T11:03:47Z", "url": "https://raw.githubusercontent.com/runamu/monday/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/runamu/monday"}], "name": "MONDAY", "notes": "The retained README marks release of the full data-generation pipeline, training scripts, and model checkpoints as pending. Linked video content and datasets remain subject to their original licenses; the repository code license does not establish a blanket data or weights license.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/runamu/monday/HEAD/README.md", "target_id": "arxiv:2505.12632", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Cross-platform mobile GUI trajectory dataset derived from instructional videos, with released data-processing helpers and example evaluation code for Android and iOS data.", "topics": ["data-generation", "mobile-navigation", "video"], "updated_at": null, "url": "https://github.com/runamu/monday"}
{"aliases": [], "authors": [], "details": {"license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/solplum/yunkai/2aa6cd83165bfc201b0128c250e80892895d63af/LICENSE"], "reason": "Complete root MIT license text inspected at the pinned commit. Repository software only; data, weights and third-party assets retain separate terms."}}, "repository_revision": "2aa6cd83165bfc201b0128c250e80892895d63af"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:57:12.431753+00:00", "role": "primary", "sha256": "eea31b35aa0b55c97f8ccda3438382ad49d2453671b49bb817efb5bc3384e900", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://raw.githubusercontent.com/solplum/yunkai/2aa6cd83165bfc201b0128c250e80892895d63af/README.md"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-20T11:06:00.276978+00:00", "role": "primary", "sha256": "01f97a863952373bd10a1f849d79706344be63f5774fe7e0cfe9ba774e41d213", "supports": ["identity"], "url": "https://api.github.com/search/repositories?q=topic%3Amobile-agent+is%3Apublic+fork%3Afalse+created%3A2008-01-01..2026-10-20&per_page=100&page=1&sort=updated&order=asc"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:54:02.419278+00:00", "role": "primary", "sha256": "e2797712132e69cc50fa7ad2ae815a48339f77eebec1e85a5dc0cd75702574f1", "supports": ["identity", "details.repository_revision"], "url": "https://api.github.com/repos/solplum/yunkai/commits/main"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:56:30.226860+00:00", "role": "primary", "sha256": "08f48cb5c15b8d505e76a91d996c656d87765946cc7137bce088e73e6e64cf06", "supports": ["identity", "details.repository_revision", "notes"], "url": "https://api.github.com/repos/solplum/yunkai/git/trees/4ca94f2f7d8f13099ae2c351d9578ed5ef0cb509?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:57:22.238029+00:00", "role": "primary", "sha256": "c39441f92c303832d42f1f153c4442533ac925007e12d70f3199c568a0baac88", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/solplum/yunkai/2aa6cd83165bfc201b0128c250e80892895d63af/LICENSE"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:59:51.424713+00:00", "role": "primary", "sha256": "964aad706676fc7b74e532f8bc441fa766f3ce0ca3e4d0e115c7a90c70656883", "supports": ["summary", "environments", "topics", "scope", "notes"], "url": "https://raw.githubusercontent.com/solplum/yunkai/2aa6cd83165bfc201b0128c250e80892895d63af/yunkai-android/app/src/main/java/com/zhuolin/yunkai/service/screen/ScreenSenseService.kt"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T11:59:54.745065+00:00", "role": "primary", "sha256": "628cc3015999176052a09e3f3bbb8635d87163a9430d98cb6a6a7c09117dfd37", "supports": ["notes"], "url": "https://raw.githubusercontent.com/solplum/yunkai/2aa6cd83165bfc201b0128c250e80892895d63af/yunkai-harmony/entry/src/main/ets/service/tools/M2Tools.ets"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T12:04:53.632582+00:00", "role": "primary", "sha256": "ba8c9b0f4b5cea5ac36a4b49f3cf27e77e5c6beb49022e43c667e359be2c6fca", "supports": ["environments", "notes"], "url": "https://raw.githubusercontent.com/solplum/yunkai/2aa6cd83165bfc201b0128c250e80892895d63af/yunkai-harmony/entry/src/main/ets/service/screen/ScreenSenseExtension.ets"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T12:04:56.914360+00:00", "role": "primary", "sha256": "423a77e1fd57f3e105898f1adfc94c493de5c0de97fae4379f9cf540c89d4640", "supports": ["notes"], "url": "https://raw.githubusercontent.com/solplum/yunkai/2aa6cd83165bfc201b0128c250e80892895d63af/yunkai-harmony/tests/fullflow/drive_harmony.sh"}], "id": "github:solplum/yunkai", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-20T11:57:12.431753+00:00", "licenses": {"code": {"basis": "Complete root MIT license text inspected at the pinned commit. Repository software only; data, weights and third-party assets retain separate terms.", "declared": "MIT", "retrieved_at": "2026-10-20T11:57:22.238029+00:00", "url": "https://raw.githubusercontent.com/solplum/yunkai/2aa6cd83165bfc201b0128c250e80892895d63af/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/solplum/yunkai"}], "name": "Yunkai", "notes": "The Android AccessibilityService contains concrete screen-reading and action paths. The inspected HarmonyOS accessibility extension is a lifecycle/event scaffold with its screen-content probe disabled; HDC appears in an external UI-test driver, so Harmony GUI-control parity is not established by this review. Setup requires a configured OpenAI-compatible model endpoint and API key: local storage does not establish offline inference or a no-transmission guarantee. Documented approval and privacy mechanisms are not independently tested security guarantees. No app, device test or model inference was run.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Android phone assistant combining model-driven tool use with accessibility-tree reading, screenshots, and tap, swipe and text-entry primitives. Its documented interaction flow presents operation plans for user confirmation.", "topics": ["mobile-navigation", "screen-understanding", "human-in-the-loop"], "updated_at": null, "url": "https://github.com/solplum/yunkai"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "462e2b627989a969f7e859e22040a83d38e7c3eac12305d844563b0925f8a787", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/stepfun-ai/gelab-zero/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:01Z", "role": "primary", "sha256": "08095ca875809a84572af7129caef5d4f4b052cc32ced7bdeb010fca125e07f0", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/stepfun-ai/gelab-zero/HEAD/LICENSE"}], "id": "github:stepfun-ai/gelab-zero", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-16T06:36:01Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T06:42:01Z", "url": "https://raw.githubusercontent.com/stepfun-ai/gelab-zero/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/stepfun-ai/gelab-zero"}], "name": "GELab Zero", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Open mobile GUI agent stack pairing a 4B model that runs on consumer hardware with local multi-device infrastructure, an MCP server, and AndroidDaily benchmark tasks.", "topics": ["mobile-navigation"], "updated_at": null, "url": "https://github.com/stepfun-ai/gelab-zero"}
{"aliases": ["github:mnotgod96/appagent", "mnotgod96/AppAgent", "https://github.com/mnotgod96/AppAgent"], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:02Z", "role": "primary", "sha256": "ac94cca1f69807d2d31d30bd5521fbf1bda6155996881054df87a85522cd8f5b", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/TencentQQGYLab/AppAgent/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:03Z", "role": "primary", "sha256": "d9e2b107cbaa3599336510dbb6703cb30210f1b4345221e76cf75cba85c2d113", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/TencentQQGYLab/AppAgent/HEAD/LICENSE"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-17T14:13:57Z", "role": "primary", "sha256": "cd15c021e5023f43c17cc6365a58177c08ae91ac7e854c64c0e531f4ed3c5d5f", "supports": ["aliases"], "url": "https://api.github.com/repos/mnotgod96/AppAgent"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-17T14:13:58Z", "role": "primary", "sha256": "cd15c021e5023f43c17cc6365a58177c08ae91ac7e854c64c0e531f4ed3c5d5f", "supports": ["aliases"], "url": "https://api.github.com/repos/TencentQQGYLab/AppAgent"}], "id": "github:tencentqqgylab/appagent", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T06:36:02Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T06:42:03Z", "url": "https://raw.githubusercontent.com/TencentQQGYLab/AppAgent/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/TencentQQGYLab/AppAgent"}], "name": "AppAgent", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/TencentQQGYLab/AppAgent/HEAD/README.md", "target_id": "arxiv:2312.13771", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Multimodal agent that operates Android apps through taps and swipes without back-end access, building a reusable knowledge base from autonomous exploration or from watching human demonstrations.", "topics": ["mobile-navigation", "memory"], "updated_at": null, "url": "https://github.com/TencentQQGYLab/AppAgent"}
{"aliases": [], "authors": [], "details": {"benchmark_protocol": {"actions": ["Android operations through the agent framework"], "counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/THUDM/Android-Lab/HEAD/README.md", "population": "benchmark task collection", "qualifier": "exact", "unit": "tasks", "value": 138}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/THUDM/Android-Lab/HEAD/README.md", "population": "benchmark application set", "qualifier": "exact", "unit": "applications", "value": 9}], "evaluation": "The evaluation pipeline produces success, subgoal success, reversed redundancy, and reasonable-operation metrics; result generation requires a configured judge model.", "evidence_urls": ["https://raw.githubusercontent.com/THUDM/Android-Lab/HEAD/README.md"], "focus": ["Android task completion", "subgoal completion", "operation efficiency"], "notes": "The benchmark uses predefined virtual-device images and apps chosen to work without network/login requirements. XML and SoM modes should be reported separately. These counts concern evaluation tasks, not the separately released Android Instruct training set.", "observations": ["UI XML", "set-of-marks views"], "setting": "interactive"}, "evaluation_type": "benchmark task evaluation", "leaderboard_url": "https://docs.google.com/spreadsheets/d/1Zv6mBfd4Ibt8mke24K6zAFrXe4AvEFaBLW3hpJqSgjw/edit?gid=0#gid=0", "metrics": ["task success"], "task_count": 138}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:35:58Z", "role": "primary", "sha256": "340680a9a7833d103234b8367195deebd29bfec7e25ebc50c2dc04fc3627e55b", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/THUDM/Android-Lab/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:35:58Z", "role": "primary", "sha256": "340680a9a7833d103234b8367195deebd29bfec7e25ebc50c2dc04fc3627e55b", "supports": ["details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/THUDM/Android-Lab/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:41:58Z", "role": "primary", "sha256": "1bbbee919161337e2456c587c6be809214406482cd9f1292a9eb62428f6961f3", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/THUDM/Android-Lab/HEAD/LICENSE"}], "id": "github:thudm/android-lab", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-16T06:35:58Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T06:41:58Z", "url": "https://raw.githubusercontent.com/THUDM/Android-Lab/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/THUDM/Android-Lab"}], "name": "AndroidLab", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/THUDM/Android-Lab/HEAD/README.md", "target_id": "arxiv:2410.24024", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Reproducible Android benchmark of 138 tasks across nine apps on predefined virtual devices, run via AVD on Mac or Docker on Linux, released with the Android Instruct training set.", "topics": ["evaluation", "mobile-navigation"], "updated_at": null, "url": "https://github.com/THUDM/Android-Lab"}
{"aliases": [], "authors": [], "details": {"license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/Tongyi-MAI/MAI-UI/HEAD/MAI-UI/LICENSE", "https://raw.githubusercontent.com/Tongyi-MAI/MAI-UI/HEAD/MAI-UI/README.md"], "reason": "The implementation and LICENSE live under MAI-UI/. A root-level missing license or the follow-up Qwen-UI-Agent documentation should not change the scoped declaration."}}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T05:29:14Z", "role": "primary", "sha256": "f644a5c0d0eb29b0ff8d8552dd505c5ecedf7c9cd9ab8cf2c617a1a14ecd0c14", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "licenses.code"], "url": "https://raw.githubusercontent.com/Tongyi-MAI/MAI-UI/HEAD/MAI-UI/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:11:45Z", "role": "primary", "sha256": "fd90bc766d7e73889d14e8d3c5c92d384fa86e163222808f6e492509f00a3656", "supports": ["identity"], "url": "https://api.github.com/repos/Tongyi-MAI/MAI-UI"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:11:46Z", "role": "primary", "sha256": "4340b3d36bc56963fb8173079da8a0f7e91f195994d29fc47a9f7087cb56ffba", "supports": ["release_status"], "url": "https://api.github.com/repos/Tongyi-MAI/MAI-UI/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T05:29:15Z", "role": "primary", "sha256": "bf989559906a7926b77390082e4267ff7b2b494e8f599a9dc5640319eb45c2ce", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/Tongyi-MAI/MAI-UI/HEAD/MAI-UI/LICENSE"}], "id": "github:tongyi-mai/mai-ui", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-17T05:29:14Z", "licenses": {"code": {"basis": "Retained MAI-UI/LICENSE and MAI-UI README; applies to the inspected implementation, subject to third-party components.", "declared": "Apache-2.0 (MAI-UI subdirectory)", "retrieved_at": "2026-10-17T05:29:15Z", "url": "https://raw.githubusercontent.com/Tongyi-MAI/MAI-UI/HEAD/MAI-UI/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/Tongyi-MAI/MAI-UI"}], "name": "MAI-UI inference and evaluation code", "notes": "The original implementation is in the MAI-UI/ subdirectory, with an Apache-2.0 LICENSE there. The current root README also promotes Qwen-UI-Agent, but that follow-up directory contains only documentation/display assets in the inspected tree. This entry does not claim the follow-up runtime, training system or weights are released.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/Tongyi-MAI/MAI-UI/HEAD/MAI-UI/README.md", "target_id": "arxiv:2512.22047", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Published MAI-UI grounding and navigation-agent implementations with inference demos and evaluation scripts.", "topics": ["mobile-navigation", "grounding", "tool-integration"], "updated_at": null, "url": "https://github.com/Tongyi-MAI/MAI-UI"}
{"aliases": [], "authors": [], "details": {"availability": "Public task definitions, evaluator and container orchestration source.", "benchmark_protocol": {"actions": ["Android GUI operations", "MCP calls when enabled", "agent-user interaction when enabled"], "counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md", "population": "README benchmark overview", "qualifier": "exact", "unit": "tasks", "value": 201}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md", "population": "README benchmark overview", "qualifier": "exact", "unit": "mobile applications", "value": 20}], "evaluation": "The publisher documents text-answer matching, backend database verification, local-storage inspection and application callbacks.", "evidence_urls": ["https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md"], "focus": ["Android task completion", "agent-user interaction", "hybrid GUI and MCP use"], "notes": "Publisher-reported inventory. GUI-only, agent-user and MCP-augmented configurations have different dependencies and task eligibility; preserve enabled modes and step budget with results.", "observations": ["Android application interface", "user-agent interaction when enabled"], "setting": "interactive"}, "leaderboard_url": "https://tongyi-mai.github.io/MobileWorld/#leaderboard", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/LICENSE"], "reason": "Repository code license; self-hosted applications, model APIs and MCP services keep their own terms."}}, "repository_revision": "e7eee8981135ecbe39005a231edf63574defd79c"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:12:16Z", "role": "primary", "sha256": "fbc306b3414dfdb230171358efd6eb8d67573fbb94e11487a4a7e971e2abf0d9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details"], "url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:12:15Z", "role": "primary", "sha256": "266e1fe5b5b1a4c1540ab0fd5eba206395084ee283f0079f424930a156cf8e18", "supports": ["identity"], "url": "https://api.github.com/repos/Tongyi-MAI/MobileWorld"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:08Z", "role": "primary", "sha256": "14500ed2dfa14bb5c34211090f0c8827e4a16c3233e35a2d695c0d7261f9358b", "supports": ["release_status"], "url": "https://api.github.com/repos/Tongyi-MAI/MobileWorld/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:09Z", "role": "primary", "sha256": "b09fcaf4fbc265223c2479c410beef2b98c5e687c78ecedf3452aa12ffc465f1", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/LICENSE"}], "id": "github:tongyi-mai/mobileworld", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-17T09:12:16Z", "licenses": {"code": {"basis": "Repository code license; self-hosted applications, model APIs and MCP services keep their own terms.", "declared": "Apache-2.0", "retrieved_at": "2026-10-17T09:14:09Z", "url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/Tongyi-MAI/MobileWorld"}], "name": "MobileWorld (Tongyi-MAI)", "notes": "This is Tongyi-MAI/MobileWorld, distinct from jacklishufan/MobileWorld (MobileWorldBench). Public source includes task definitions, verification logic and environment orchestration. The README reports 201 tasks across 20 applications; this is not an independent count of the evolving task tree. Linux/KVM or WSL2/KVM is required by the documented host setup, with macOS support in progress. MCP and simulated-user settings can require separate external services.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md", "target_id": "arxiv:2512.19432", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A containerized Android evaluation environment with GUI-only, agent-user interaction and MCP-augmented tasks, plus checks on application and backend state.", "topics": ["evaluation", "mobile-navigation", "human-in-the-loop", "tool-integration"], "updated_at": null, "url": "https://github.com/Tongyi-MAI/MobileWorld"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:59:55Z", "role": "primary", "sha256": "2403ef3ec300e257dc631e3c569fc9aabaab1d3f385ac37abe1e4021aaae6e21", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/VeriSafeAgent/VeriSafeAgent/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T13:06:20.028238+00:00", "role": "primary", "sha256": "9b04efe4136a39e3e5f21a1d3bb8a44075f1370bdbeec6a4307783f3836f8311", "supports": ["summary", "relations", "notes"], "url": "https://arxiv.org/html/2503.18492v2"}], "id": "github:verisafeagent/verisafeagent", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-18T10:59:55Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/VeriSafeAgent/VeriSafeAgent"}], "name": "VeriSafe Agent", "notes": "The verification method requires developers to supply app-state predicates and transition hooks. The paper-to-repository relation is supported by the exact-version paper, not inferred from the repository name.", "published_at": null, "relations": [{"evidence_url": "https://arxiv.org/html/2503.18492v2", "target_id": "arxiv:2503.18492", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Runtime verification framework for Android GUI agents that checks proposed actions against logical rules derived from user instructions and developer-defined app states.", "topics": ["safety-security", "mobile-navigation", "state-tracking"], "updated_at": null, "url": "https://github.com/VeriSafeAgent/VeriSafeAgent"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:42:12Z", "role": "primary", "sha256": "5f460f9b2a18315d07b8c48d78dcc764892d09d9250e95f5e591b5966fe59328", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/vivo-ai-lab/BlueLM-GUI/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T10:48:41Z", "role": "primary", "sha256": "6036aa17e52be8051fc3c8ede37fc4d0b2bc2589518be7623566c75868612178", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/vivo-ai-lab/BlueLM-GUI/HEAD/LICENSE"}], "id": "github:vivo-ai-lab/bluelm-gui", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-16T10:42:12Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T10:48:41Z", "url": "https://raw.githubusercontent.com/vivo-ai-lab/BlueLM-GUI/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/vivo-ai-lab/BlueLM-GUI"}], "name": "BlueLM-GUI", "notes": "The repository lists the agent as in-house. Public model weights were not established by this review; linked benchmark assets have their own access terms.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/vivo-ai-lab/BlueLM-GUI/HEAD/README.md", "target_id": "arxiv:2609.12394", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile GUI agent research release with technical report, benchmark data, and evaluation tooling from vivo AI Lab.", "topics": ["mobile-navigation", "reinforcement-learning"], "updated_at": null, "url": "https://github.com/vivo-ai-lab/BlueLM-GUI"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:02Z", "role": "primary", "sha256": "085f1a1810805bcade9555b1e5c374a7db1b8b1377afeeea285d927853b02f3d", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/Westlake-AGI-Lab/AppAgentX/HEAD/README.md"}], "id": "github:westlake-agi-lab/appagentx", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T06:36:02Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/Westlake-AGI-Lab/AppAgentX"}], "name": "AppAgentX", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/Westlake-AGI-Lab/AppAgentX/HEAD/README.md", "target_id": "arxiv:2503.02268", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile agent research using accumulated interaction experience.", "topics": ["mobile-navigation", "memory"], "updated_at": null, "url": "https://github.com/Westlake-AGI-Lab/AppAgentX"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T13:14:29Z", "role": "primary", "sha256": "15d40c50df8493575a94aa2aa4913c654fea7b7f821d99b7bf443a64f1cc50d3", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/Wuzheng02/OS-Kairos/HEAD/README.md"}], "id": "github:wuzheng02/os-kairos", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T13:14:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/Wuzheng02/OS-Kairos"}], "name": "OS-Kairos", "notes": "The documented evaluation modes distinguish model-simulated human feedback from actual human interaction; preserve that distinction when interpreting results.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/Wuzheng02/OS-Kairos/HEAD/README.md", "target_id": "arxiv:2503.16465", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Android GUI-agent research implementation that uses confidence-guided interaction to choose between autonomous actions and human assistance.", "topics": ["human-in-the-loop", "safety-security", "mobile-navigation"], "updated_at": null, "url": "https://github.com/Wuzheng02/OS-Kairos"}
{"aliases": [], "authors": [], "details": {}, "environments": ["unspecified"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:59:55Z", "role": "primary", "sha256": "282883d02391a86c5a4d0cdafdc1d33f10a5073f31eba8c852095601d0aeb939", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "notes"], "url": "https://raw.githubusercontent.com/Wuzheng02/VeriOS/HEAD/README.md"}], "id": "github:wuzheng02/verios", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-18T10:59:55Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/Wuzheng02/VeriOS"}], "name": "VeriOS", "notes": "The released scripts evaluate recorded task inputs; the retained README does not establish a live Android execution environment. No runtime behavior or reported results were independently reproduced.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/Wuzheng02/VeriOS/HEAD/README.md", "target_id": "arxiv:2509.07553", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Research code for proactive human–GUI-agent verification, including offline interaction-loop and dual-agent evaluation scripts plus LLaMA-Factory fine-tuning configurations.", "topics": ["safety-security", "human-in-the-loop", "mobile-navigation"], "updated_at": null, "url": "https://github.com/Wuzheng02/VeriOS"}
{"aliases": [], "authors": [], "details": {"availability": "Public federated-training/evaluation code and ungated annotation partitions; original images are separate dependencies.", "benchmark_protocol": {"actions": ["model predictions on mobile-agent examples"], "counts": [{"basis": "reported", "evidence_url": "https://huggingface.co/datasets/wwh0411/FedMABench/raw/main/README.md", "population": "released FedMABench partition families", "qualifier": "exact", "unit": "dataset families", "value": 6}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/wwh0411/FedMABench/HEAD/README.md", "population": "publisher benchmark overview", "qualifier": "exact", "unit": "heterogeneity types", "value": 3}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/wwh0411/FedMABench/HEAD/README.md", "population": "publisher benchmark overview", "qualifier": "exact", "unit": "federated learning algorithms", "value": 8}], "evaluation": "The provided evaluation workflow performs model inference over selected partitions and invokes test_swift_fed.py for accuracy scoring.", "evidence_urls": ["https://raw.githubusercontent.com/wwh0411/FedMABench/HEAD/README.md", "https://huggingface.co/datasets/wwh0411/FedMABench/raw/main/README.md"], "focus": ["mobile-agent federated training", "data heterogeneity"], "notes": "The dataset-family count does not count tasks, apps, screenshots or client instances. Code and data licenses are unknown; external image sources are required.", "observations": ["mobile-agent examples with externally sourced screenshots"], "setting": "offline"}, "repository_revision": "417d8b0006830f423c7d07c213fc57277d75d966"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:17Z", "role": "primary", "sha256": "b49e2b419918078ef9c68f3c9becc6c13d8fe530c165a36bdd61e370746eeea8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details.benchmark_protocol"], "url": "https://raw.githubusercontent.com/wwh0411/FedMABench/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:17Z", "role": "primary", "sha256": "3e1b2b643a263af129b3a4092a84efe47d3643f00509f7b9517da21a4aac0371", "supports": ["identity"], "url": "https://api.github.com/repos/wwh0411/FedMABench"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:22:54Z", "role": "primary", "sha256": "4fb977a469cee3d5083da0b5bf2984fedc6b867146a90b20963985e08f9e9716", "supports": ["release_status", "details.repository_revision", "licenses.code"], "url": "https://api.github.com/repos/wwh0411/FedMABench/git/trees/master?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:06Z", "role": "primary", "sha256": "df5379f4a9b350dad0c3d374d2f9a1d6eacd974b6d54750e2a14ecec1faec6e5", "supports": ["identity", "release_status"], "url": "https://huggingface.co/api/datasets/wwh0411/FedMABench"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:06Z", "role": "primary", "sha256": "2874269995d8c9f5dabe266433ecf724bf54c27af599d899f3f0090b8ee37cdc", "supports": ["summary", "details.benchmark_protocol", "licenses.data"], "url": "https://huggingface.co/datasets/wwh0411/FedMABench/raw/main/README.md"}], "id": "github:wwh0411/fedmabench", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-17T11:18:17Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/wwh0411/FedMABench"}], "name": "FedMABench", "notes": "The public Hub lists six dataset families of JSON/JSONL partition annotations. The repository explicitly says unpacked screenshots are not provided and must be reconstructed from original AndroidControl and AITW sources. This is offline training/evaluation infrastructure rather than a live Android task environment. No repository license file or dataset-license declaration was found in the inspected sources; neither is inferred from the underlying ms-swift project.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/wwh0411/FedMABench/HEAD/README.md", "target_id": "arxiv:2503.05143", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A federated mobile-agent training and evaluation suite that varies user-data heterogeneity and application distribution, with released partition annotations and inference/scoring scripts.", "topics": ["evaluation", "imitation-learning", "mobile-navigation"], "updated_at": null, "url": "https://github.com/wwh0411/FedMABench"}
{"aliases": [], "authors": [], "details": {}, "environments": ["unspecified"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:43:11Z", "role": "primary", "sha256": "2cea1be73ea75acd46990ab1fb567fbd83ad58a2bc69ca858b207660df9fe8c1", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/X-LANCE/META-GUI-baseline/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T10:48:42Z", "role": "primary", "sha256": "01fb614f0536ea76c1c25809cc8cde66cde21a96ac6ca0ea81b2c093e2157d2a", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/X-LANCE/META-GUI-baseline/HEAD/LICENSE"}], "id": "github:x-lance/meta-gui-baseline", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-16T10:43:11Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T10:48:42Z", "url": "https://raw.githubusercontent.com/X-LANCE/META-GUI-baseline/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/X-LANCE/META-GUI-baseline"}], "name": "META-GUI baseline", "notes": "Its README describes mobile GUI agents without naming an operating system.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/X-LANCE/META-GUI-baseline/HEAD/README.md", "target_id": "arxiv:2205.11029", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Training and evaluation pipeline for conversational mobile GUI agents, with action prediction, response generation, and dataset processing.", "topics": ["mobile-navigation", "human-in-the-loop"], "updated_at": null, "url": "https://github.com/X-LANCE/META-GUI-baseline"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android", "cross-platform"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:02Z", "role": "primary", "sha256": "ca402ffd3b05f72a6d72f47de52c962f92e410749a77939044f3301d4330af16", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:03Z", "role": "primary", "sha256": "961819a89dacd1f4f161e1d2ebf616b538bf095a2eecfa3ef40b7ccec633fac4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/LICENSE"}], "id": "github:x-plug/mobileagent", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T06:36:02Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T06:42:03Z", "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/X-PLUG/MobileAgent"}], "name": "Mobile-Agent", "notes": "This repository contains multiple Mobile-Agent generations. Platform coverage differs by version; use the corresponding paper and implementation instructions.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/README.md", "target_id": "arxiv:2401.16158", "type": "documented_by"}, {"evidence_url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/README.md", "target_id": "arxiv:2406.01014", "type": "documented_by"}, {"evidence_url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/README.md", "target_id": "arxiv:2508.15144", "type": "documented_by"}, {"evidence_url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/README.md", "target_id": "arxiv:2602.16855", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile device agent family using visual interface interaction.", "topics": ["mobile-navigation", "planning"], "updated_at": null, "url": "https://github.com/X-PLUG/MobileAgent"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:42:12Z", "role": "primary", "sha256": "55de0ed6627a5812d1f26d2a920e0af47afb17f8a99cae41b70a85ba30a23370", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/xbmxb/CoCo-Agent/HEAD/README.md"}], "id": "github:xbmxb/coco-agent", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T10:42:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/xbmxb/CoCo-Agent"}], "name": "CoCo-Agent", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/xbmxb/CoCo-Agent/HEAD/README.md", "target_id": "arxiv:2402.11941", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Research implementation combining screen and layout perception with conditional action prediction for smartphone automation.", "topics": ["mobile-navigation", "screen-understanding"], "updated_at": null, "url": "https://github.com/xbmxb/CoCo-Agent"}
{"aliases": [], "authors": [], "details": {"platform_constraints": {"harmonyos": "The README limits device debugging support to HarmonyOS 4 or earlier."}}, "environments": ["android", "harmonyos"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T13:14:29Z", "role": "primary", "sha256": "02e231c68ffc37c829789eabc508a220f3d99a33ee8bf676e53c999a0ff54021", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/Yuqi-Zhou/CHOP/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T13:29:25Z", "role": "primary", "sha256": "1a9f9af82764fdfc07dd8c2ec02e66cbb5c7c2cfc899b0e7b53b26e2a774ddf9", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/Yuqi-Zhou/CHOP/HEAD/LICENSE"}], "id": "github:yuqi-zhou/chop", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-16T13:14:29Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T13:29:25Z", "url": "https://raw.githubusercontent.com/Yuqi-Zhou/CHOP/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/Yuqi-Zhou/CHOP"}], "name": "CHOP", "notes": "The README says the complete CHOP-ZH dataset remains unreleased. Android and HarmonyOS compatibility is publisher-documented and has not been runtime-tested here.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/Yuqi-Zhou/CHOP/HEAD/README.md", "target_id": "arxiv:2503.03743", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile automation framework that uses reusable basis subtasks to constrain and refine planning between user goals and executable actions.", "topics": ["mobile-navigation", "planning", "workflow"], "updated_at": null, "url": "https://github.com/Yuqi-Zhou/CHOP"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android", "ios"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:40:53Z", "role": "primary", "sha256": "de9c289c418218d40cdf1731775158af771d010266d7ea2aa398f2dc91f22acc", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/zai-org/Open-AutoGLM/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:07Z", "role": "primary", "sha256": "af69329b4667040c498cc87dfcc165db1f5f9452fe2ad3024ad7eef63d467666", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/zai-org/Open-AutoGLM/HEAD/LICENSE"}], "id": "github:zai-org/open-autoglm", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T06:40:53Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T06:42:07Z", "url": "https://raw.githubusercontent.com/zai-org/Open-AutoGLM/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/zai-org/Open-AutoGLM"}], "name": "Open-AutoGLM", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Phone agent model and framework with device interaction tooling.", "topics": ["mobile-navigation"], "updated_at": null, "url": "https://github.com/zai-org/Open-AutoGLM"}
{"aliases": [], "authors": [], "details": {"disabled": false, "download_url": "https://huggingface.co/Tongyi-MAI/MAI-UI-8B/tree/main", "gated": false, "hub_id": "Tongyi-MAI/MAI-UI-8B"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:07:19Z", "role": "primary", "sha256": "a1087d2a0dde6e7ba6d79db546ee6360a5ffd95ffbc3add1478eedec603a4187", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/Tongyi-MAI/MAI-UI-8B/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:07:18Z", "role": "primary", "sha256": "349e6d5753fa94a47feb4b2fc53ecd6b9188b645a0cffabef92fd1aa0976ecad", "supports": ["identity", "release_status", "details", "licenses.weights"], "url": "https://huggingface.co/api/models/Tongyi-MAI/MAI-UI-8B"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T04:07:19Z", "role": "primary", "sha256": "a1087d2a0dde6e7ba6d79db546ee6360a5ffd95ffbc3add1478eedec603a4187", "supports": ["licenses.weights"], "url": "https://huggingface.co/Tongyi-MAI/MAI-UI-8B/raw/main/README.md"}], "id": "url:00b1a3abf9bcb424b264", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-17T04:07:19Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T04:07:19Z", "url": "https://huggingface.co/Tongyi-MAI/MAI-UI-8B/raw/main/README.md"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/Tongyi-MAI/MAI-UI-8B"}], "name": "MAI-UI 8B", "notes": "Four public safetensors shards are present and Apache-2.0 is declared. The card presents family-wide results and device-cloud architecture; those claims are not all assigned to the 8B checkpoint. Other parameter sizes are not duplicated in this proposal batch.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/Tongyi-MAI/MAI-UI-8B/raw/main/README.md", "target_id": "arxiv:2512.22047", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A released MAI-UI checkpoint combining mobile GUI actions, agent-user interaction and tool-use-oriented navigation.", "topics": ["grounding", "mobile-navigation", "tool-integration"], "updated_at": null, "url": "https://huggingface.co/Tongyi-MAI/MAI-UI-8B"}
{"aliases": ["url:1ab38d1d6a4c46a8eb3e", "OpenMobile-2/OpenMobile-27B", "https://huggingface.co/OpenMobile-2/OpenMobile-27B"], "authors": [], "details": {"artifact_inspection": "Public file-manifest inspection only; weights were not downloaded.", "base_model": "Qwen/Qwen3.6-27B", "gated": false, "hub_revision": "3d844db8c20421524a5012837b151e444ad35ae6", "listed_weight_files": ["model-00001-of-00012.safetensors", "model-00002-of-00012.safetensors", "model-00003-of-00012.safetensors", "model-00004-of-00012.safetensors", "model-00005-of-00012.safetensors", "model-00006-of-00012.safetensors", "model-00007-of-00012.safetensors", "model-00008-of-00012.safetensors", "model-00009-of-00012.safetensors", "model-00010-of-00012.safetensors", "model-00011-of-00012.safetensors", "model-00012-of-00012.safetensors"]}, "environments": ["android", "web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:51Z", "role": "primary", "sha256": "ba760ab75e997941dabf0845b34e5fb83daeb83a5cfa16b13929477cfc61a31c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-27B/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:49:48Z", "role": "primary", "sha256": "c7e388efe1ecfd415b7b5af7f296e62646a0a1380037f1e57ad1a43c26463b9a", "supports": ["details.gated", "details.hub_revision", "details.listed_weight_files"], "url": "https://huggingface.co/api/models/OpenMobile-2/OpenMobile-2-27B"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:46:06Z", "role": "primary", "sha256": "9b385e9f6aa2f7169f616a76887df3b76df605cb2bea071d99ee7ca3f9b659cc", "supports": ["environments"], "url": "https://os-copilot.github.io/OpenMobile2-Home/"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T01:48:51Z", "role": "primary", "sha256": "ba760ab75e997941dabf0845b34e5fb83daeb83a5cfa16b13929477cfc61a31c", "supports": ["licenses.weights"], "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-27B/raw/main/README.md"}, {"method": "huggingface_repository_identity", "retrieved_at": "2026-10-17T19:15:11Z", "role": "primary", "sha256": "f669181b7f1b92bbbcb8ab71f0d15d8c3cf93b3665d73d20e9b9f0dc3a36e158", "supports": ["aliases"], "url": "https://huggingface.co/api/models/OpenMobile-2/OpenMobile-27B"}, {"method": "huggingface_repository_identity", "retrieved_at": "2026-10-17T19:15:12Z", "role": "primary", "sha256": "f669181b7f1b92bbbcb8ab71f0d15d8c3cf93b3665d73d20e9b9f0dc3a36e158", "supports": ["aliases"], "url": "https://huggingface.co/api/models/OpenMobile-2/OpenMobile-2-27B"}], "id": "url:1611de0e6d606165d12d", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-17T01:48:51Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T01:48:51Z", "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-27B/raw/main/README.md"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-27B"}], "name": "OpenMobile-2 27B", "notes": "The public Hub manifest lists weight files; the catalog did not download weights or reproduce inference. License declarations apply to this checkpoint separately from code and training data.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-27B/raw/main/README.md", "target_id": "github:openmobile2/openmobile2-code", "type": "variant_of"}, {"evidence_url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-27B/raw/main/README.md", "target_id": "url:546e6c95825d1318c98d", "type": "trained_on"}, {"evidence_url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-27B/raw/main/README.md", "target_id": "arxiv:2610.14157", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile-agent checkpoint based on Qwen3.6-27B for GUI and app-native tool interaction.", "topics": ["mobile-navigation", "tool-integration"], "updated_at": null, "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-27B"}
{"aliases": [], "authors": [], "details": {"dataset_profile": {"counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/UI-S1/README.md", "population": "public example subset", "qualifier": "exact", "unit": "training examples", "value": 1000}], "evidence_urls": ["https://huggingface.co/datasets/mPLUG/UI_S1_dataset/raw/main/README.md", "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/UI-S1/README.md"], "formats": ["JSONL", "Parquet"], "modalities": ["images", "text", "actions"], "notes": "The count is explicitly reported by the publisher, not inferred from the filename. Full training data remains outside this release.", "splits": ["training example subset"], "supervision": ["GUI actions"]}, "disabled": false, "download_url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset/tree/main", "gated": false, "hub_id": "mPLUG/UI_S1_dataset"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:07:19Z", "role": "primary", "sha256": "d826463e2aa159f083dc74869bfabb8abb5b8ea4f2cdf4aeb7676172b18aaaa5", "supports": ["name", "kind", "relations", "licenses.data"], "url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:07:19Z", "role": "primary", "sha256": "cdfbcbf23a3b1b4a609e1943e80dcf144ca1224a74ebf2308fde4fcb4326ab3c", "supports": ["identity", "release_status", "details", "licenses.data"], "url": "https://huggingface.co/api/datasets/mPLUG/UI_S1_dataset"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:06:57Z", "role": "primary", "sha256": "f668c890a5a87953a243715d0d47367c23f0c99b524d80f48bbdde8163f3e942", "supports": ["summary", "environments", "details.dataset_profile", "topics", "scope"], "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/UI-S1/README.md"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T04:07:19Z", "role": "primary", "sha256": "d826463e2aa159f083dc74869bfabb8abb5b8ea4f2cdf4aeb7676172b18aaaa5", "supports": ["licenses.data"], "url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset/raw/main/README.md"}], "id": "url:16184830c0f4bdb146fa", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-17T04:07:19Z", "licenses": {"code": null, "data": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T04:07:19Z", "url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset/raw/main/README.md"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset"}], "name": "UI-S1 released training examples", "notes": "The release contains train_1000.jsonl and images.parquet. The official README explicitly describes 1,000 released examples and calls the release only part of the training dataset. Apache-2.0 is declared by the dataset card; this is not the complete training corpus.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset/raw/main/README.md", "target_id": "arxiv:2509.11543", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A public example subset of the UI-S1 mobile training data, packaged as JSONL annotations and Parquet images.", "topics": ["reinforcement-learning", "data-generation", "mobile-navigation"], "updated_at": null, "url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset"}
{"aliases": [], "authors": [], "details": {"disabled": false, "download_url": "https://huggingface.co/mPLUG/UI-S1-7B/tree/main", "gated": false, "hub_id": "mPLUG/UI-S1-7B"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:03:41Z", "role": "primary", "sha256": "341abd3833131080682b27fe0b79e310d7cf9465602b77b8e399e45200552d61", "supports": ["name", "kind", "relations", "licenses.weights"], "url": "https://huggingface.co/mPLUG/UI-S1-7B/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:03:40Z", "role": "primary", "sha256": "d0c25fa2fad8372ffc8b51b63701c7e5548cca08a612c0081c4c317f9532894d", "supports": ["identity", "release_status", "details", "licenses.weights"], "url": "https://huggingface.co/api/models/mPLUG/UI-S1-7B"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:06:57Z", "role": "primary", "sha256": "f668c890a5a87953a243715d0d47367c23f0c99b524d80f48bbdde8163f3e942", "supports": ["summary", "environments", "topics", "scope"], "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/UI-S1/README.md"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T04:03:41Z", "role": "primary", "sha256": "341abd3833131080682b27fe0b79e310d7cf9465602b77b8e399e45200552d61", "supports": ["licenses.weights"], "url": "https://huggingface.co/mPLUG/UI-S1-7B/raw/main/README.md"}], "id": "url:1c4ee99a9a55ae71a7ac", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-17T04:03:41Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T04:03:41Z", "url": "https://huggingface.co/mPLUG/UI-S1-7B/raw/main/README.md"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/mPLUG/UI-S1-7B"}], "name": "UI-S1 7B", "notes": "Four public safetensors shards are present. The card declares Apache-2.0 for the weights. The project publishes only a portion of its training data; no complete training corpus or independent reproduction is inferred.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/mPLUG/UI-S1-7B/raw/main/README.md", "target_id": "arxiv:2509.11543", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A mobile GUI checkpoint trained with semi-online reinforcement learning that uses offline trajectories to improve multi-turn action prediction.", "topics": ["reinforcement-learning", "mobile-navigation", "action-prediction"], "updated_at": null, "url": "https://huggingface.co/mPLUG/UI-S1-7B"}
{"aliases": [], "authors": [], "details": {"benchmark_protocol": {"actions": ["mobile UI actions", "clarification responses"], "counts": [], "evaluation": "Paper defines multi-path and noise/ambiguity evaluations; the public card identifies which files are full common-task sets and which are samples.", "evidence_urls": ["https://huggingface.co/datasets/xwk123/MobileBench-v2/raw/main/README.md", "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"], "focus": ["offline multi-path evaluation", "noisy interfaces", "ambiguous instructions"], "notes": "Release completeness differs by split. No full-benchmark sample total is inferred from the archive manifest.", "observations": ["mobile screenshots", "XML UI state", "instructions"], "setting": "offline"}, "disabled": false, "download_url": "https://huggingface.co/datasets/xwk123/MobileBench-v2/tree/main", "gated": false, "hub_id": "xwk123/MobileBench-v2", "license_review": {"data": {"evidence_urls": ["https://huggingface.co/datasets/xwk123/MobileBench-v2/raw/main/README.md"], "reason": "The same first-party card has an Apache-2.0 metadata header but explicitly assigns Apache-2.0 to code and CC-BY-NC-SA-4.0 to the dataset in its License section. Preserve both declarations and leave a single data license unresolved instead of displaying the permissive header as the data permission."}}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:33Z", "role": "primary", "sha256": "13424be795c7b75b8c2195469c1252a7b3ec633e8bb31f1f6d7e44476611cbe9", "supports": ["name", "kind", "summary", "topics", "scope", "relations", "details", "licenses.data"], "url": "https://huggingface.co/datasets/xwk123/MobileBench-v2/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:33Z", "role": "primary", "sha256": "247b1766b8cbdb2943c4602d2667f9f06dec8b84f0d24457080d499177475f22", "supports": ["identity", "release_status", "details"], "url": "https://huggingface.co/api/datasets/xwk123/MobileBench-v2"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:42Z", "role": "primary", "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e", "supports": ["relations", "summary"], "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:38:26Z", "role": "primary", "sha256": "356a8dca28fa3dc46bc05b13eaf04a3db273e63c06be4fd15d0e87e0343c0824", "supports": ["environments", "notes"], "url": "https://huggingface.co/api/datasets/xwk123/Mobile3M"}], "id": "url:1d5b85321b98765141fc", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-17T04:01:33Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/xwk123/MobileBench-v2"}], "name": "Mobile-Bench-v2 released data", "notes": "The card distinguishes complete common-simple/common-complex JSON files from sampled noisy and ambiguous subsets; common tasks also require the separately cataloged Mobile3M dataset. Card metadata says Apache-2.0, while the prose explicitly assigns Apache-2.0 to code and CC-BY-NC-SA-4.0 to data. Do not apply the permissive header to dataset payloads, and do not describe every announced split as fully released.", "published_at": null, "relations": [{"evidence_url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50", "target_id": "arxiv:2505.11891", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Offline mobile-agent task data spanning common tasks and released noisy, contaminated and ambiguous-instruction subsets.", "topics": ["evaluation", "mobile-navigation", "robustness"], "updated_at": null, "url": "https://huggingface.co/datasets/xwk123/MobileBench-v2"}
{"aliases": ["url:1ff6b78a764bdcc6dd03", "HanXiao1999/UI-Genie-Agent-5k", "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-5k"], "authors": [], "details": {"dataset_profile": {"counts": [], "evidence_urls": ["https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/raw/main/README.md", "https://raw.githubusercontent.com/Euphoria16/UI-Genie/HEAD/README.md"], "formats": ["JSONL", "PNG"], "modalities": ["screenshots", "text", "actions"], "notes": "Public JSONL annotations and screenshots are present. MIT is declared in the dataset card. The release name, model-card links and annotation filename use different size labels; this review does not infer a reliable trajectory count from them.", "splits": [], "supervision": ["GUI action trajectories"]}, "disabled": false, "download_url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/tree/main", "gated": false, "hub_id": "HanXiao1999/UI-Genie-Agent-16k"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "a748fc7dbb53d5d751c5ee109e437c377e214b1d837762f8d09995349d86cec9", "supports": ["name", "kind", "relations", "licenses.data"], "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:33Z", "role": "primary", "sha256": "548df402288350920a26bff2099544bf21835200ee58ff2c657c331fa6200317", "supports": ["identity", "release_status", "details", "licenses.data"], "url": "https://huggingface.co/api/datasets/HanXiao1999/UI-Genie-Agent-16k"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:54Z", "role": "primary", "sha256": "e08569bd9d8a6ff44537d4fe69243ddfeb8a41ae5c9f87ef84af50a67c64c726", "supports": ["summary", "environments", "topics", "scope"], "url": "https://raw.githubusercontent.com/Euphoria16/UI-Genie/HEAD/README.md"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "a748fc7dbb53d5d751c5ee109e437c377e214b1d837762f8d09995349d86cec9", "supports": ["licenses.data"], "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/raw/main/README.md"}, {"method": "huggingface_repository_identity", "retrieved_at": "2026-10-17T19:15:09Z", "role": "primary", "sha256": "66006a586e03be3eb1dfc29dc9c951241fd7e4204430e7db258da1037e17ac6e", "supports": ["aliases"], "url": "https://huggingface.co/api/datasets/HanXiao1999/UI-Genie-Agent-5k"}, {"method": "huggingface_repository_identity", "retrieved_at": "2026-10-17T19:15:10Z", "role": "primary", "sha256": "66006a586e03be3eb1dfc29dc9c951241fd7e4204430e7db258da1037e17ac6e", "supports": ["aliases"], "url": "https://huggingface.co/api/datasets/HanXiao1999/UI-Genie-Agent-16k"}], "id": "url:2e1927450da2183a5abe", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-17T04:01:34Z", "licenses": {"code": null, "data": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-17T04:01:34Z", "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/raw/main/README.md"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k"}], "name": "UI-Genie trajectory data", "notes": "Public JSONL annotations and screenshots are present. MIT is declared in the dataset card. The release name, model-card links and annotation filename use different size labels; this review does not infer a reliable trajectory count from them.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/raw/main/README.md", "target_id": "arxiv:2505.21496", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Synthetic mobile GUI trajectory supervision and screenshots released with the UI-Genie agent-training pipeline.", "topics": ["data-generation", "mobile-navigation", "imitation-learning"], "updated_at": null, "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k"}
{"aliases": [], "authors": ["Toby Jia-Jun Li", "Amos Azaria", "Brad A. Myers"], "details": {"publication": {"authors": ["Toby Jia-Jun Li", "Amos Azaria", "Brad A. Myers"], "date_basis": "Supplied year precision: 2017. Publications: SUGILITE, CHI 2017 Only publication year is asserted; event dates are kept separate.", "date_parts": [2017], "doi": "10.1145/3025453.3025483", "event_dates": null, "evidence_urls": ["https://www.cs.cmu.edu/~NatProg/sugilite.html", "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Related to later APPINITE and PUMICE work but distinguished here by its 2017 three-author publication and base demonstration-automation contribution. Publication month/day are not independently identified by the retained sources.", "pages": "6038-6049", "pdf_url": "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf", "publisher": null, "series": null, "title": "SUGILITE: Creating Multimodal Smartphone Automation by Demonstration", "type": "conference-paper", "url": "https://doi.org/10.1145/3025453.3025483", "venue": "Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems", "volume": null}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:22Z", "role": "primary", "sha256": "32ee05ff1a91ed4a22d4bc156a462872aa4e28f5c79abfbce5dbf3655f412033", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.notes", "details.publication.type", "details.publication.venue"], "url": "https://www.cs.cmu.edu/~NatProg/sugilite.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:54:39Z", "role": "primary", "sha256": "cc23c19284f0a558c4b99b8b051abca8ed61e274e9e1f1fed1ae91487f4368ad", "supports": ["details.publication.authors", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.title", "details.publication.url"], "url": "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:54:39Z", "role": "primary", "sha256": "cc23c19284f0a558c4b99b8b051abca8ed61e274e9e1f1fed1ae91487f4368ad", "supports": ["details.publication.authors", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.title", "details.publication.url", "environments", "name", "scope", "summary", "topics"], "url": "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:22Z", "role": "primary", "sha256": "32ee05ff1a91ed4a22d4bc156a462872aa4e28f5c79abfbce5dbf3655f412033", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.notes", "details.publication.type", "details.publication.venue", "kind"], "url": "https://www.cs.cmu.edu/~NatProg/sugilite.html"}], "id": "url:392a602c660ffa91be46", "identifiers": {"doi": "10.1145/3025453.3025483"}, "kind": "paper", "last_verified_at": "2026-10-17T09:54:39Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://doi.org/10.1145/3025453.3025483"}, {"rel": "publication_pdf", "url": "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf"}], "name": "SUGILITE: Creating Multimodal Smartphone Automation by Demonstration", "notes": "The annotation was reviewed against retained primary publication sources. Experiments have not been independently reproduced. Related to later APPINITE and PUMICE work but distinguished here by its 2017 three-author publication and base demonstration-automation contribution.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces SUGILITE, which combines spoken instructions, demonstrated Android actions, and UI hierarchies to generate reusable automation scripts. Its interface includes context checking and repairs for unfamiliar situations and changing app interfaces.", "topics": ["mobile-navigation", "recording", "human-in-the-loop", "cross-app"], "updated_at": null, "url": "https://doi.org/10.1145/3025453.3025483"}
{"aliases": [], "authors": [], "details": {"dataset_profile": {"counts": [{"basis": "reported", "evidence_url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md", "population": "recommended hflqf88888/GUIOdyssey release", "qualifier": "exact", "unit": "episodes", "value": 8334}], "evidence_urls": ["https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/README.md", "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md", "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/introduction.md"], "formats": ["JSON annotations", "PNG screenshots"], "modalities": ["screenshots", "instructions", "actions", "bounding boxes", "step context"], "notes": "The repository gives conflicting episode totals (8,334 and 8,834). This profile uses 8,334 from the specifically recommended current dataset card. No independent archive recount was performed. Coordinates are normalized to 0–1000.", "splits": ["random", "task", "device", "app"], "supervision": ["cross-app trajectories", "action grounding"]}, "download_url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/tree/main", "sample_count": 8334, "sample_unit": "episodes reported by the current release card"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:39:52Z", "role": "primary", "sha256": "fd627ee0a6ee0596e0ee8147996b9a7a3436f754fc95ed63cf5f408d778b2831", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "4585b765d7c8b3e9bb6187d36d576edde454d4c0158a6aa8b3fdbedf34c89a15", "supports": ["details.dataset_profile"], "url": "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:39:52Z", "role": "primary", "sha256": "78c19ee712487af60df1913f11572958564e59a1a2cc663b1b30d971855d7a28", "supports": ["details.dataset_profile"], "url": "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/introduction.md"}, {"method": "huggingface_card", "retrieved_at": "2026-10-16T11:39:52Z", "role": "primary", "sha256": "fd627ee0a6ee0596e0ee8147996b9a7a3436f754fc95ed63cf5f408d778b2831", "supports": ["licenses.data"], "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md"}], "id": "url:511903ebfac45e6751b2", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-16T11:39:52Z", "licenses": {"code": null, "data": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "cc-by-4.0", "retrieved_at": "2026-10-16T11:39:52Z", "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey"}], "name": "GUIOdyssey — current data release", "notes": "The project recommends this release over its earlier OpenGVLab/GUI-Odyssey upload. Episode count follows the current data card; conflicting repository prose is documented in the profile.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md", "target_id": "arxiv:2406.08451", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Cross-app Android interaction episodes with fine-grained step instructions, screen descriptions, action context, and target boxes.", "topics": ["mobile-navigation", "cross-app", "data-generation"], "updated_at": null, "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey"}
{"aliases": ["url:a778c3411858c38c0f39", "OpenMobile-2/OpenMobile-Data", "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data"], "authors": [], "details": {"dataset_profile": {"counts": [{"basis": "reported", "evidence_url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md", "population": "SFT collection", "qualifier": "exact", "unit": "trajectories", "value": 11643}, {"basis": "reported", "evidence_url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md", "population": "SFT collection", "qualifier": "exact", "unit": "decision steps", "value": 118582}, {"basis": "reported", "evidence_url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md", "population": "RL collection", "qualifier": "exact", "unit": "executable tasks", "value": 2475}], "evidence_urls": ["https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md"], "formats": ["JSON", "JSONL", "PNG"], "modalities": ["screenshots", "text", "tool calls"], "notes": "These are publisher-reported totals at three distinct grains, not values to sum. Earlier screenshots may be collapsed; each SFT example keeps at most three images. The card and repository disagree on the singular/plural RL filename, so consumers should inspect the actual file manifest.", "splits": ["sft/train", "rl/train"], "supervision": ["next-action supervision", "verifiable task outcomes"]}}, "environments": ["android", "web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:51Z", "role": "primary", "sha256": "abacf9a10759a9e7a8eeec5a266c96ed83742bd9296a19be95d09c9717e18b7c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:10Z", "role": "primary", "sha256": "485279038266d9454df75e27a80a0a0d71c24e90700126d2dcfa0da921b1273d", "supports": ["relations", "environments"], "url": "https://raw.githubusercontent.com/OpenMobile2/OpenMobile2-Code/HEAD/README.md"}, {"method": "huggingface_repository_identity", "retrieved_at": "2026-10-17T19:15:18Z", "role": "primary", "sha256": "14b1211ed709147f4022f311c17303ca70faaffa22be143617eb431d966eec1a", "supports": ["aliases"], "url": "https://huggingface.co/api/datasets/OpenMobile-2/OpenMobile-Data"}, {"method": "huggingface_repository_identity", "retrieved_at": "2026-10-17T19:15:20Z", "role": "primary", "sha256": "14b1211ed709147f4022f311c17303ca70faaffa22be143617eb431d966eec1a", "supports": ["aliases"], "url": "https://huggingface.co/api/datasets/OpenMobile-2/OpenMobile-Data-v2"}], "id": "url:546e6c95825d1318c98d", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-17T01:48:51Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2"}], "name": "OpenMobile-Data-v2", "notes": "The reviewed card contains no explicit license declaration, so data-license status remains unknown. The repository code license is not inherited. The current code README points to the v2 dataset; an older project-page URL was not counted as a separate asset.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/OpenMobile2/OpenMobile2-Code/HEAD/README.md", "target_id": "arxiv:2610.14157", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile-agent supervision from emulator and simulator trajectories, plus executable tasks with starting states and success checks for reinforcement learning.", "topics": ["mobile-navigation", "data-generation", "reinforcement-learning", "tool-integration"], "updated_at": null, "url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2"}
{"aliases": [], "authors": [], "details": {"availability": "Ungated Parquet annotation files for train, validation, test and test_unseen_os; videos external.", "dataset_profile": {"counts": [{"basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "train split", "qualifier": "exact", "unit": "video annotation records", "value": 19725}, {"basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "validation split", "qualifier": "exact", "unit": "video annotation records", "value": 495}, {"basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "test split", "qualifier": "exact", "unit": "video annotation records", "value": 100}, {"basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "test_unseen_os split", "qualifier": "exact", "unit": "video annotation records", "value": 50}, {"basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "publisher overview of MONDAY", "qualifier": "approximately", "unit": "detected scenes", "value": 333000}, {"basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "publisher overview of MONDAY", "qualifier": "approximately", "unit": "identified actions", "value": 313000}], "evidence_urls": ["https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "https://raw.githubusercontent.com/runamu/monday/HEAD/README.md"], "formats": ["Parquet"], "modalities": ["text", "timestamps", "bounding boxes", "action labels"], "notes": "Split counts are video-annotation rows; scene and action totals are rounded publisher reports and are not added to row counts. Source videos/images are not included in the Hub files.", "splits": ["train", "validation", "test", "test_unseen_os"], "supervision": ["video-derived scene and action annotations"]}, "license_review": {"data": {"evidence_urls": ["https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "https://raw.githubusercontent.com/runamu/monday/HEAD/README.md", "https://raw.githubusercontent.com/runamu/monday/HEAD/LICENSE"], "reason": "No dataset-license declaration in the inspected card; Apache-2.0 applies to companion code and is not transferred to YouTube content or this annotation package."}}, "release_revision": "d7bd929cf629bf0767f154cbdd984eea1eba01e9"}, "environments": ["android", "ios"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:07Z", "role": "primary", "sha256": "62a346fd0d328deb5b56a652c8581850b0c8120f5c77e53b33f24b9baf937adb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details.dataset_profile", "licenses.data"], "url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:07Z", "role": "primary", "sha256": "f55c319a70c8ff988049363dc8fc266a9f1b1a09b8ac7096ee573f962e8f9492", "supports": ["identity", "release_status", "details.release_revision"], "url": "https://huggingface.co/api/datasets/runamu/MONDAY"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:53Z", "role": "primary", "sha256": "cb3d2329571a80b6edeab98c04f8b63c7f4e976929788d6a8283238b0b7fdadc", "supports": ["notes", "details.dataset_profile", "licenses.data"], "url": "https://raw.githubusercontent.com/runamu/monday/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:34:09Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["notes", "licenses.data"], "url": "https://raw.githubusercontent.com/runamu/monday/HEAD/LICENSE"}], "id": "url:570654ff67ecefa2b955", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-17T12:32:07Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/runamu/MONDAY"}], "name": "MONDAY annotations", "notes": "The ungated Hub publishes four Parquet splits containing video identifiers and annotations. Original videos and extracted screenshots must be obtained separately; the code README explains that consumers download source videos from YouTube. A Windows Mobile unseen-OS test split is documented but is not labeled desktop Windows here. The companion code has an Apache-2.0 file, while the data card declares no data license and the repository defers third-party materials to original terms. Training scripts, pretrained checkpoints and the full generation pipeline remain planned updates.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "target_id": "arxiv:2505.12632", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Video-derived mobile navigation annotations that pair scene boundaries and screen or element boxes with action labels for training and evaluating GUI agents.", "topics": ["data-generation", "mobile-navigation", "video", "imitation-learning"], "updated_at": null, "url": "https://huggingface.co/datasets/runamu/MONDAY"}
{"aliases": [], "authors": [], "details": {"disabled": false, "download_url": "https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B/tree/main", "gated": false, "hub_id": "HanXiao1999/UI-Genie-Agent-7B"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:03:41Z", "role": "primary", "sha256": "3d4e2deda3e8ecc2e6bbba732c01a84dee2443bb7132ef1aeae444f001d23d69", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:03:41Z", "role": "primary", "sha256": "20e47378595ed007766a135c37fe6709d8853a780ecd5ef56792f0b88c05aeff", "supports": ["identity", "release_status", "details", "licenses.weights"], "url": "https://huggingface.co/api/models/HanXiao1999/UI-Genie-Agent-7B"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T04:03:41Z", "role": "primary", "sha256": "3d4e2deda3e8ecc2e6bbba732c01a84dee2443bb7132ef1aeae444f001d23d69", "supports": ["licenses.weights"], "url": "https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B/raw/main/README.md"}], "id": "url:6d959b58bd4a2e98e417", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-17T04:03:41Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-17T04:03:41Z", "url": "https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B/raw/main/README.md"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B"}], "name": "UI-Genie Agent 7B", "notes": "Four public safetensors shards are present and the card declares MIT. Its training-data metadata/link uses UI-Genie-Agent-5k while prose labels it 16k; no precise training-set relationship or count is asserted across those inconsistent references. Larger announced models are not counted as released.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B/raw/main/README.md", "target_id": "arxiv:2505.21496", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A Qwen2.5-VL mobile action model trained using existing and reward-guided synthetic trajectories from the UI-Genie framework.", "topics": ["mobile-navigation", "imitation-learning", "action-prediction"], "updated_at": null, "url": "https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B"}
{"aliases": [], "authors": [], "details": {"disabled": false, "download_url": "https://huggingface.co/OS-Copilot/OS-Genesis-7B-AC/tree/main", "gated": false, "hub_id": "OS-Copilot/OS-Genesis-7B-AC"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:03:41Z", "role": "primary", "sha256": "62de4360ad62165bd4dc37d5897d6f5f88813956dff33bac63a24ded50cca118", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/OS-Copilot/OS-Genesis-7B-AC/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:03:41Z", "role": "primary", "sha256": "c35278027cd0e36e2fbbba4861031eca2a52090f20b40fb5aa680b067bb13dac", "supports": ["identity", "release_status", "details", "licenses.weights"], "url": "https://huggingface.co/api/models/OS-Copilot/OS-Genesis-7B-AC"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T04:03:41Z", "role": "primary", "sha256": "62de4360ad62165bd4dc37d5897d6f5f88813956dff33bac63a24ded50cca118", "supports": ["licenses.weights"], "url": "https://huggingface.co/OS-Copilot/OS-Genesis-7B-AC/raw/main/README.md"}], "id": "url:80858580c1009eba0e98", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-17T04:03:41Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T04:03:41Z", "url": "https://huggingface.co/OS-Copilot/OS-Genesis-7B-AC/raw/main/README.md"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/OS-Copilot/OS-Genesis-7B-AC"}], "name": "OS-Genesis 7B AC", "notes": "Four public safetensors shards are present. The card declares Apache-2.0. This is the AC task-specific checkpoint; AndroidWorld and WebArena variants are separate releases and their results are not transferred to it.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/OS-Copilot/OS-Genesis-7B-AC/raw/main/README.md", "target_id": "arxiv:2412.19723", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "The AndroidControl-oriented Qwen2-VL checkpoint trained with mobile trajectories generated through OS-Genesis reverse task synthesis.", "topics": ["mobile-navigation", "action-prediction", "imitation-learning"], "updated_at": null, "url": "https://huggingface.co/OS-Copilot/OS-Genesis-7B-AC"}
{"aliases": [], "authors": [], "details": {"dataset_profile": {"counts": [], "evidence_urls": ["https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/raw/main/README.md", "https://raw.githubusercontent.com/Euphoria16/UI-Genie/HEAD/README.md"], "formats": ["JSONL"], "modalities": ["text"], "notes": "The public manifest contains reward_data.jsonl but no separately packaged image archive. The card declares MIT. The 517k identifier is not converted into a verified sample count, and complete image packaging is not inferred from the JSONL filename.", "splits": [], "supervision": ["trajectory rewards"]}, "disabled": false, "download_url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/tree/main", "gated": false, "hub_id": "HanXiao1999/UI-Genie-RM-517k"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "dddb70b2b6986525f3980cbe50c3241d17f840a81fda9715b01ac3b25dd35d63", "supports": ["name", "kind", "relations", "licenses.data"], "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:33Z", "role": "primary", "sha256": "ab4bf30b6188959f825f2747ca711b0f190dddfe1658319c881ca9c73be9ecc9", "supports": ["identity", "release_status", "details", "licenses.data"], "url": "https://huggingface.co/api/datasets/HanXiao1999/UI-Genie-RM-517k"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:54Z", "role": "primary", "sha256": "e08569bd9d8a6ff44537d4fe69243ddfeb8a41ae5c9f87ef84af50a67c64c726", "supports": ["summary", "environments", "topics", "scope"], "url": "https://raw.githubusercontent.com/Euphoria16/UI-Genie/HEAD/README.md"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "dddb70b2b6986525f3980cbe50c3241d17f840a81fda9715b01ac3b25dd35d63", "supports": ["licenses.data"], "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/raw/main/README.md"}], "id": "url:84e5aeeffaf561baa966", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-17T04:01:34Z", "licenses": {"code": null, "data": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-17T04:01:34Z", "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/raw/main/README.md"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k"}], "name": "UI-Genie reward data", "notes": "The public manifest contains reward_data.jsonl but no separately packaged image archive. The card declares MIT. The 517k identifier is not converted into a verified sample count, and complete image packaging is not inferred from the JSONL filename.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/raw/main/README.md", "target_id": "arxiv:2505.21496", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile GUI reward annotations released for training UI-Genie’s trajectory-assessment model.", "topics": ["data-generation", "mobile-navigation", "reward-models"], "updated_at": null, "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k"}
{"aliases": [], "authors": [], "details": {"disabled": false, "download_url": "https://huggingface.co/openbmb/AgentCPM-GUI/tree/main", "gated": false, "hub_id": "openbmb/AgentCPM-GUI"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:03:33Z", "role": "primary", "sha256": "9016a68e833a7717c922d9363a6d6c56cc7cf6a7087543f5694507668fe9ab75", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/openbmb/AgentCPM-GUI/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:03:33Z", "role": "primary", "sha256": "4d76c8cc19f1ff4c850ba6cc566d50bbd2355e10921a2214e38c921cedfeed4c", "supports": ["identity", "release_status", "details", "licenses.weights"], "url": "https://huggingface.co/api/models/openbmb/AgentCPM-GUI"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T02:03:33Z", "role": "primary", "sha256": "9016a68e833a7717c922d9363a6d6c56cc7cf6a7087543f5694507668fe9ab75", "supports": ["licenses.weights"], "url": "https://huggingface.co/openbmb/AgentCPM-GUI/raw/main/README.md"}], "id": "url:8ef3985dce697e5feea9", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-17T02:03:33Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T02:03:33Z", "url": "https://huggingface.co/openbmb/AgentCPM-GUI/raw/main/README.md"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/openbmb/AgentCPM-GUI"}], "name": "AgentCPM-GUI 8B checkpoint", "notes": "The Hub provides four safetensors shards and associated model files without gating. Weight metadata declares Apache-2.0, while the prose license section refers specifically to code; these scopes are kept distinct. The card describes Android-app operation, and the CAGUI evaluation data remains a separate existing catalog asset.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/openbmb/AgentCPM-GUI/raw/main/README.md", "target_id": "arxiv:2506.01391", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "An eight-billion-parameter MiniCPM-V-based model that consumes smartphone screenshots and predicts compact actions for Chinese and English Android app tasks.", "topics": ["mobile-navigation", "grounding", "reinforcement-learning"], "updated_at": null, "url": "https://huggingface.co/openbmb/AgentCPM-GUI"}
{"aliases": [], "authors": ["Toby Jia-Jun Li", "Oriana Riva"], "details": {"publication": {"authors": ["Toby Jia-Jun Li", "Oriana Riva"], "date_basis": "Supplied month precision: 2018-06. Publication line: MobiSys 2018, June 2018", "date_parts": [2018, 6], "doi": "10.1145/3210240.3210339", "event_dates": null, "evidence_urls": ["https://www.microsoft.com/en-us/research/publication/kite-building-conversational-bots-mobile-apps/", "https://www.microsoft.com/en-us/research/wp-content/uploads/2018/05/kite_mobisys18.pdf"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Final proceedings page range and volume are not established in the retained first-party citation. The paper states a 14-page extent, not a page range. Exact publication day is unknown.", "pages": null, "pdf_url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2018/05/kite_mobisys18.pdf", "publisher": null, "series": null, "title": "Kite: Building Conversational Bots from Mobile Apps", "type": "conference-paper", "url": "https://doi.org/10.1145/3210240.3210339", "venue": "The 16th Annual International Conference on Mobile Systems, Applications, and Services", "volume": null}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:59:26Z", "role": "primary", "sha256": "e2f5403d77f563ec6a88458e32d057559a8f8ba4d2a80304e70c2c793fb60bb5", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.notes"], "url": "https://www.microsoft.com/en-us/research/publication/kite-building-conversational-bots-mobile-apps/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:59:27Z", "role": "primary", "sha256": "bfb67283f49dad7974d97e3b3da9d9ff24744d18e83c4d25cbe4f12ecf807071", "supports": ["details.publication.authors", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pdf_url", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2018/05/kite_mobisys18.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:59:27Z", "role": "primary", "sha256": "bfb67283f49dad7974d97e3b3da9d9ff24744d18e83c4d25cbe4f12ecf807071", "supports": ["details.publication.authors", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pdf_url", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue", "environments", "kind", "name", "scope", "summary", "topics"], "url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2018/05/kite_mobisys18.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:59:26Z", "role": "primary", "sha256": "e2f5403d77f563ec6a88458e32d057559a8f8ba4d2a80304e70c2c793fb60bb5", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.notes"], "url": "https://www.microsoft.com/en-us/research/publication/kite-building-conversational-bots-mobile-apps/"}], "id": "url:901ca855640457dfe2f1", "identifiers": {"doi": "10.1145/3210240.3210339"}, "kind": "paper", "last_verified_at": "2026-10-17T09:59:27Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://doi.org/10.1145/3210240.3210339"}, {"rel": "publication_pdf", "url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2018/05/kite_mobisys18.pdf"}], "name": "Kite: Building Conversational Bots from Mobile Apps", "notes": "The annotation was reviewed against retained primary publication sources. Experiments have not been independently reproduced. ", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Derives task graphs from demonstrated Android app interactions and layers a conversational question-answer interface over those graphs. The evaluation examines task-model extraction and developer use of the resulting bot templates.", "topics": ["mobile-navigation", "workflow", "human-in-the-loop"], "updated_at": null, "url": "https://doi.org/10.1145/3210240.3210339"}
{"aliases": [], "authors": [], "details": {"availability": "Public ungated JSON artifact is listed by the Hub manifest.", "dataset_profile": {"counts": [], "evidence_urls": ["https://huggingface.co/api/datasets/BlitherBoom/AutoDroid-V2-Dataset", "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/step_3_training/README.md"], "formats": ["JSON in ShareGPT conversation format"], "modalities": ["text"], "notes": "The card has license metadata only. The project training README supplies formatting and purpose. No sample count or split inventory is inferred from the training configuration.", "splits": [], "supervision": ["supervised conversations for AutoDroid-V2 fine-tuning"]}, "disabled": false, "download_url": "https://huggingface.co/datasets/BlitherBoom/AutoDroid-V2-Dataset/tree/main", "gated": false, "hub_id": "BlitherBoom/AutoDroid-V2-Dataset", "license_review": {"data": {"evidence_urls": ["https://huggingface.co/datasets/BlitherBoom/AutoDroid-V2-Dataset/raw/main/README.md"], "reason": "Publisher dataset-card license declaration; does not establish permissions for model weights or third-party application content."}}, "release_revision": "f041810dd32a2f2999647b7d4f4b8438482c01b8"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:15:33Z", "role": "primary", "sha256": "1b300edfbf44167da71639a56f8ab668dabd33769575fb313ebef5220fc1bddb", "supports": ["name", "kind", "identity", "release_status", "details.hub_id", "details.gated", "details.disabled", "details.release_revision", "details.availability", "details.download_url", "details.dataset_profile.modalities"], "url": "https://huggingface.co/api/datasets/BlitherBoom/AutoDroid-V2-Dataset"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:15:33Z", "role": "primary", "sha256": "d8d7a46d41a1a37fe4f0a5f637bf55c649310185329127d8a2204632e480be17", "supports": ["licenses.data"], "url": "https://huggingface.co/datasets/BlitherBoom/AutoDroid-V2-Dataset/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:58Z", "role": "primary", "sha256": "8ba37983a2c2da53d96a52696c07e4bdbea4e987a1a07b557935d614c3be46d2", "supports": ["summary", "topics", "scope", "notes", "details.dataset_profile", "relations"], "url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/step_3_training/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:58Z", "role": "primary", "sha256": "74508100843f8db6db6bb151e77ac1cc604a6b7ebd16d3225266d73434465136", "supports": ["environments", "topics", "scope"], "url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/README_minimal.md"}], "id": "url:9a3506ca6ef034adb424", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-17T09:15:33Z", "licenses": {"code": null, "data": {"basis": "Publisher dataset-card license declaration; does not establish permissions for model weights or third-party application content.", "declared": "mit", "retrieved_at": "2026-10-17T09:15:33Z", "url": "https://huggingface.co/datasets/BlitherBoom/AutoDroid-V2-Dataset/raw/main/README.md"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/BlitherBoom/AutoDroid-V2-Dataset"}], "name": "AutoDroid V2 training data", "notes": "The public Hub manifest lists AutoDroid-V2-Dataset.json; no training records were downloaded. The card contains only an MIT metadata declaration, so the description and intended training use come from the official repository training guide. Sample count, split sizes and third-party-content rights remain unverified; the training command max_samples value is not treated as a dataset count.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/step_3_training/README.md", "target_id": "github:mobilellm/autodroid-v2", "type": "component_of"}], "review_status": "curated", "scope": "core", "summary": "Conversation-formatted supervision released for fine-tuning AutoDroid V2, with the project documenting a ShareGPT-style JSON configuration.", "topics": ["data-generation", "imitation-learning", "mobile-navigation"], "updated_at": null, "url": "https://huggingface.co/datasets/BlitherBoom/AutoDroid-V2-Dataset"}
{"aliases": [], "authors": [], "details": {"disabled": false, "download_url": "https://huggingface.co/datasets/mllmTeam/DroidCall/tree/main", "gated": false, "hub_id": "mllmTeam/DroidCall", "license_review": {"data": {"evidence_urls": ["https://huggingface.co/datasets/mllmTeam/DroidCall/raw/main/README.md"], "reason": "The Hub dataset card declares Apache-2.0 in its metadata header (license: apache-2.0). The companion repository's MIT code license is a separate declaration."}}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:28Z", "role": "primary", "sha256": "08a6c5cfa655e1ecd774a41a9a815e845ad0afd47b289378bc1d6ee66c81dda9", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details", "licenses.data"], "url": "https://huggingface.co/datasets/mllmTeam/DroidCall/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:28Z", "role": "primary", "sha256": "c7804987d56b03314a4c48e3ddf2e5819fc0d9c83cc65ba54a981a2f4a584dd9", "supports": ["identity", "release_status", "details", "licenses.data"], "url": "https://huggingface.co/api/datasets/mllmTeam/DroidCall"}], "id": "url:ae8f5208eea9e7f1f606", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-17T02:02:28Z", "licenses": {"code": null, "data": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T02:02:28Z", "url": "https://huggingface.co/datasets/mllmTeam/DroidCall/raw/main/README.md"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/mllmTeam/DroidCall"}], "name": "DroidCall data", "notes": "The release provides JSONL data and API annotations. This is Android intent-calling supervision rather than screenshot-and-click trajectories, so it is marked adjacent. The dataset card declares Apache-2.0; the companion repository’s MIT code license is a separate declaration.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/datasets/mllmTeam/DroidCall/raw/main/README.md", "target_id": "arxiv:2412.00402", "type": "documented_by"}], "review_status": "curated", "scope": "adjacent", "summary": "Instruction-to-function-call examples for learning Android intent invocation, with training, testing and API-annotation files for mobile task execution.", "topics": ["mobile-navigation", "tool-integration", "data-generation"], "updated_at": null, "url": "https://huggingface.co/datasets/mllmTeam/DroidCall"}
{"aliases": [], "authors": [], "details": {"availability": "Ungated v1.0 JSON task-definition file.", "benchmark_protocol": {"actions": ["mobile GUI actions through a separately configured agent"], "counts": [{"basis": "reported", "evidence_url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md", "population": "MobBench tasks used in the paper", "qualifier": "exact", "unit": "tasks", "value": 50}], "evaluation": "The publisher reports a fifty-task real-device evaluation; the inspected release does not establish an automatic correctness judge.", "evidence_urls": ["https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md"], "focus": ["mobile task completion"], "notes": "Task definitions are distinct from device images, agent execution and automated scoring.", "observations": ["Android device interface"], "setting": "interactive"}, "license_review": {"data": {"evidence_urls": ["https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md"], "reason": "Dataset-card declaration for the MobBench task-definition release only."}}, "release_revision": "28941d10c49a16efb991d4157e512e14204bf3d6"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:07Z", "role": "primary", "sha256": "231a8f483256c774840c99383ab6536520a0aed0f04d62b4d64f1f59477b906e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details.benchmark_protocol", "licenses.data"], "url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:07Z", "role": "primary", "sha256": "4e7225f956d7cee98fe671e7bfd91fc407d87dd805d8f0c11c3b0c839714ccf3", "supports": ["identity", "release_status", "details.release_revision"], "url": "https://huggingface.co/api/datasets/OpenDFM/MobA-MobBench"}], "id": "url:b53e03a6e4ca4226d126", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-17T12:32:07Z", "licenses": {"code": null, "data": {"basis": "Dataset-card declaration for the MobBench task-definition release only.", "declared": "cc-by-nc-sa-4.0", "retrieved_at": "2026-10-17T12:32:07Z", "url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench"}], "name": "MobBench task definitions", "notes": "The ungated manifest lists MobBench_tasks_release_v1.0.json and bilingual cards. The card reports fifty tasks; no sample records were downloaded to recount them. This release supplies task definitions and agent setup guidance, not an independently verified automatic judge or a bundled Android environment. The data card declares CC-BY-NC-SA-4.0; code and model licenses are separate.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md", "target_id": "arxiv:2410.13757", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A public set of real-device mobile task definitions used to evaluate MobA, with Chinese and English task material packaged in a versioned JSON release.", "topics": ["evaluation", "mobile-navigation"], "updated_at": null, "url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench"}
{"aliases": [], "authors": ["Toby Jia-Jun Li", "Igor Labutov", "Xiaohan Nancy Li", "Xiaoyi Zhang", "Wenze Shi", "Wanling Ding", "Tom M. Mitchell", "Brad A. Myers"], "details": {"publication": {"authors": ["Toby Jia-Jun Li", "Igor Labutov", "Xiaohan Nancy Li", "Xiaoyi Zhang", "Wenze Shi", "Wanling Ding", "Tom M. Mitchell", "Brad A. Myers"], "date_basis": "Supplied year precision: 2018. APPINITE publication citation: VL/HCC 2018", "date_parts": [2018], "doi": null, "event_dates": null, "evidence_urls": ["https://toby.li/files/TobyLi-VLHCC18-APPINITE.pdf", "https://www.cs.cmu.edu/~NatProg/sugilite.html", "https://toby.li/publications/"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The base SUGILITE framework and later PUMICE work are distinct publications; this paper focuses on resolving data-description ambiguity in demonstrations. Author-hosted manuscript and institutional publication lists supply the retained evidence. DOI, final page range, and exact publication day remain unknown.", "pages": null, "pdf_url": "https://toby.li/files/TobyLi-VLHCC18-APPINITE.pdf", "publisher": null, "series": null, "title": "APPINITE: A Multi-Modal Interface for Specifying Data Descriptions in Programming by Demonstration Using Natural Language Instructions", "type": "conference-paper", "url": "https://ieeexplore.ieee.org/document/8506506", "venue": "Proceedings of the 2018 IEEE Symposium on Visual Languages and Human-Centric Computing", "volume": null}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:54:46Z", "role": "primary", "sha256": "6e05fd08b187adba32148e0835ef6b9e20cd6a3ba5e0de6e2778eb18c02788ee", "supports": ["details.publication.authors", "details.publication.identity_basis", "details.publication.notes", "details.publication.pdf_url", "details.publication.title"], "url": "https://toby.li/files/TobyLi-VLHCC18-APPINITE.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:22Z", "role": "primary", "sha256": "32ee05ff1a91ed4a22d4bc156a462872aa4e28f5c79abfbce5dbf3655f412033", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.notes", "details.publication.type", "details.publication.venue"], "url": "https://www.cs.cmu.edu/~NatProg/sugilite.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:55:20Z", "role": "primary", "sha256": "adfcec73830b612b181d4846ace3fbaab1768e906715c1d90fe657e23fe4d985", "supports": ["details.publication.identity_basis", "details.publication.notes", "details.publication.url"], "url": "https://toby.li/publications/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:54:46Z", "role": "primary", "sha256": "6e05fd08b187adba32148e0835ef6b9e20cd6a3ba5e0de6e2778eb18c02788ee", "supports": ["details.publication.authors", "details.publication.identity_basis", "details.publication.notes", "details.publication.pdf_url", "details.publication.title", "environments", "name", "scope", "summary", "topics"], "url": "https://toby.li/files/TobyLi-VLHCC18-APPINITE.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:22Z", "role": "primary", "sha256": "32ee05ff1a91ed4a22d4bc156a462872aa4e28f5c79abfbce5dbf3655f412033", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.notes", "details.publication.type", "details.publication.venue", "kind"], "url": "https://www.cs.cmu.edu/~NatProg/sugilite.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:55:20Z", "role": "primary", "sha256": "adfcec73830b612b181d4846ace3fbaab1768e906715c1d90fe657e23fe4d985", "supports": ["details.publication.identity_basis", "details.publication.notes", "details.publication.url"], "url": "https://toby.li/publications/"}], "id": "url:ba2c664c1b3c6f1b172f", "identifiers": {}, "kind": "paper", "last_verified_at": "2026-10-17T09:54:46Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://ieeexplore.ieee.org/document/8506506"}, {"rel": "publication_pdf", "url": "https://toby.li/files/TobyLi-VLHCC18-APPINITE.pdf"}], "name": "APPINITE: A Multi-Modal Interface for Specifying Data Descriptions in Programming by Demonstration Using Natural Language Instructions", "notes": "The annotation was reviewed against retained primary publication sources. Experiments have not been independently reproduced. The base SUGILITE framework and later PUMICE work are distinct publications; this paper focuses on resolving data-description ambiguity in demonstrations.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces APPINITE, a conversational interface for specifying the intended targets of demonstrated Android actions. It constructs semantic UI representations and uses an on-screen overlay to preview and refine executable data descriptions.", "topics": ["grounding", "human-in-the-loop", "mobile-navigation"], "updated_at": null, "url": "https://ieeexplore.ieee.org/document/8506506"}
{"aliases": [], "authors": [], "details": {"artifact_type": "model-checkpoint", "disabled": false, "download_url": "https://huggingface.co/zai-org/AutoGLM-Phone-9B/tree/main", "gated": false, "hub_id": "zai-org/AutoGLM-Phone-9B", "languages": ["zh"], "modalities": [], "size_category_reported": null}, "environments": ["android", "ios"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:50:49Z", "role": "primary", "sha256": "94b02fa7104849cedee8ddd1fa33e22d3039e05ae9dd03033805a000e3fed847", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/api/models/zai-org/AutoGLM-Phone-9B"}, {"method": "huggingface_api", "retrieved_at": "2026-10-16T06:50:49Z", "role": "primary", "sha256": "94b02fa7104849cedee8ddd1fa33e22d3039e05ae9dd03033805a000e3fed847", "supports": ["details", "licenses.weights"], "url": "https://huggingface.co/api/models/zai-org/AutoGLM-Phone-9B"}], "id": "url:c918d5c828a3c6cfbc5d", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-16T06:50:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card", "declared": "mit", "retrieved_at": "2026-10-16T06:50:49Z", "url": "https://huggingface.co/zai-org/AutoGLM-Phone-9B"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/zai-org/AutoGLM-Phone-9B"}], "name": "AutoGLM Phone 9B", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/api/models/zai-org/AutoGLM-Phone-9B", "target_id": "github:zai-org/open-autoglm", "type": "variant_of"}], "review_status": "curated", "scope": "core", "summary": "AutoGLM phone-agent checkpoint for Open-AutoGLM, fine-tuned from GLM-4.1V-9B-Base with about 10.3B BF16 parameters and tagged for Chinese.", "topics": ["mobile-navigation"], "updated_at": null, "url": "https://huggingface.co/zai-org/AutoGLM-Phone-9B"}
{"aliases": [], "authors": [], "details": {"artifact_type": "model-checkpoint", "disabled": false, "download_url": "https://huggingface.co/zai-org/AutoGLM-Phone-9B-Multilingual/tree/main", "gated": false, "hub_id": "zai-org/AutoGLM-Phone-9B-Multilingual", "languages": ["zh"], "modalities": [], "size_category_reported": null}, "environments": ["android", "ios"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:50:49Z", "role": "primary", "sha256": "d66bc86d9fb61f88d1456b36cb0c2c9ab5e178b55bc9d34f307b35733f9b90bc", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/api/models/zai-org/AutoGLM-Phone-9B-Multilingual"}, {"method": "huggingface_api", "retrieved_at": "2026-10-16T06:50:49Z", "role": "primary", "sha256": "d66bc86d9fb61f88d1456b36cb0c2c9ab5e178b55bc9d34f307b35733f9b90bc", "supports": ["details", "licenses.weights"], "url": "https://huggingface.co/api/models/zai-org/AutoGLM-Phone-9B-Multilingual"}], "id": "url:d236e7ec7a2b0028950a", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-16T06:50:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card", "declared": "mit", "retrieved_at": "2026-10-16T06:50:49Z", "url": "https://huggingface.co/zai-org/AutoGLM-Phone-9B-Multilingual"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/zai-org/AutoGLM-Phone-9B-Multilingual"}], "name": "AutoGLM Phone 9B Multilingual", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/api/models/zai-org/AutoGLM-Phone-9B-Multilingual", "target_id": "github:zai-org/open-autoglm", "type": "variant_of"}], "review_status": "curated", "scope": "core", "summary": "Multilingual variant of the AutoGLM phone-agent checkpoint for Open-AutoGLM, likewise fine-tuned from GLM-4.1V-9B-Base with about 10.3B BF16 parameters.", "topics": ["mobile-navigation"], "updated_at": null, "url": "https://huggingface.co/zai-org/AutoGLM-Phone-9B-Multilingual"}
{"aliases": [], "authors": [], "details": {"artifact_inspection": "Public file-manifest inspection only; weights were not downloaded.", "base_model": "Qwen/Qwen3.5-9B", "gated": false, "hub_revision": "68ebbac4d5bdf725103a22d076122b8aa883a0f2", "listed_weight_files": ["model.safetensors"]}, "environments": ["android", "web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:51Z", "role": "primary", "sha256": "09c59e6b35a5fe1eea528595f326546269ea8a2a75aa404f1f7950b9de5f30d1", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-9B/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:49:48Z", "role": "primary", "sha256": "1aab6befd309e54ba71676670039b4098362974ce0ce89b25872f137d50c103f", "supports": ["details.gated", "details.hub_revision", "details.listed_weight_files"], "url": "https://huggingface.co/api/models/OpenMobile-2/OpenMobile-2-9B"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:46:06Z", "role": "primary", "sha256": "9b385e9f6aa2f7169f616a76887df3b76df605cb2bea071d99ee7ca3f9b659cc", "supports": ["environments"], "url": "https://os-copilot.github.io/OpenMobile2-Home/"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T01:48:51Z", "role": "primary", "sha256": "09c59e6b35a5fe1eea528595f326546269ea8a2a75aa404f1f7950b9de5f30d1", "supports": ["licenses.weights"], "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-9B/raw/main/README.md"}], "id": "url:d35224f787e7ec21ce36", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-17T01:48:51Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T01:48:51Z", "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-9B/raw/main/README.md"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-9B"}], "name": "OpenMobile-2 9B", "notes": "The public Hub manifest lists weight files; the catalog did not download weights or reproduce inference. License declarations apply to this checkpoint separately from code and training data.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-9B/raw/main/README.md", "target_id": "github:openmobile2/openmobile2-code", "type": "variant_of"}, {"evidence_url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-9B/raw/main/README.md", "target_id": "url:546e6c95825d1318c98d", "type": "trained_on"}, {"evidence_url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-9B/raw/main/README.md", "target_id": "arxiv:2610.14157", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile-agent checkpoint trained on OpenMobile-Data-v2 for screenshot actions and app-native tool calls.", "topics": ["mobile-navigation", "tool-integration"], "updated_at": null, "url": "https://huggingface.co/OpenMobile-2/OpenMobile-2-9B"}
{"aliases": [], "authors": [], "details": {"dataset_profile": {"counts": [], "evidence_urls": ["https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/raw/main/README.md", "https://huggingface.co/api/datasets/OS-Copilot/OS-Genesis-mobile-data", "https://raw.githubusercontent.com/OS-Copilot/OS-Genesis/HEAD/README.md"], "formats": ["JSONL", "ZIP"], "modalities": ["screenshots", "text", "actions"], "notes": "AC and AW refer to distinct target training sets; no sample count is inferred from the two JSONL files or ZIP packaging.", "splits": ["AndroidControl training", "AndroidWorld training"], "supervision": ["mobile action trajectories"]}, "disabled": false, "download_url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/tree/main", "gated": false, "hub_id": "OS-Copilot/OS-Genesis-mobile-data"}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "de9de63e21e60e882277a6268e8153abb6c14aaf3e9a7f83e7f98ac14bf37170", "supports": ["name", "kind", "relations", "licenses.data"], "url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:33Z", "role": "primary", "sha256": "6a5e0c2baecc2dc8bf4466903798f5ecda07cdac917042bbd4cfbe54d895c11e", "supports": ["identity", "release_status", "details", "licenses.data"], "url": "https://huggingface.co/api/datasets/OS-Copilot/OS-Genesis-mobile-data"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "430e495ab250395d666854bd18b0fc29b819cd784cd7730215ef65e461834d0d", "supports": ["summary", "environments", "topics", "scope"], "url": "https://raw.githubusercontent.com/OS-Copilot/OS-Genesis/HEAD/README.md"}, {"method": "huggingface_card", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "de9de63e21e60e882277a6268e8153abb6c14aaf3e9a7f83e7f98ac14bf37170", "supports": ["licenses.data"], "url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/raw/main/README.md"}], "id": "url:d3ec5122a2b52fd5ae4b", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-17T04:01:34Z", "licenses": {"code": null, "data": {"basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-17T04:01:34Z", "url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/raw/main/README.md"}, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data"}], "name": "OS-Genesis mobile training data", "notes": "The public manifest contains AC/AW JSONL training annotations and a screenshot archive. MIT is declared for the data in its own card, separately from Apache-2.0 declarations on some model checkpoints. The gated web-data release is not included in this asset.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/raw/main/README.md", "target_id": "arxiv:2412.19723", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Reverse-task-synthesis mobile trajectories released in separate AndroidControl and AndroidWorld training annotation files.", "topics": ["data-generation", "mobile-navigation", "imitation-learning"], "updated_at": null, "url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data"}
{"aliases": [], "authors": [], "details": {"disabled": false, "download_url": "https://huggingface.co/xuyifan/MobileRL-9B/tree/main", "gated": false, "hub_id": "xuyifan/MobileRL-9B", "languages": ["en"], "modalities": [], "size_category_reported": null}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:03:40Z", "role": "primary", "sha256": "a00f13f5a86f2de7eb9c866cc4d08b958d21b2ac30dc3b9e1662e4bb336b7cb3", "supports": ["name", "kind", "relations", "licenses.weights", "identity", "release_status", "details"], "url": "https://huggingface.co/api/models/xuyifan/MobileRL-9B"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:03:41Z", "role": "primary", "sha256": "5c2d5eb247958f1af0646cbac831ecfbc7f839baa236a0d733075592da81f58e", "supports": ["licenses.weights"], "url": "https://huggingface.co/xuyifan/MobileRL-9B/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:04Z", "role": "primary", "sha256": "752fad8ebd8b8eda03648329a6fc2585e5bcb2b96875b8aa2ce7d9f3fff78153", "supports": ["summary", "environments", "relations", "topics", "scope"], "url": "https://raw.githubusercontent.com/THUDM/MobileRL/HEAD/README.md"}, {"method": "huggingface_api", "retrieved_at": "2026-10-17T04:03:40Z", "role": "primary", "sha256": "a00f13f5a86f2de7eb9c866cc4d08b958d21b2ac30dc3b9e1662e4bb336b7cb3", "supports": ["details", "licenses.weights"], "url": "https://huggingface.co/api/models/xuyifan/MobileRL-9B"}], "id": "url:d5667c854845c77b9f5b", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-17T04:03:40Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card", "declared": "apache-2.0", "retrieved_at": "2026-10-17T04:03:40Z", "url": "https://huggingface.co/xuyifan/MobileRL-9B"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/xuyifan/MobileRL-9B"}], "name": "MobileRL 9B checkpoint", "notes": "Five public safetensors shards are present. The short card declares Apache-2.0 and a GLM-4.1V-9B base. The official project confirms the checkpoint and Android targets, and distinguishes MobileRL bounding-box actions from coordinate-format alternatives.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/THUDM/MobileRL/HEAD/README.md", "target_id": "arxiv:2509.18119", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "A GLM-4.1V-based mobile action checkpoint released by the MobileRL project for Android interaction.", "topics": ["reinforcement-learning", "mobile-navigation"], "updated_at": null, "url": "https://huggingface.co/xuyifan/MobileRL-9B"}
{"aliases": [], "authors": [], "details": {"benchmark_protocol": {"actions": ["mobile interface operations", "clarification requests"], "counts": [{"basis": "reported", "evidence_url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md", "population": "MobileGUI-VBench release", "qualifier": "exact", "unit": "tasks", "value": 150}, {"basis": "reported", "evidence_url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md", "population": "MobileGUI-VBench release", "qualifier": "exact", "unit": "mobile apps", "value": 40}], "evaluation": "Published task definitions include preconditions and clarification requirements; the metadata review does not independently validate the reported agent scores.", "evidence_urls": ["https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md"], "focus": ["mobile task completion", "clarification behavior", "cross-app tasks"], "notes": "The card describes 140 single-app and 10 cross-app tasks. Task and app counts are different units.", "observations": ["mobile app interfaces"], "setting": "interactive"}, "disabled": false, "download_url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/tree/main", "gated": false, "hub_id": "vivo-ai/MobileGUI-VBench"}, "environments": ["unspecified"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:42:32Z", "role": "primary", "sha256": "422ff6a557a1aabd8f6c6ef26e5fd05b992f4acf0e5128ab8bc437021fcc5ea7", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:42:32Z", "role": "primary", "sha256": "5850fc58f54c877cffe328dba2a0b5e3e98767637aae6d6efd9a037cf06eabce", "supports": ["identity", "release_status", "details", "licenses.data"], "url": "https://huggingface.co/api/datasets/vivo-ai/MobileGUI-VBench"}], "id": "url:d7a4f34a6a5202af5f64", "identifiers": {}, "kind": "benchmark", "last_verified_at": "2026-10-17T02:42:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench"}], "name": "MobileGUI-VBench", "notes": "Public task files are available as JSONL and XLSX with documentation. The card explicitly declares Apache-2.0 for the dataset, despite having no license field in its YAML metadata. It identifies mobile apps without fixing an operating-system taxonomy; model scores are not imported.", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md", "target_id": "arxiv:2609.12394", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Mobile-app task definitions covering everyday scenarios, with annotated preconditions and clarification requirements for evaluating agent behavior.", "topics": ["evaluation", "mobile-navigation", "cross-app"], "updated_at": null, "url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench"}
{"aliases": [], "authors": [], "details": {"artifact_type": "model-checkpoint", "disabled": false, "download_url": "https://huggingface.co/stepfun-ai/GELab-Zero-4B-preview/tree/main", "gated": false, "hub_id": "stepfun-ai/GELab-Zero-4B-preview", "languages": ["en", "zh"], "modalities": [], "size_category_reported": null}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:50:49Z", "role": "primary", "sha256": "cd1efa947316f13967165ac906400170df6d28446804ba0763a49fc21a731e7e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://huggingface.co/api/models/stepfun-ai/GELab-Zero-4B-preview"}, {"method": "huggingface_api", "retrieved_at": "2026-10-16T06:50:49Z", "role": "primary", "sha256": "cd1efa947316f13967165ac906400170df6d28446804ba0763a49fc21a731e7e", "supports": ["details", "licenses.weights"], "url": "https://huggingface.co/api/models/stepfun-ai/GELab-Zero-4B-preview"}], "id": "url:d7ad447ecd712c6d51b8", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-16T06:50:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": {"basis": "publisher model/dataset card", "declared": "apache-2.0", "retrieved_at": "2026-10-16T06:50:49Z", "url": "https://huggingface.co/stepfun-ai/GELab-Zero-4B-preview"}}, "links": [{"rel": "primary", "url": "https://huggingface.co/stepfun-ai/GELab-Zero-4B-preview"}], "name": "GELab Zero 4B Preview", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://huggingface.co/api/models/stepfun-ai/GELab-Zero-4B-preview", "target_id": "github:stepfun-ai/gelab-zero", "type": "variant_of"}], "review_status": "curated", "scope": "core", "summary": "Preview GELab-Zero phone-use agent checkpoint fine-tuned from Qwen3-VL-4B-Instruct, with about 4.4B BF16 parameters, tagged for Android in English and Chinese, under Apache-2.0.", "topics": ["mobile-navigation"], "updated_at": null, "url": "https://huggingface.co/stepfun-ai/GELab-Zero-4B-preview"}