{"aliases": [], "authors": ["Peter C Humphreys", "David Raposo", "Toby Pohlen", "Gregory Thornton", "Rachita Chhaparia", "Alistair Muldal", "Josh Abramson", "Petko Georgiev", "Alex Goldin", "Adam Santoro", "Timothy Lillicrap"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "94129847ac85f4a8aeab74907cc68a31c435b078ab950695d9328b6c3896b46d", "submitted_at": "2022-02-16T15:23:46Z", "updated_at": "2022-11-11T13:45:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2202.08137v2"}, "publication": {"authors": ["Peter Humphreys", "David Raposo", "Toby Pohlen", "Gregory Thornton", "Rachita Chhaparia", "Alistair Muldal", "Josh Abramson", "Petko Georgiev", "Adam Santoro", "Timothy Lillicrap"], "date_basis": "Explicit publisher metadata: 2022/06/28; precision=day.", "date_parts": [2022, 6, 28], "doi": null, "event_dates": "17--23 Jul 2022", "evidence_urls": ["https://proceedings.mlr.press/v162/humphreys22a.html", "https://proceedings.mlr.press/v162/humphreys22a/humphreys22a.pdf"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The formal ICML PDF lists 10 authors beginning Peter Humphreys and uses Toby Pohlen. The landing lists Peter C Humphreys and Tobias Pohlen. The retained arXiv snapshot lists 11 authors, including Alex Goldin. These are preserved as distinct version-specific author lists; the publication field uses only the formal PDF list. The publisher issue date comes from citation_publication_date; the conference date range is retained separately and does not replace it. Publisher issue date is 2022-06-28; the July 17–23 conference range is an event date, not a substitute publication day. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "9466-9482", "pdf_url": "https://proceedings.mlr.press/v162/humphreys22a/humphreys22a.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "A Data-Driven Approach for Learning to Control Computers", "type": "conference-paper", "url": "https://proceedings.mlr.press/v162/humphreys22a.html", "venue": "Proceedings of the 39th International Conference on Machine Learning", "volume": "162"}}, "environments": ["web"], "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": "2026-10-17T09:53:47+00:00", "role": "primary", "sha256": "b0ac6ec4bf3aad3773c53a0fffe8688a6287f25f28faf3743603ec2c1ae08a8b", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.event_dates", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.publisher", "details.publication.series", "details.publication.type", "details.publication.url", "details.publication.venue", "details.publication.volume"], "url": "https://proceedings.mlr.press/v162/humphreys22a.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:59:46+00:00", "role": "primary", "sha256": "ba2a9a0a5e46aa5f34cfc720ac08049253917407e2fbd4a8cdbd2c8ca3ec8455", "supports": ["details.publication.authors", "details.publication.identity_basis", "details.publication.notes", "details.publication.title"], "url": "https://proceedings.mlr.press/v162/humphreys22a/humphreys22a.pdf"}, {"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:2202.08137", "identifiers": {"arxiv": "2202.08137"}, "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/2202.08137"}, {"rel": "publication", "url": "https://proceedings.mlr.press/v162/humphreys22a.html"}, {"rel": "publication_pdf", "url": "https://proceedings.mlr.press/v162/humphreys22a/humphreys22a.pdf"}], "name": "A data-driven approach for learning to control computers", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2022-02-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines reinforcement learning with behavioral priors from human interactions to learn computer control through keyboard and mouse actions.", "topics": ["reinforcement-learning", "automation"], "updated_at": "2022-11-11", "url": "https://arxiv.org/abs/2202.08137"}
{"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": ["Zhizheng Zhang", "Xiaoyi Zhang", "Wenxuan Xie", "Yan Lu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "631a39d2929c68bb93a7f95af22c17d2ab208668fd97d9082fe0601a73d123dd", "submitted_at": "2023-06-02T02:42:58Z", "updated_at": "2023-12-04T13:36:59Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2306.01242v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:42:42Z", "role": "primary", "sha256": "d1c1bc3fee56d124427abd2aabbcf876418633a8adf7a03f4ef0317cba6a42ae", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2008.05132%2C2010.04295%2C2101.04893%2C2112.05692%2C2306.01242%2C2311.03079%2C2401.05459%2C2402.03746%2C2402.15506%2C2403.20329%2C2404.06395%2C2404.10179%2C2405.10292%2C2406.09187%2C2406.14596%2C2408.03326%2C2409.12089%2C2501.10893%2C2504.09352&max_results=19"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:42:42Z", "role": "primary", "sha256": "d1c1bc3fee56d124427abd2aabbcf876418633a8adf7a03f4ef0317cba6a42ae", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2008.05132%2C2010.04295%2C2101.04893%2C2112.05692%2C2306.01242%2C2311.03079%2C2401.05459%2C2402.03746%2C2402.15506%2C2403.20329%2C2404.06395%2C2404.10179%2C2405.10292%2C2406.09187%2C2406.14596%2C2408.03326%2C2409.12089%2C2501.10893%2C2504.09352&max_results=19"}], "id": "arxiv:2306.01242", "identifiers": {"arxiv": "2306.01242"}, "kind": "paper", "last_verified_at": "2026-10-16T06:42:42Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2306.01242"}], "name": "Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental findings and artifact availability have not been independently reproduced. UI task automation is stated in the abstract, but its platform and detailed evaluation protocol are not identified.", "published_at": "2023-06-02", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Presents ResponsibleTA, a coordinator-executor framework that checks command feasibility and task completion while using local memory for privacy-related controls. The paper compares prompted and learned implementations and evaluates them on UI task automation.", "topics": ["safety-security", "evaluation", "automation"], "updated_at": "2023-12-04", "url": "https://arxiv.org/abs/2306.01242"}
{"aliases": [], "authors": ["Justin Payan", "Swaroop Mishra", "Mukul Singh", "Carina Negreanu", "Christian Poelitz", "Chitta Baral", "Subhro Roy", "Rasika Chakravarthy", "Benjamin Van Durme", "Elnaz Nouri"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1648acae2228b8ae2f042d7986585a66bc6a649320d569b12fd093b96c15cb5c", "submitted_at": "2023-10-23T02:00:55Z", "updated_at": "2023-10-23T02:00:55Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2310.14495v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T07:57:30Z", "role": "primary", "sha256": "4856a9c146f74964be623730f3cee6b15fcaad83f7d83a4956e971b541a63070", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2304.08479%2C2305.09699%2C2305.09770%2C2305.11271%2C2305.14343%2C2305.16338%2C2305.16985%2C2306.04529%2C2306.05499%2C2306.07179%2C2306.11134%2C2307.00804%2C2307.02443%2C2308.01552%2C2308.05391%2C2308.05822%2C2308.06595%2C2308.07201%2C2308.09289%2C2309.04561%2C2309.05251%2C2309.07550%2C2309.09958%2C2309.10094%2C2309.13965%2C2310.07433%2C2310.07899%2C2310.09103%2C2310.12670%2C2310.12793%2C2310.12815%2C2310.12945%2C2310.12972%2C2310.13345%2C2310.14495%2C2310.17596%2C2310.19805%2C2311.01011%2C2311.07215%2C2311.09227%2C2311.10538%2C2311.10751%2C2311.11261%2C2311.11855%2C2311.18492%2C2311.18760%2C2312.02976%2C2312.03815%2C2312.07424%2C2312.09238&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:11:47Z", "role": "primary", "sha256": "40fd8a31083963f1cbbcfeb308244494139277e4a6d0e56c2ebe5a7cda821e7c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/2310.14495v1"}], "id": "arxiv:2310.14495", "identifiers": {"arxiv": "2310.14495"}, "kind": "paper", "last_verified_at": "2026-10-17T09:11:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2310.14495"}], "name": "InstructExcel: A Benchmark for Natural Language Instruction in Excel", "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. This is an application-specific automation benchmark grounded in recorded Excel user actions. Its execution interface is OfficeScripts, so it is adjacent rather than a visual GUI navigation benchmark.", "published_at": "2023-10-23", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Introduces InstructExcel, a benchmark for generating Excel OfficeScripts from natural-language requests, built using scripts recorded from user actions and a collection of existing spreadsheets.", "topics": ["evaluation", "workflow", "automation"], "updated_at": "2023-10-23", "url": "https://arxiv.org/abs/2310.14495"}
{"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": ["Chaoyun Zhang", "Liqun Li", "Shilin He", "Xu Zhang", "Bo Qiao", "Si Qin", "Minghua Ma", "Yu Kang", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "533acb1c9aa3f1c77adb2c67779da86e3d5de95264ba3ec1f81d803f67da7753", "submitted_at": "2024-02-08T15:40:35Z", "updated_at": "2024-05-23T05:18:58Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2402.07939v5"}, "publication": {"authors": ["Chaoyun Zhang", "Liqun Li", "Shilin He", "Xu Zhang", "Bo Qiao", "Si Qin", "Minghua Ma", "Yu Kang", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang"], "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.26", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.naacl-long.26/"], "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": "597-622", "pdf_url": "https://aclanthology.org/2025.naacl-long.26.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "UFO: A UI-Focused Agent for Windows OS Interaction", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-long.26/", "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": ["windows", "desktop"], "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": "bbe15e312bcbc923811ef73e561fa7db6a7244ee3747bb9e3792e166b9327235", "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.26/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:24Z", "role": "primary", "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "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:2402.07939", "identifiers": {"arxiv": "2402.07939"}, "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/2402.07939"}, {"rel": "publication", "url": "https://aclanthology.org/2025.naacl-long.26/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2025.naacl-long.26.pdf"}], "name": "UFO: A UI-Focused Agent for Windows OS Interaction", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-02-08", "relations": [], "review_status": "curated", "scope": "core", "summary": "UFO uses two agents to inspect Windows application interfaces and their control metadata, then grounds and executes user requests within and across applications. The study evaluates this UI-focused architecture on nine Windows applications.", "topics": ["cross-app", "planning", "grounding", "automation"], "updated_at": "2024-05-23", "url": "https://arxiv.org/abs/2402.07939"}
{"aliases": [], "authors": ["Runliang Niu", "Jindong Li", "Shiqi Wang", "Yali Fu", "Xiyu Hu", "Xueyuan Leng", "He Kong", "Yi Chang", "Qi Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "63424a86302625b15a91ff0252ca16c0a6448160bfd748ba32e386c82883584e", "submitted_at": "2024-02-09T02:33:45Z", "updated_at": "2024-02-09T02:33:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2402.07945v1"}}, "environments": ["desktop"], "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:2402.07945", "identifiers": {"arxiv": "2402.07945"}, "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/2402.07945"}], "name": "ScreenAgent: A Vision Language Model-driven Computer Control 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": "2024-02-09", "relations": [], "review_status": "curated", "scope": "core", "summary": "Combines a screenshot-and-action dataset with a planning, acting, and reflecting loop for computer control through mouse and keyboard actions.", "topics": ["automation", "planning"], "updated_at": "2024-02-09", "url": "https://arxiv.org/abs/2402.07945"}
{"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": ["Chenhui Cui", "Tao Li", "Junjie Wang", "Chunyang Chen", "Dave Towey", "Rubing Huang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a844cdd06a32b8e89f362b7e924b36e27e72c1f1def81ed0b934f761ffcaba78", "submitted_at": "2024-04-13T09:56:50Z", "updated_at": "2026-06-25T14:05:55Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2404.08948v4"}}, "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:2404.08948", "identifiers": {"arxiv": "2404.08948"}, "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/2404.08948"}], "name": "Large Language Models for Mobile GUI Text Input Generation: An Empirical Study", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-04-13", "relations": [], "review_status": "curated", "scope": "core", "summary": "Studies language-model generation of mobile text inputs, comparing UI representations, execution feedback, and human assistance for app testing.", "topics": ["automation", "evaluation"], "updated_at": "2026-06-25", "url": "https://arxiv.org/abs/2404.08948"}
{"aliases": [], "authors": ["Zirui Song", "Yaohang Li", "Meng Fang", "Yanda Li", "Zhenhao Chen", "Zecheng Shi", "Yuan Huang", "Xiuying Chen", "Ling Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5e531ec2ef9e5d90586b8f3052e16d41da95114b7382047d0a02fd671a0db355", "submitted_at": "2024-04-28T05:33:15Z", "updated_at": "2025-03-23T13:04:57Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2404.18074v3"}}, "environments": ["desktop"], "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:2404.18074", "identifiers": {"arxiv": "2404.18074"}, "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/2404.18074"}], "name": "MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot", "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": "2024-04-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces MMAC-Copilot, which coordinates agents with different expertise to operate PC applications. VIBench evaluates visual interaction with applications that lack usable APIs, spanning office, recreation and game tasks.", "topics": ["automation", "evaluation", "planning"], "updated_at": "2025-03-23", "url": "https://arxiv.org/abs/2404.18074"}
{"aliases": [], "authors": ["Arushi Jain", "Shubham Paliwal", "Monika Sharma", "Lovekesh Vig", "Gautam Shroff"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ca8d7e7dc3a537573ac3990d532589cdca12bf441ee40521cc46044fd10c5263", "submitted_at": "2024-05-21T14:49:12Z", "updated_at": "2024-05-21T14:49:12Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2405.12842v1"}}, "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", "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:2405.12842", "identifiers": {"arxiv": "2405.12842"}, "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/2405.12842"}], "name": "SmartFlow: Robotic Process Automation using 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.", "published_at": "2024-05-21", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents SmartFlow, which converts visible GUI elements into text for language-model action planning and executes the plan through a scripting engine. A collection of enterprise applications evaluates adaptation to different layouts and tasks.", "topics": ["automation", "workflow", "screen-understanding"], "updated_at": "2024-05-21", "url": "https://arxiv.org/abs/2405.12842"}
{"aliases": [], "authors": ["Shengcheng Yu", "Chunrong Fang", "Mingzhe Du", "Zimin Ding", "Zhenyu Chen", "Zhendong Su"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0061e9004afe11bf188164ea37de1acd15e1b95ae2fcad22044264a89e4636b3", "submitted_at": "2024-06-12T15:48:39Z", "updated_at": "2024-06-12T15:48:39Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2406.08340v1"}}, "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:2406.08340", "identifiers": {"arxiv": "2406.08340"}, "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/2406.08340"}], "name": "Practical, Automated Scenario-based Mobile App Testing", "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": "ScenTest builds scenario-specific event knowledge graphs from crowdsourced test reports containing GUI and action information. It uses the current app state and testing context to generate scenario tests across applications.", "topics": ["automation", "cross-app", "screen-understanding", "evaluation"], "updated_at": "2024-06-12", "url": "https://arxiv.org/abs/2406.08340"}
{"aliases": [], "authors": ["Zhe Liu", "Cheng Li", "Chunyang Chen", "Junjie Wang", "Mengzhuo Chen", "Boyu Wu", "Yawen Wang", "Jun Hu", "Qing Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "73b706ac6089a7d19836268437f3fea58d10b9d170ac596ac0d5a12f0d3a9668", "submitted_at": "2024-07-03T11:58:09Z", "updated_at": "2024-12-04T08:00:42Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2407.03037v2"}}, "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:2407.03037", "identifiers": {"arxiv": "2407.03037"}, "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/2407.03037"}], "name": "Seeing is Believing: Vision-driven Non-crash Functional Bug Detection for Mobile 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": "2024-07-03", "relations": [], "review_status": "curated", "scope": "core", "summary": "Trident combines exploration, monitoring, and detection agents to identify functional bugs that do not crash a mobile app. It reasons over screenshot sequences and interface transitions to construct test oracles, evaluated on 590 non-crash bugs and additional live apps.", "topics": ["automation", "evaluation", "screen-understanding", "state-tracking"], "updated_at": "2024-12-04", "url": "https://arxiv.org/abs/2407.03037"}
{"aliases": [], "authors": ["Yongxiang Hu", "Xuan Wang", "Yingchuan Wang", "Yu Zhang", "Shiyu Guo", "Chaoyi Chen", "Xin Wang", "Yangfan Zhou"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a594fa7e150c9f5c22ed4d88f0551305f801f5780851ecf844802f2d2cd07c48", "submitted_at": "2024-07-12T06:14:46Z", "updated_at": "2024-07-12T06:14:46Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2407.09018v1"}}, "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:2407.09018", "identifiers": {"arxiv": "2407.09018"}, "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/2407.09018"}], "name": "AUITestAgent: Automatic Requirements Oriented GUI Function Testing", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-07-12", "relations": [], "review_status": "curated", "scope": "core", "summary": "Automates mobile GUI tests from natural-language requirements, combining action generation with verification based on interaction traces.", "topics": ["automation", "evaluation"], "updated_at": "2024-07-12", "url": "https://arxiv.org/abs/2407.09018"}
{"aliases": [], "authors": ["Segev Shlomov", "Avi Yaeli", "Sami Marreed", "Sivan Schwartz", "Netanel Eder", "Offer Akrabi", "Sergey Zeltyn"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4caa87e0b88d9375a23ca412ed19b3806f67712ca4ac222a39746e08ee80b07d", "submitted_at": "2024-07-22T14:41:32Z", "updated_at": "2024-08-18T09:02:43Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2407.15673v3"}}, "environments": ["web"], "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:2407.15673", "identifiers": {"arxiv": "2407.15673"}, "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/2407.15673"}], "name": "IDA: Breaking Barriers in No-code UI Automation Through Large Language Models and Human-Centric Design", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-07-22", "relations": [], "review_status": "curated", "scope": "core", "summary": "IDA helps business users create web UI automation through guided demonstrations, a semantic programming model, and a teaching-oriented interface. A prototype user study examines automation creation with enterprise applications by users without programming backgrounds.", "topics": ["human-in-the-loop", "automation", "workflow", "industry"], "updated_at": "2024-08-18", "url": "https://arxiv.org/abs/2407.15673"}
{"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": ["Mobina Shahbandeh", "Parsa Alian", "Noor Nashid", "Ali Mesbah"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5bdbd80e252cfa37dc62d666a202e647f93813549c55dde82daf36afe309c7f2", "submitted_at": "2024-09-16T21:18:39Z", "updated_at": "2024-09-16T21:18:39Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2409.10741v1"}}, "environments": ["web"], "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:2409.10741", "identifiers": {"arxiv": "2409.10741"}, "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/2409.10741"}], "name": "NaviQAte: Functionality-Guided Web Application 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": "2024-09-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "Frames web-application exploration as functionality-oriented question answering, generating navigation actions from multimodal context.", "topics": ["web-navigation", "automation"], "updated_at": "2024-09-16", "url": "https://arxiv.org/abs/2409.10741"}
{"aliases": [], "authors": ["Brian Tang", "Kang G. Shin"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "377d46c738f1a6f3e1c22ea99971a2fcfcf25ded82b2d2a24f728e614e22a1b3", "submitted_at": "2024-09-23T18:06:32Z", "updated_at": "2024-09-23T18:06:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2409.15441v1"}}, "environments": ["web"], "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:2409.15441", "identifiers": {"arxiv": "2409.15441"}, "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/2409.15441"}], "name": "Steward: Natural Language Web Automation", "notes": "Reviewed against the retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2024-09-23", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Steward, a natural-language browser automation system that repeatedly plans and executes website actions. The paper examines completion detection, state representation, responsiveness, and caching in real-site tasks.", "topics": ["web-navigation", "automation", "efficiency"], "updated_at": "2024-09-23", "url": "https://arxiv.org/abs/2409.15441"}
{"aliases": [], "authors": ["Junting Lu", "Zhiyang Zhang", "Fangkai Yang", "Jue Zhang", "Lu Wang", "Chao Du", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "618f41c2253a532780766b38396f241a48b587c580d6b4d7065d1519e6149751", "submitted_at": "2024-09-25T17:58:08Z", "updated_at": "2025-05-19T16:12:40Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.17140v2"}, "publication": {"authors": ["Junting Lu", "Zhiyang Zhang", "Fangkai Yang", "Jue Zhang", "Lu Wang", "Chao Du", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang"], "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.381", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.381/"], "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": "7711-7743", "pdf_url": "https://aclanthology.org/2025.acl-long.381.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.381/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}}, "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": "2026-10-18T04:09:52Z", "role": "primary", "sha256": "31ab26306d5c41b25731db1ad7f73495330e637c1694c9da644f4e238a73917b", "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.381/"}, {"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:2409.17140", "identifiers": {"arxiv": "2409.17140"}, "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/2409.17140"}, {"rel": "publication", "url": "https://aclanthology.org/2025.acl-long.381/"}, {"rel": "publication_pdf", "url": "https://aclanthology.org/2025.acl-long.381.pdf"}], "name": "AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents", "notes": "Reviewed against the retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2024-09-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces AXIS, an API-first application agent that can use UI actions and expand its available APIs through automated application exploration. The work evaluates the approach on Microsoft Word tasks.", "topics": ["tool-integration", "automation", "efficiency"], "updated_at": "2025-05-19", "url": "https://arxiv.org/abs/2409.17140"}
{"aliases": [], "authors": ["Chengyou Jia", "Minnan Luo", "Zhuohang Dang", "Qiushi Sun", "Fangzhi Xu", "Junlin Hu", "Tianbao Xie", "Zhiyong Wu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ece9f64cc037dad8633388edf1b54d88818d8092b77e19b15780e929b23aa593", "submitted_at": "2024-10-24T09:58:40Z", "updated_at": "2024-10-24T09:58:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2410.18603v1"}}, "environments": ["desktop"], "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:2410.18603", "identifiers": {"arxiv": "2410.18603"}, "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/2410.18603"}], "name": "AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer 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": "2024-10-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a platform that integrates specialized agents under a coordinating MetaAgent for varied computer tasks.", "topics": ["automation", "tool-integration"], "updated_at": "2024-10-24", "url": "https://arxiv.org/abs/2410.18603"}
{"aliases": [], "authors": ["Xiao Liu", "Bo Qin", "Dongzhu Liang", "Guang Dong", "Hanyu Lai", "Hanchen Zhang", "Hanlin Zhao", "Iat Long Iong", "Jiadai Sun", "Jiaqi Wang", "Junjie Gao", "Junjun Shan", "Kangning Liu", "Shudan Zhang", "Shuntian Yao", "Siyi Cheng", "Wentao Yao", "Wenyi Zhao", "Xinghan Liu", "Xinyi Liu", "Xinying Chen", "Xinyue Yang", "Yang Yang", "Yifan Xu", "Yu Yang", "Yujia Wang", "Yulin Xu", "Zehan Qi", "Yuxiao Dong", "Jie Tang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7cfe1aa31818f06567aa3d619ad90ac4bdb9f9f9003a1a8a71294cd4f8ccf8dc", "submitted_at": "2024-10-28T17:05:10Z", "updated_at": "2024-10-28T17:05:10Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2411.00820v1"}}, "environments": ["web", "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", "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:2411.00820", "identifiers": {"arxiv": "2411.00820"}, "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/2411.00820"}], "name": "AutoGLM: Autonomous Foundation Agents for GUIs", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2024-10-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents AutoGLM agents for browser and phone control, separating planning from grounding and training through an evolving interaction curriculum.", "topics": ["automation", "reinforcement-learning", "grounding"], "updated_at": "2024-10-28", "url": "https://arxiv.org/abs/2411.00820"}
{"aliases": [], "authors": ["Siyuan Hu", "Mingyu Ouyang", "Difei Gao", "Mike Zheng Shou"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "255e101e263c4e3a0cb491d4c34b3e75a8f3660cec2141e3a507a30cf5514dbd", "submitted_at": "2024-11-15T16:23:52Z", "updated_at": "2024-11-15T16:23:52Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2411.10323v1"}}, "environments": ["desktop"], "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", "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=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2411.10323", "identifiers": {"arxiv": "2411.10323"}, "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/2411.10323"}], "name": "The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use", "notes": "Reviewed against the retained original arXiv abstract. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2024-11-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents a preliminary study of Claude 3.5 Computer Use across desktop tasks and software, analyzing planning, action, and critique behavior and providing a framework for deploying GUI-automation models.", "topics": ["evaluation", "automation", "planning"], "updated_at": "2024-11-15", "url": "https://arxiv.org/abs/2411.10323"}
{"aliases": [], "authors": ["Lu Wang", "Fangkai Yang", "Chaoyun Zhang", "Junting Lu", "Jiaxu Qian", "Shilin He", "Pu Zhao", "Bo Qiao", "Ray Huang", "Si Qin", "Qisheng Su", "Jiayi Ye", "Yudi Zhang", "Jian-Guang Lou", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "54051d974e388ed2a26f1421b8c1fc79472bb941810519039ef48e90bf4761b6", "submitted_at": "2024-12-13T11:19:56Z", "updated_at": "2025-01-13T06:47:21Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2412.10047v2"}}, "environments": ["desktop", "windows"], "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": "2026-10-17T09:13:28Z", "role": "primary", "sha256": "aaddc3cae2fcadc9780390fceb663c0200ecb042639e2c69bccea19607cd78ea", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/2412.10047v2"}], "id": "arxiv:2412.10047", "identifiers": {"arxiv": "2412.10047"}, "kind": "paper", "last_verified_at": "2026-10-17T09:13:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2412.10047"}], "name": "Large Action Models: From Inception to Implementation", "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": "2024-12-13", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses a Windows-agent case study to describe a development workflow for large action models, covering data collection, training, grounding, environment integration, and evaluation.", "topics": ["automation", "data-generation", "evaluation"], "updated_at": "2025-01-13", "url": "https://arxiv.org/abs/2412.10047"}
{"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": ["Pranjal Aggarwal", "Sean Welleck"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9e4091fc740249b6406dd9e96f2692d7fac9323759ec6fad6ba5a05f3e445844", "submitted_at": "2025-02-24T18:41:33Z", "updated_at": "2025-10-03T02:09:59Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2502.18525v2"}}, "environments": ["desktop"], "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:2502.18525", "identifiers": {"arxiv": "2502.18525"}, "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/2502.18525"}], "name": "Programming with Pixels: Can Computer-Use Agents do Software Engineering?", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-02-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a visual IDE environment and benchmark for software-engineering tasks, comparing screenshot-based control with access to editing and shell tools.", "topics": ["evaluation", "tool-integration", "automation"], "updated_at": "2025-10-03", "url": "https://arxiv.org/abs/2502.18525"}
{"aliases": [], "authors": ["Sami Marreed", "Alon Oved", "Avi Yaeli", "Segev Shlomov", "Ido Levy", "Offer Akrabi", "Aviad Sela", "Asaf Adi", "Nir Mashkif"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2248d423c954ee6e406e3f46f6da43fabd6e832ffacc05cfa32083f2ff0c2700", "submitted_at": "2025-02-24T09:31:56Z", "updated_at": "2025-07-09T13:52:32Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2503.01861v3"}}, "environments": ["web"], "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:2503.01861", "identifiers": {"arxiv": "2503.01861"}, "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/2503.01861"}], "name": "Towards Enterprise-Ready Computer Using Generalist 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": "2025-02-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "Describes the CUGA enterprise-agent development process, emphasizing iterative evaluation, failure analysis, and refinement on software-task benchmarks.", "topics": ["automation", "evaluation", "workflow"], "updated_at": "2025-07-09", "url": "https://arxiv.org/abs/2503.01861"}
{"aliases": [], "authors": ["Chaoyun Zhang", "Shilin He", "Liqun Li", "Si Qin", "Yu Kang", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "43a533866496d3ebd3e34c04142a702e4a3aaa387c3830e3bb993fdbb0ce8432", "submitted_at": "2025-03-14T04:26:21Z", "updated_at": "2025-06-23T13:01:02Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.11069v2"}}, "environments": ["cross-platform"], "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:2503.11069", "identifiers": {"arxiv": "2503.11069"}, "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/2503.11069"}], "name": "API Agents vs. GUI Agents: Divergence and Convergence", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-03-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "Compares API-driven and GUI-driven agents across architecture, development, and interaction considerations, discussing when hybrid approaches are useful.", "topics": ["tool-integration", "survey", "automation"], "updated_at": "2025-06-23", "url": "https://arxiv.org/abs/2503.11069"}
{"aliases": [], "authors": ["Antoine Chevrot", "Alexandre Vernotte", "Jean-Rémy Falleri", "Xavier Blanc", "Bruno Legeard"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "76d0ffb55478570499c8cddf92a27d346cf11749f8ae5f8e128c87653b2bdbdc", "submitted_at": "2025-04-02T08:48:01Z", "updated_at": "2025-04-02T08:48:01Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2504.01495v1"}}, "environments": ["web"], "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:2504.01495", "identifiers": {"arxiv": "2504.01495"}, "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/2504.01495"}], "name": "Are Autonomous Web Agents Good Testers?", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-04-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "Adapts web agents to execute natural-language test steps, verify assertions, and issue test verdicts. The study introduces 113 passing and failing test cases across three offline web applications and compares two agent implementations with qualitative failure analysis.", "topics": ["automation", "evaluation", "web-navigation"], "updated_at": "2025-04-02", "url": "https://arxiv.org/abs/2504.01495"}
{"aliases": [], "authors": ["Xiaolei Li", "Jialun Cao", "Yepang Liu", "Shing-Chi Cheung", "Hailong Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a646bb2136cdaf47a0d8b3f485d3e1973fc15ac4f844e1beddedf6021b56ffe4", "submitted_at": "2025-04-03T07:45:09Z", "updated_at": "2025-04-03T07:45:09Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2504.02357v1"}}, "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"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:12:09Z", "role": "primary", "sha256": "054a5a305d86c7fb9107d467d194fc4a64aa4f5af23d214bea7f52c2f2c9fd35", "supports": ["environments"], "url": "https://arxiv.org/html/2504.02357"}], "id": "arxiv:2504.02357", "identifiers": {"arxiv": "2504.02357"}, "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/2504.02357"}], "name": "ReuseDroid: A VLM-empowered Android UI Test Migrator Boosted by Active Feedback", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced. The platform or GUI evaluation setting was additionally checked in the primary full text.", "published_at": "2025-04-03", "relations": [], "review_status": "curated", "scope": "core", "summary": "ReuseDroid migrates Android GUI tests between functionally similar apps using VLM agents that separate shared test intent from app-specific interaction flows. It introduces LinPro, a dataset of 578 migration tasks across 39 apps, to evaluate test transfer.", "topics": ["automation", "evaluation", "cross-app"], "updated_at": "2025-04-03", "url": "https://arxiv.org/abs/2504.02357"}
{"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": ["Chaoyun Zhang", "He Huang", "Chiming Ni", "Jian Mu", "Si Qin", "Shilin He", "Lu Wang", "Fangkai Yang", "Pu Zhao", "Chao Du", "Liqun Li", "Yu Kang", "Zhao Jiang", "Suzhen Zheng", "Rujia Wang", "Jiaxu Qian", "Minghua Ma", "Jian-Guang Lou", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dc47a80b48a6a5f126e36fa14639d56d8c8025a453fbcee2cbdb73eb67945561", "submitted_at": "2025-04-20T13:04:43Z", "updated_at": "2025-04-25T05:14:14Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.14603v2"}}, "environments": ["desktop", "windows"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T07:57:47Z", "role": "primary", "sha256": "27144160e8981bb9f36b60c391689774913ff3f026eeeffc2923154c404a6529", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2504.03206%2C2504.03601%2C2504.06821%2C2504.09723%2C2504.11301%2C2504.11543%2C2504.12609%2C2504.14233%2C2504.14348%2C2504.14603%2C2504.16073%2C2504.16419%2C2504.17892%2C2504.18580%2C2504.20965%2C2505.00019%2C2505.00693%2C2505.01578%2C2505.02094%2C2505.03570%2C2505.03574%2C2505.05026%2C2505.05849%2C2505.06507%2C2505.07003%2C2505.07473%2C2505.10468%2C2505.10887%2C2505.12053%2C2505.12490%2C2505.12728%2C2505.13291%2C2505.14030%2C2505.14454%2C2505.14646%2C2505.15801%2C2505.15816%2C2505.17020%2C2505.18746%2C2505.19095%2C2505.19713%2C2505.20023%2C2505.20732%2C2505.20795%2C2505.21055%2C2505.22304%2C2505.22429%2C2505.23450%2C2505.23559%2C2506.00641&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:20:07Z", "role": "primary", "sha256": "0ff3084c62a2ae0fbda31be5d409fb8ca3a6887da897a238beec93a8d7be7825", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/2504.14603v2"}], "id": "arxiv:2504.14603", "identifiers": {"arxiv": "2504.14603"}, "kind": "paper", "last_verified_at": "2026-10-17T11:20:07Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2504.14603"}], "name": "UFO2: The Desktop AgentOS", "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": "2025-04-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces UFO2, a Windows desktop agent architecture combining a coordinating HostAgent, application-specialized agents, and a shared GUI/API action layer. It integrates UI Automation, visual parsing, speculative planning, and an isolated picture-in-picture desktop.", "topics": ["automation", "cross-app", "tool-integration"], "updated_at": "2025-04-25", "url": "https://arxiv.org/abs/2504.14603"}
{"aliases": [], "authors": ["Kai Mei", "Xi Zhu", "Hang Gao", "Shuhang Lin", "Yongfeng Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2c382ce428e6dd41ec07af7575461c69906ce386fd2bcd8ad9f0d792d2b8f0b3", "submitted_at": "2025-05-24T18:56:00Z", "updated_at": "2025-10-31T21:48:48Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2505.18829v2"}}, "environments": ["desktop"], "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:2505.18829", "identifiers": {"arxiv": "2505.18829"}, "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/2505.18829"}], "name": "LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-05-24", "relations": [], "review_status": "curated", "scope": "core", "summary": "AIOS 1.0 exposes computer states and actions through an MCP server to provide structured environmental context for agents. LiteCUA is a lightweight agent built on this interface, evaluated on OSWorld to study the effect of computer-environment contextualization.", "topics": ["tool-integration", "automation"], "updated_at": "2025-10-31", "url": "https://arxiv.org/abs/2505.18829"}
{"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": ["Xuetian Chen", "Yinghao Chen", "Xinfeng Yuan", "Zhuo Peng", "Lu Chen", "Yuekeng Li", "Zhoujia Zhang", "Yingqian Huang", "Leyan Huang", "Jiaqing Liang", "Tianbao Xie", "Zhiyong Wu", "Qiushi Sun", "Biqing Qi", "Bowen Zhou"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fcd5a34bf6187f48da8e08842678e1e21cd558b2bcc7aab2611ceee7bc0d0179", "submitted_at": "2025-07-25T10:14:53Z", "updated_at": "2025-07-25T10:14:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2507.19132v1"}}, "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:2507.19132", "identifiers": {"arxiv": "2507.19132"}, "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/2507.19132"}], "name": "OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-07-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "OS-MAP organizes 416 computer-use tasks across 15 applications by a five-level automation taxonomy and a hierarchy of user demands. The benchmark separates required autonomy from generalization scope to diagnose where agents struggle as task demands increase.", "topics": ["evaluation", "automation", "planning"], "updated_at": "2025-07-25", "url": "https://arxiv.org/abs/2507.19132"}
{"aliases": [], "authors": ["Linxin Song", "Yutong Dai", "Viraj Prabhu", "Jieyu Zhang", "Taiwei Shi", "Li Li", "Junnan Li", "Silvio Savarese", "Zeyuan Chen", "Jieyu Zhao", "Ran Xu", "Caiming Xiong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b6e4272a69c1a93f22bd35032547ffb6021a79c97d179a1075e14aee69dea83a", "submitted_at": "2025-08-05T21:33:36Z", "updated_at": "2026-02-20T10:14:08Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2508.03923v3"}}, "environments": ["desktop"], "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:2508.03923", "identifiers": {"arxiv": "2508.03923"}, "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/2508.03923"}], "name": "CoAct-1: Computer-using Multi-Agent System with Coding Actions", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-08-05", "relations": [], "review_status": "curated", "scope": "core", "summary": "CoAct-1 delegates subtasks between a GUI operator and a programmer that executes Python or Bash. Its OSWorld evaluation studies a hybrid action space in which scripts handle suitable file and data operations while visual interaction handles other steps.", "topics": ["tool-integration", "automation", "efficiency", "planning"], "updated_at": "2026-02-20", "url": "https://arxiv.org/abs/2508.03923"}
{"aliases": [], "authors": ["Yutong Bian", "Xianhao Lin", "Yupeng Xie", "Tianyang Liu", "Mingchen Zhuge", "Siyuan Lu", "Haoming Tang", "Jinlin Wang", "Jiayi Zhang", "Jiaqi Chen", "Xiangru Tang", "Yongxin Ni", "Sirui Hong", "Chenglin Wu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c5034c06e63607a1279668964e91c14ed762a95b6e3953337ef8b8b63c4fd57d", "submitted_at": "2025-08-17T07:31:11Z", "updated_at": "2025-08-17T07:31:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2508.14104v1"}}, "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:2508.14104", "identifiers": {"arxiv": "2508.14104"}, "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/2508.14104"}], "name": "You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software 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": "2025-08-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "RealDevWorld evaluates generated software repositories with 194 development tasks and AppEvalPilot, an agent judge that operates the resulting GUIs. The evaluation examines functional behavior, visual fidelity, and runtime responses to produce task-specific diagnostic feedback.", "topics": ["evaluation", "automation", "observability"], "updated_at": "2025-08-17", "url": "https://arxiv.org/abs/2508.14104"}
{"aliases": [], "authors": ["Zhaoyang Liu", "Jingjing Xie", "Zichen Ding", "Zehao Li", "Bowen Yang", "Zhenyu Wu", "Xuehui Wang", "Qiushi Sun", "Shi Liu", "Weiyun Wang", "Shenglong Ye", "Qingyun Li", "Xuan Dong", "Yue Yu", "Chenyu Lu", "YunXiang Mo", "Yao Yan", "Zeyue Tian", "Xiao Zhang", "Yuan Huang", "Yiqian Liu", "Weijie Su", "Gen Luo", "Xiangyu Yue", "Biqing Qi", "Kai Chen", "Bowen Zhou", "Yu Qiao", "Qifeng Chen", "Wenhai Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "70d09da7d4990118b2b0745cbddf2bab25852ba3ec26625902fee94cdab37c8d", "submitted_at": "2025-09-18T17:59:22Z", "updated_at": "2025-09-19T05:29:03Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.15221v2"}}, "environments": ["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:2509.15221", "identifiers": {"arxiv": "2509.15221"}, "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/2509.15221"}], "name": "ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform 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": "2025-09-18", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a cross-platform computer-use dataset and agents trained with a collection pipeline combining automated interaction and human input.", "topics": ["data-generation", "automation"], "updated_at": "2025-09-19", "url": "https://arxiv.org/abs/2509.15221"}
{"aliases": [], "authors": ["Viraj Prabhu", "Yutong Dai", "Matthew Fernandez", "Jing Gu", "Krithika Ramakrishnan", "Yanqi Luo", "Silvio Savarese", "Caiming Xiong", "Junnan Li", "Zeyuan Chen", "Ran Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "23794419031fe219fc342c041d666045080b274926dc22ab101a65581b4e4efd", "submitted_at": "2025-10-01T23:41:47Z", "updated_at": "2025-10-01T23:41:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.01524v1"}}, "environments": ["web"], "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"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:27:51+00:00", "role": "primary", "sha256": "8466eed10f7f630a68fa742ff9de6b5ba052c497ff421acd4fbee529093d3a58", "supports": ["summary", "scope", "environments"], "url": "https://arxiv.org/html/2510.01524v1"}], "id": "arxiv:2510.01524", "identifiers": {"arxiv": "2510.01524"}, "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/2510.01524"}], "name": "WALT: Web Agents that Learn Tools", "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": "WALT explores website functionality and converts demonstrated interactions into validated, reusable tools combining DOM actions, URL navigation, and agentic fallbacks. It evaluates this expanded browser action space on WebArena and VisualWebArena.", "topics": ["web-navigation", "tool-integration", "efficiency", "automation"], "updated_at": "2025-10-01", "url": "https://arxiv.org/abs/2510.01524"}
{"aliases": [], "authors": ["Yuan Wang", "Mingyu Li", "Haibo Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1c22547bf82eb2fb87e8bf6a3846d25c17cac296763726ed9a25faf88bdca33c", "submitted_at": "2025-10-06T09:14:58Z", "updated_at": "2026-03-25T11:29:08Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.04607v2"}}, "environments": ["desktop", "windows"], "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:2510.04607", "identifiers": {"arxiv": "2510.04607"}, "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/2510.04607"}], "name": "From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents", "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": "2025-10-06", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a Declarative Model Interface that maps existing GUIs to access, state and observation primitives while handling low-level interactions. Evaluation uses Word, PowerPoint and Excel on Windows with a GUI-agent baseline.", "topics": ["automation", "tool-integration", "planning"], "updated_at": "2026-03-25", "url": "https://arxiv.org/abs/2510.04607"}
{"aliases": [], "authors": ["Avihay Cohen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bedde658a28c57551c27563fa22cb037839dddd4e5eabe1c66afa27523d0d406", "submitted_at": "2025-10-15T13:39:13Z", "updated_at": "2025-10-15T13:39:13Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.13543v1"}}, "environments": ["web"], "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:2510.13543", "identifiers": {"arxiv": "2510.13543"}, "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/2510.13543"}], "name": "In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers", "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 short abstract supplies the framework and threat setting but no quantitative evaluation details.", "published_at": "2025-10-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "Proposes an in-browser fuzzing framework that uses language-model guidance to test indirect prompt-injection vulnerabilities in agentic browsers. The work focuses on unwanted actions triggered by webpage instructions under the browser agent's user privileges.", "topics": ["safety-security", "automation"], "updated_at": "2025-10-15", "url": "https://arxiv.org/abs/2510.13543"}
{"aliases": [], "authors": ["Zishu Wei", "Qixiang Ma", "Xavier Hu", "Yuhang Liu", "Hui Zang", "Yudong Zhao", "Tao Wang", "Shengyu Zhang", "Fei Wu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "49e76d19d0477bcc56f19e8170fed7e9cc80f9c4bafb5f03af3a2d172cb113bc", "submitted_at": "2025-12-10T07:40:23Z", "updated_at": "2025-12-10T07:40:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.09396v1"}}, "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", "notes"], "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:2512.09396", "identifiers": {"arxiv": "2512.09396"}, "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/2512.09396"}], "name": "GAIR: GUI Automation via Information-Joint Reasoning and Group Reflection", "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": "2025-12-10", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces GAIR, which combines information from specialized GUI models through a general-purpose coordinating model. When the available information is insufficient, group reflection sends targeted requests back to the specialists before selecting an operation.", "topics": ["planning", "self-reflection", "automation"], "updated_at": "2025-12-10", "url": "https://arxiv.org/abs/2512.09396"}
{"aliases": [], "authors": ["Yifei Gao", "Jiang Wu", "Xiaoyi Chen", "Yifan Yang", "Zhe Cui", "Tianyi Ma", "Jiaming Zhang", "Jitao Sang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "47a340b19cf399f2ae7851482030d85e572b0f6ad8415c67657beec737a80e06", "submitted_at": "2026-01-08T02:07:53Z", "updated_at": "2026-01-08T02:07:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.04500v1"}}, "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:2601.04500", "identifiers": {"arxiv": "2601.04500"}, "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/2601.04500"}], "name": "GUITester: Enabling GUI Agents for Exploratory Defect Discovery", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-01-08", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces GUITestBench for interactive defect discovery and GUITester, which separates task navigation from anomaly verification. Testing-oriented plans and history-based reflection help distinguish software defects from agent execution mistakes.", "topics": ["automation", "evaluation", "self-reflection"], "updated_at": "2026-01-08", "url": "https://arxiv.org/abs/2601.04500"}
{"aliases": [], "authors": ["Tianyi Chen", "Yinheng Li", "Michael Solodko", "Sen Wang", "Nan Jiang", "Tingyuan Cui", "Junheng Hao", "Jongwoo Ko", "Sara Abdali", "Leon Xu", "Suzhen Zheng", "Hao Fan", "Pashmina Cameron", "Justin Wagle", "Kazuhito Koishida"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5a3efa3cd0add437e327ea49896a3ee794daa178664dfb4096aba66fed27554b", "submitted_at": "2026-01-28T23:38:25Z", "updated_at": "2026-02-02T23:11:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.21123v2"}}, "environments": ["desktop", "windows"], "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:2601.21123", "identifiers": {"arxiv": "2601.21123"}, "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/2601.21123"}], "name": "CUA-Skill: Develop Skills for Computer Using Agent", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and released artifacts have not been independently reproduced.", "published_at": "2026-01-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "CUA-Skill encodes Windows application knowledge in parameterized skills and execution/composition graphs. Its agent retrieves and instantiates these skills and uses memory for failure recovery, with end-to-end evaluation on WindowsAgentArena.", "topics": ["tool-integration", "planning", "memory", "automation"], "updated_at": "2026-02-02", "url": "https://arxiv.org/abs/2601.21123"}
{"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": ["Xingyi Zhang", "Yulei Ye", "Kaifeng Huang", "Wenhao Li", "Xiangfeng Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "86a47f084b23cc70e754808f6404bed0bbd500f78fcac4ccc104f95052a49868", "submitted_at": "2026-02-11T12:54:53Z", "updated_at": "2026-02-11T12:54:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.10814v1"}}, "environments": ["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:2602.10814", "identifiers": {"arxiv": "2602.10814"}, "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/2602.10814"}], "name": "See, Plan, Snap: Evaluating Multimodal GUI Agents in Scratch", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-02-11", "relations": [], "review_status": "curated", "scope": "core", "summary": "ScratchWorld evaluates program construction through the Scratch interface using fine-grained drag-and-drop actions and a complementary semantic-API mode. Runtime tests assess the resulting programs, allowing analysis of the gap between program reasoning and GUI manipulation.", "topics": ["evaluation", "grounding", "automation"], "updated_at": "2026-02-11", "url": "https://arxiv.org/abs/2602.10814"}
{"aliases": [], "authors": ["Xiwen Teoh", "Yun Lin", "Duc-Minh Nguyen", "Ruofei Ren", "Wenjie Zhang", "Jin Song Dong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2076fc8b0b7b37bdf43fe2e0b0cc5fa4c3a8cb7b44a41fdf80f59a8c05c7e1b3", "submitted_at": "2026-02-12T08:51:07Z", "updated_at": "2026-04-23T15:00:58Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2602.11724v3"}}, "environments": ["web"], "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:2602.11724", "identifiers": {"arxiv": "2602.11724"}, "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/2602.11724"}], "name": "WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements", "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": "WebTestPilot turns natural-language requirements into web test steps with inferred preconditions and postconditions over symbolized GUI elements. A benchmark of bug-injected web applications tests whether these context-aware oracles distinguish application defects from agent mistakes.", "topics": ["automation", "evaluation", "planning"], "updated_at": "2026-04-23", "url": "https://arxiv.org/abs/2602.11724"}
{"aliases": [], "authors": ["Chenyang Ma", "Clyde Fare", "Matthew Wilson", "Dave Braines"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "353036db8a5609d64792ea49523ca424cf265d981ff34d1e7bc8fed35ffb21c0", "submitted_at": "2026-02-16T15:59:56Z", "updated_at": "2026-02-16T15:59:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.14865v1"}}, "environments": ["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", "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:2602.14865", "identifiers": {"arxiv": "2602.14865"}, "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/2602.14865"}], "name": "EmbeWebAgent: Embedding Web Agents into Any Customized UI", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-02-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "EmbeWebAgent embeds agent access into existing web applications through frontend observations and a page-specific function registry. Its workflow combines GUI primitives, composite actions and MCP tools, demonstrated in a live interface.", "topics": ["web-navigation", "tool-integration", "automation", "workflow"], "updated_at": "2026-02-16", "url": "https://arxiv.org/abs/2602.14865"}
{"aliases": [], "authors": ["Syed Yusuf Ahmed", "Shiwei Feng", "Chanwoo Bae", "Calix Barrus Xiangyu Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8ad18d7fe815f5529fef663130b7ce8841763589e7f4319c0c7556ec2df1da03", "submitted_at": "2026-03-10T22:56:03Z", "updated_at": "2026-03-10T22:56:03Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.10268v1"}}, "environments": ["web"], "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:2603.10268", "identifiers": {"arxiv": "2603.10268"}, "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/2603.10268"}], "name": "SpecOps: A Fully Automated AI Agent Testing Framework in Real-World GUI Environments", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-03-10", "relations": [], "review_status": "curated", "scope": "core", "summary": "SpecOps divides testing of GUI-based agents into test generation, environment setup, execution and validation handled by specialist agents. Its evaluation spans five real-world agents, including web applications and browser extensions, and measures execution reliability and bug discovery.", "topics": ["automation", "evaluation", "planning"], "updated_at": "2026-03-10", "url": "https://arxiv.org/abs/2603.10268"}
{"aliases": [], "authors": ["Akash Ghosh", "Tajamul Ashraf", "Rishu Kumar Singh", "Numan Saeed", "Sriparna Saha", "Xiuying Chen", "Salman Khan"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8fb6a294616e1be46c5da05f60cda7d43c05d8a1ce71116c5e30cb94507cd56f", "submitted_at": "2026-03-25T10:25:48Z", "updated_at": "2026-03-25T10:25:48Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.24157v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:16Z", "role": "primary", "sha256": "9289bc047b59e93f75703b72f5e92d9277e115238427519c343df550220e351b", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2602.19870%2C2602.22769%2C2602.23166%2C2602.23320%2C2603.00198%2C2603.00842%2C2603.00991%2C2603.01050%2C2603.01145%2C2603.02236%2C2603.02795%2C2603.03278%2C2603.04549%2C2603.06713%2C2603.07106%2C2603.07670%2C2603.07853%2C2603.08706%2C2603.09716%2C2603.10002%2C2603.10664%2C2603.11139%2C2603.11320%2C2603.12483%2C2603.13026%2C2603.13247%2C2603.15714%2C2603.16065%2C2603.16289%2C2603.16839%2C2603.17216%2C2603.17378%2C2603.19313%2C2603.19685%2C2603.21489%2C2603.22527%2C2603.23638%2C2603.24157%2C2603.24639%2C2603.27646%2C2603.28069%2C2603.28407%2C2603.29418%2C2603.29847%2C2604.00528%2C2604.00886%2C2604.01194%2C2604.01438%2C2604.01560%2C2604.02985&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:16Z", "role": "primary", "sha256": "9289bc047b59e93f75703b72f5e92d9277e115238427519c343df550220e351b", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2602.19870%2C2602.22769%2C2602.23166%2C2602.23320%2C2603.00198%2C2603.00842%2C2603.00991%2C2603.01050%2C2603.01145%2C2603.02236%2C2603.02795%2C2603.03278%2C2603.04549%2C2603.06713%2C2603.07106%2C2603.07670%2C2603.07853%2C2603.08706%2C2603.09716%2C2603.10002%2C2603.10664%2C2603.11139%2C2603.11320%2C2603.12483%2C2603.13026%2C2603.13247%2C2603.15714%2C2603.16065%2C2603.16289%2C2603.16839%2C2603.17216%2C2603.17378%2C2603.19313%2C2603.19685%2C2603.21489%2C2603.22527%2C2603.23638%2C2603.24157%2C2603.24639%2C2603.27646%2C2603.28069%2C2603.28407%2C2603.29418%2C2603.29847%2C2604.00528%2C2604.00886%2C2604.01194%2C2604.01438%2C2604.01560%2C2604.02985&max_results=50"}], "id": "arxiv:2603.24157", "identifiers": {"arxiv": "2603.24157"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:16Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2603.24157"}], "name": "CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified.", "published_at": "2026-03-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "CareFlow benchmarks long healthcare-software workflows, while CarePilot coordinates action proposals, execution checks and corrective feedback using short- and long-term memory. Its actor consumes visual interfaces and system state to select semantic actions.", "topics": ["automation", "planning", "memory", "evaluation", "long-horizon", "workflow"], "updated_at": "2026-03-25", "url": "https://arxiv.org/abs/2603.24157"}
{"aliases": [], "authors": ["Fanheng Kong", "Jingyuan Zhang", "Yang Yue", "Chenxi Sun", "Yang Tian", "Shi Feng", "Xiaocui Yang", "Daling Wang", "Yu Tian", "Jun Du", "Wenchong Zeng", "Han Li", "Kun Gai"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8414eb53c66f745fb074d9f2699f76ffea81cb55f98aacf9ce896401937f80c5", "submitted_at": "2026-03-26T09:27:29Z", "updated_at": "2026-03-26T09:27:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.25226v1"}}, "environments": ["web"], "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:2603.25226", "identifiers": {"arxiv": "2603.25226"}, "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/2603.25226"}], "name": "WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing", "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": "2026-03-26", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces WebTestBench for end-to-end website testing, separating checklist generation from defect detection. Its WebTester baseline evaluates test coverage, detection and sustained interaction across web application categories.", "topics": ["evaluation", "web-navigation", "automation"], "updated_at": "2026-03-26", "url": "https://arxiv.org/abs/2603.25226"}
{"aliases": [], "authors": ["Zirui Zhao", "Jun Hao Liew", "Yan Yang", "Wenzhuo Yang", "Ziyang Luo", "Doyen Sahoo", "Silvio Savarese", "Junnan Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "47e2cb6818c8e26889da590d26073ccc84474bb2e3391f9b184e5d7f8a31ef1d", "submitted_at": "2026-04-02T06:27:52Z", "updated_at": "2026-04-04T01:55:00Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2604.01676v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:33:02Z", "role": "primary", "sha256": "e436adf2735cb537ee4b24aa0c3f36930a50c2f683cc6868e7c40df602bdb6b8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2604.00892%2C2604.01221%2C2604.01676%2C2604.02345%2C2604.03465%2C2604.05157%2C2604.06134%2C2604.06240%2C2604.06995%2C2604.07277%2C2604.07831%2C2604.07929%2C2604.08005%2C2604.09581%2C2604.10261%2C2604.10577%2C2604.10988%2C2604.11201%2C2604.18847%2C2604.21375%2C2604.24441%2C2604.26020%2C2605.00551%2C2605.02168%2C2605.07505%2C2605.10347%2C2605.12294%2C2605.15040%2C2605.16883%2C2605.27134%2C2605.28258%2C2606.01790%2C2606.02031%2C2606.02208%2C2606.03203%2C2606.03236%2C2606.03951%2C2606.04391%2C2606.04627%2C2606.04701%2C2606.05233%2C2606.05597%2C2606.05697%2C2606.06560%2C2606.06708%2C2606.07027%2C2606.07074%2C2606.09399%2C2606.09447%2C2606.09764&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:33:02Z", "role": "primary", "sha256": "e436adf2735cb537ee4b24aa0c3f36930a50c2f683cc6868e7c40df602bdb6b8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2604.00892%2C2604.01221%2C2604.01676%2C2604.02345%2C2604.03465%2C2604.05157%2C2604.06134%2C2604.06240%2C2604.06995%2C2604.07277%2C2604.07831%2C2604.07929%2C2604.08005%2C2604.09581%2C2604.10261%2C2604.10577%2C2604.10988%2C2604.11201%2C2604.18847%2C2604.21375%2C2604.24441%2C2604.26020%2C2605.00551%2C2605.02168%2C2605.07505%2C2605.10347%2C2605.12294%2C2605.15040%2C2605.16883%2C2605.27134%2C2605.28258%2C2606.01790%2C2606.02031%2C2606.02208%2C2606.03203%2C2606.03236%2C2606.03951%2C2606.04391%2C2606.04627%2C2606.04701%2C2606.05233%2C2606.05597%2C2606.05697%2C2606.06560%2C2606.06708%2C2606.07027%2C2606.07074%2C2606.09399%2C2606.09447%2C2606.09764&max_results=50"}], "id": "arxiv:2604.01676", "identifiers": {"arxiv": "2604.01676"}, "kind": "paper", "last_verified_at": "2026-10-16T06:33:02Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.01676"}], "name": "GPA: Learning GUI Process Automation from Demonstrations", "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": "2026-04-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents demonstration-based GUI process replay with Sequential Monte Carlo localization and readiness checks. GPA executes the learned workflow locally and can serve as the GUI execution component of an agent using MCP or CLI tools.", "topics": ["automation", "workflow", "robustness"], "updated_at": "2026-04-04", "url": "https://arxiv.org/abs/2604.01676"}
{"aliases": [], "authors": ["Wee Joe Tan", "Zi Rui Lucas Lim", "Shashank Durgad", "Karim Obegi", "Aiden Yiliu Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "445e520a60e0e3cc0c3c519e21bfa8eebfa33d4fe4320c437e67b94a02d84504", "submitted_at": "2026-02-25T18:59:42Z", "updated_at": "2026-04-14T20:54:46Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2604.09581v2"}}, "environments": ["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:2604.09581", "identifiers": {"arxiv": "2604.09581"}, "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/2604.09581"}], "name": "Avenir-UX: Automated UX Evaluation via Simulated Human Web Interaction with GUI Grounding", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-02-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "Avenir-UX combines grounded web interaction with simulated user profiles and structured usability measures to produce evaluations of website journeys. The paper describes its architecture and use of SUS, step-wise ease questions and think-aloud traces for automated UX reporting.", "topics": ["automation", "evaluation", "ui-design", "grounding"], "updated_at": "2026-04-14", "url": "https://arxiv.org/abs/2604.09581"}
{"aliases": [], "authors": ["Zhaoyang Wang", "Qianhui Wu", "Xuchao Zhang", "Chaoyun Zhang", "Wenlin Yao", "Fazle Elahi Faisal", "Baolin Peng", "Si Qin", "Suman Nath", "Qingwei Lin", "Chetan Bansal", "Dongmei Zhang", "Saravan Rajmohan", "Jianfeng Gao", "Huaxiu Yao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bf709a3d7096bc07218206edb1accfdda64036a39ea770e637b3e073dd9a76c8", "submitted_at": "2026-04-14T21:48:15Z", "updated_at": "2026-08-31T07:02:14Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2604.13318v2"}}, "environments": ["web"], "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:2604.13318", "identifiers": {"arxiv": "2604.13318"}, "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/2604.13318"}], "name": "WebXSkill: Skill Learning for Autonomous Web Agents", "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": "2026-04-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "WebXSkill pairs parameterized action programs with step-level language guidance, mining reusable skills from synthetic browser-agent traces. A URL-based graph supports retrieval, and deployment alternates between direct program execution and guided native planning.", "topics": ["memory", "planning", "web-navigation", "automation"], "updated_at": "2026-08-31", "url": "https://arxiv.org/abs/2604.13318"}
{"aliases": [], "authors": ["Zhiyuan Peng", "Wei Tao", "Xin Yin", "Chenhao Ying", "Yuan Luo", "Yiwen Guo"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "74ec7a508a815781cc7e721aa6c5e351f086f6cab46da48e22c2b58f52af8ce0", "submitted_at": "2026-04-21T17:59:16Z", "updated_at": "2026-09-29T10:11:48Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2604.19742v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:19Z", "role": "primary", "sha256": "05ec5d668ac75d3d7c5b71ea7d6e76a3fbf5ebeb742e0843db2329e5e41aa208", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2604.03598%2C2604.04759%2C2604.05547%2C2604.06170%2C2604.07340%2C2604.10547%2C2604.10938%2C2604.11978%2C2604.12282%2C2604.13018%2C2604.13346%2C2604.13954%2C2604.15579%2C2604.15671%2C2604.15715%2C2604.16520%2C2604.18240%2C2604.18934%2C2604.19572%2C2604.19667%2C2604.19742%2C2604.20841%2C2604.20987%2C2604.22436%2C2604.23781%2C2604.24479%2C2604.26148%2C2604.27621%2C2604.27996%2C2604.28093%2C2604.28139%2C2604.28181%2C2605.00425%2C2605.01462%2C2605.02240%2C2605.03042%2C2605.03242%2C2605.04811%2C2605.05191%2C2605.05811%2C2605.06110%2C2605.07073%2C2605.07358%2C2605.08374%2C2605.08985%2C2605.10912%2C2605.10966%2C2605.11363%2C2605.11732%2C2605.11817&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:19Z", "role": "primary", "sha256": "05ec5d668ac75d3d7c5b71ea7d6e76a3fbf5ebeb742e0843db2329e5e41aa208", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2604.03598%2C2604.04759%2C2604.05547%2C2604.06170%2C2604.07340%2C2604.10547%2C2604.10938%2C2604.11978%2C2604.12282%2C2604.13018%2C2604.13346%2C2604.13954%2C2604.15579%2C2604.15671%2C2604.15715%2C2604.16520%2C2604.18240%2C2604.18934%2C2604.19572%2C2604.19667%2C2604.19742%2C2604.20841%2C2604.20987%2C2604.22436%2C2604.23781%2C2604.24479%2C2604.26148%2C2604.27621%2C2604.27996%2C2604.28093%2C2604.28139%2C2604.28181%2C2605.00425%2C2605.01462%2C2605.02240%2C2605.03042%2C2605.03242%2C2605.04811%2C2605.05191%2C2605.05811%2C2605.06110%2C2605.07073%2C2605.07358%2C2605.08374%2C2605.08985%2C2605.10912%2C2605.10966%2C2605.11363%2C2605.11732%2C2605.11817&max_results=50"}], "id": "arxiv:2604.19742", "identifiers": {"arxiv": "2604.19742"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:19Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.19742"}], "name": "PlayCoder: Making LLM-Generated GUI Code Playable", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified.", "published_at": "2026-04-21", "relations": [], "review_status": "curated", "scope": "core", "summary": "PlayEval measures whether generated GUI applications remain logically playable, using PlayTester to execute task-oriented GUI playthroughs. PlayCoder closes the loop between repository-aware generation, interactive testing and targeted code repair.", "topics": ["evaluation", "automation", "ui-design", "workflow"], "updated_at": "2026-09-29", "url": "https://arxiv.org/abs/2604.19742"}
{"aliases": [], "authors": ["Alice Gao", "Weixi Tong", "Rishab Vempati", "Katharina Reinecke", "R. Benjamin Shapiro", "Tianyi Zhang", "Jason Wu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bb6d24f7dc38921da883c4850b37f1c7eb48a03de920356d4ec2e095dbb44b04", "submitted_at": "2026-04-28T18:04:11Z", "updated_at": "2026-04-28T18:04:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.26020v1"}}, "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:2604.26020", "identifiers": {"arxiv": "2604.26020"}, "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/2604.26020"}], "name": "Training Computer Use Agents to Assess the Usability of Graphical User Interfaces", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-04-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "uxCUA learns to assess interface usability by choosing interaction flows, executing them and predicting a numerical usability score. Training uses interactive UIs with usability labels and human preferences, with evaluations on synthetic and real interfaces.", "topics": ["ui-design", "evaluation", "automation"], "updated_at": "2026-04-28", "url": "https://arxiv.org/abs/2604.26020"}
{"aliases": [], "authors": ["Chiyeong Heo", "Jaechang Kim", "Junhyuk Kwon", "Hoyoung Kim", "Dongmin Park", "Jonghyun Lee", "Jungseul Ok"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0bd75e6bf9d5a8185a2204cdd99d42f9d96c102f7297abcadb9f8425e9246349", "submitted_at": "2026-05-08T10:57:19Z", "updated_at": "2026-05-08T10:57:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.10966v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:19Z", "role": "primary", "sha256": "05ec5d668ac75d3d7c5b71ea7d6e76a3fbf5ebeb742e0843db2329e5e41aa208", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2604.03598%2C2604.04759%2C2604.05547%2C2604.06170%2C2604.07340%2C2604.10547%2C2604.10938%2C2604.11978%2C2604.12282%2C2604.13018%2C2604.13346%2C2604.13954%2C2604.15579%2C2604.15671%2C2604.15715%2C2604.16520%2C2604.18240%2C2604.18934%2C2604.19572%2C2604.19667%2C2604.19742%2C2604.20841%2C2604.20987%2C2604.22436%2C2604.23781%2C2604.24479%2C2604.26148%2C2604.27621%2C2604.27996%2C2604.28093%2C2604.28139%2C2604.28181%2C2605.00425%2C2605.01462%2C2605.02240%2C2605.03042%2C2605.03242%2C2605.04811%2C2605.05191%2C2605.05811%2C2605.06110%2C2605.07073%2C2605.07358%2C2605.08374%2C2605.08985%2C2605.10912%2C2605.10966%2C2605.11363%2C2605.11732%2C2605.11817&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:19Z", "role": "primary", "sha256": "05ec5d668ac75d3d7c5b71ea7d6e76a3fbf5ebeb742e0843db2329e5e41aa208", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2604.03598%2C2604.04759%2C2604.05547%2C2604.06170%2C2604.07340%2C2604.10547%2C2604.10938%2C2604.11978%2C2604.12282%2C2604.13018%2C2604.13346%2C2604.13954%2C2604.15579%2C2604.15671%2C2604.15715%2C2604.16520%2C2604.18240%2C2604.18934%2C2604.19572%2C2604.19667%2C2604.19742%2C2604.20841%2C2604.20987%2C2604.22436%2C2604.23781%2C2604.24479%2C2604.26148%2C2604.27621%2C2604.27996%2C2604.28093%2C2604.28139%2C2604.28181%2C2605.00425%2C2605.01462%2C2605.02240%2C2605.03042%2C2605.03242%2C2605.04811%2C2605.05191%2C2605.05811%2C2605.06110%2C2605.07073%2C2605.07358%2C2605.08374%2C2605.08985%2C2605.10912%2C2605.10966%2C2605.11363%2C2605.11732%2C2605.11817&max_results=50"}], "id": "arxiv:2605.10966", "identifiers": {"arxiv": "2605.10966"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:19Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.10966"}], "name": "MMTB: Evaluating Terminal Agents on Multimedia-File Tasks", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified. Adjacent computer-automation benchmark using terminal workflows, explicitly separated from graphical-interface control.", "published_at": "2026-05-08", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "MultiMedia-TerminalBench evaluates agents that use terminal tools to work with audio and video files. The Terminus-MM harness adds multimedia perception to study how accessible evidence changes executable workflows and task outcomes.", "topics": ["evaluation", "automation", "video", "tool-integration"], "updated_at": "2026-05-08", "url": "https://arxiv.org/abs/2605.10966"}
{"aliases": [], "authors": ["Yutong Huang", "Vikranth Srivatsa", "Alex Asch", "Hansin Tushar Patwa", "Yiying Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "51576fb9bde23f769d3200a0d593ad610eb27248917132aff1bcf6eb7ff03cea", "submitted_at": "2026-05-17T08:24:01Z", "updated_at": "2026-05-17T08:24:01Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.17320v1"}}, "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:2605.17320", "identifiers": {"arxiv": "2605.17320"}, "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/2605.17320"}], "name": "TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents", "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": "2026-05-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "TClone versions live GUI workspaces through snapshots, isolated forks, rollback and selective commit or merge. It separates fast branch creation from durable checkpoints using copy-on-write sharing, filesystem versioning and asynchronous checkpointing, with end-to-end agent-loop latency measurements.", "topics": ["sandbox", "efficiency", "safety-security", "automation"], "updated_at": "2026-05-17", "url": "https://arxiv.org/abs/2605.17320"}
{"aliases": [], "authors": ["JunJia Guo", "Yuhang Yao", "Chang Li", "Zimeng Pan", "Jiawei", "Zhou", "Jingdi Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "64f8e09fc62f080a75aec1928b82187063cfc3ad8467290608347622410b6460", "submitted_at": "2026-05-22T20:29:12Z", "updated_at": "2026-09-29T00:12:17Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2605.26144v4"}}, "environments": ["web", "android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:23Z", "role": "primary", "sha256": "9a71e95803ce58c462c84e2b45a891555e31d1fb409e643bb3ca4675a44c96e6", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2605.12233%2C2605.12493%2C2605.12978%2C2605.13119%2C2605.14133%2C2605.16909%2C2605.17260%2C2605.17324%2C2605.17448%2C2605.17656%2C2605.17721%2C2605.19447%2C2605.19587%2C2605.20894%2C2605.22642%2C2605.23204%2C2605.25233%2C2605.25901%2C2605.26086%2C2605.26144%2C2605.26252%2C2605.26646%2C2605.27209%2C2605.27705%2C2605.27898%2C2605.28158%2C2605.28255%2C2605.29341%2C2605.29463%2C2605.29801%2C2605.30010%2C2605.30052%2C2605.30126%2C2605.30434%2C2605.30907%2C2605.30914%2C2605.31264%2C2605.31557%2C2606.00530%2C2606.00543%2C2606.00856%2C2606.01057%2C2606.01961%2C2606.02540%2C2606.03103%2C2606.03889%2C2606.03895%2C2606.04315%2C2606.04455%2C2606.05525&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:23Z", "role": "primary", "sha256": "9a71e95803ce58c462c84e2b45a891555e31d1fb409e643bb3ca4675a44c96e6", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2605.12233%2C2605.12493%2C2605.12978%2C2605.13119%2C2605.14133%2C2605.16909%2C2605.17260%2C2605.17324%2C2605.17448%2C2605.17656%2C2605.17721%2C2605.19447%2C2605.19587%2C2605.20894%2C2605.22642%2C2605.23204%2C2605.25233%2C2605.25901%2C2605.26086%2C2605.26144%2C2605.26252%2C2605.26646%2C2605.27209%2C2605.27705%2C2605.27898%2C2605.28158%2C2605.28255%2C2605.29341%2C2605.29463%2C2605.29801%2C2605.30010%2C2605.30052%2C2605.30126%2C2605.30434%2C2605.30907%2C2605.30914%2C2605.31264%2C2605.31557%2C2606.00530%2C2606.00543%2C2606.00856%2C2606.01057%2C2606.01961%2C2606.02540%2C2606.03103%2C2606.03889%2C2606.03895%2C2606.04315%2C2606.04455%2C2606.05525&max_results=50"}], "id": "arxiv:2605.26144", "identifiers": {"arxiv": "2605.26144"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:23Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.26144"}], "name": "VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified. Adjacent GUI-application generation benchmark with real component interaction probes; its main evaluated agents are application coders, not general GUI task executors.", "published_at": "2026-05-22", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "VISTA evaluates coding agents that turn design handoffs into working web and Android applications. Its evaluator locates annotated interactive components and probes their behavior, keeping visual localization distinct from functional correctness.", "topics": ["evaluation", "ui-design", "automation"], "updated_at": "2026-09-29", "url": "https://arxiv.org/abs/2605.26144"}
{"aliases": [], "authors": ["Yixu Huang", "Bo Li", "Na Li", "Zhe Wang", "Kaijie Chen", "Haonan Ge", "Qingyi Si", "Yuanzhe Shen", "Ruihan Yang", "Guangjing Wang", "Hongcheng Guo"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4e03e0ef06c6610eaefeec08b7891a1ab4d5073c0793650d4845735259978723", "submitted_at": "2026-05-27T10:08:48Z", "updated_at": "2026-10-02T05:26:34Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.28258v2"}}, "environments": ["web"], "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:2605.28258", "identifiers": {"arxiv": "2605.28258"}, "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/2605.28258"}], "name": "GUI Agents for Continual Game Generation", "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. GUI agents actually load and play browser-game builds, providing an executable interface-testing signal for game-code generation; the central application remains game development.", "published_at": "2026-05-27", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "PlaytestArena evaluates generated browser games using expected in-play behaviors adjudicated by GUI agents. Play2Code pairs a coding agent with a rubric-blind GUI playtester whose interaction traces and feedback guide iterative refinement, with a separate final judge.", "topics": ["evaluation", "automation", "workflow"], "updated_at": "2026-10-02", "url": "https://arxiv.org/abs/2605.28258"}
{"aliases": [], "authors": ["Yuhao Yang", "Tianyu Fan", "Chao Huang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f7490150e82a5abfc510c60401cccf21c821d829e66cc5f2b40fd2fbbf4b0df4", "submitted_at": "2026-06-02T16:30:33Z", "updated_at": "2026-06-02T16:30:33Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.03854v1"}}, "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:2606.03854", "identifiers": {"arxiv": "2606.03854"}, "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/2606.03854"}], "name": "CLI-Anything: Towards Agent-Native Computer Use", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced. Adjacent computer-interface architecture: the described application command harnesses concern computer operation, but no GUI execution or comparative benchmark result is established in the abstract.", "published_at": "2026-06-02", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "CLI-Anything argues for application interfaces built around structured commands, explicit state and execution feedback. It describes transforming existing software into command-line harnesses and organizing that approach through CLI-Hub.", "topics": ["automation", "tool-integration", "workflow"], "updated_at": "2026-06-02", "url": "https://arxiv.org/abs/2606.03854"}
{"aliases": [], "authors": ["Bo Zhang", "Borui Zhang", "Chenghao Jiang", "Minglei Shi", "Xiaofeng Wang", "Zheng Zhu", "Jie Zhou", "Jiwen Lu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "33c343e9bc02976fc3e32057cdcdebc3abeae5ef049b877443e81917a8abc550", "submitted_at": "2026-05-28T17:59:31Z", "updated_at": "2026-05-28T17:59:31Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.07594v1"}}, "environments": ["desktop", "macos"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:28Z", "role": "primary", "sha256": "7eaa9a5430d3a45049e612a117da345c1daafc54277a35a7cf56b42fbb1e8618", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2606.05646%2C2606.05670%2C2606.06556%2C2606.06891%2C2606.07367%2C2606.07594%2C2606.07682%2C2606.07723%2C2606.07867%2C2606.10394%2C2606.10525%2C2606.11290%2C2606.12203%2C2606.12736%2C2606.13040%2C2606.13368%2C2606.13578%2C2606.13669%2C2606.13802%2C2606.13898%2C2606.14397%2C2606.15057%2C2606.15300%2C2606.15441%2C2606.17162%2C2606.18425%2C2606.19336%2C2606.19409%2C2606.19704%2C2606.20950%2C2606.21033%2C2606.21565%2C2606.23521%2C2606.23654%2C2606.24775%2C2606.25084%2C2606.26080%2C2606.27406%2C2606.27634%2C2606.28430%2C2606.28480%2C2606.29955%2C2606.30616%2C2607.00692%2C2607.01084%2C2607.02032%2C2607.02448%2C2607.02490%2C2607.02577%2C2607.02911&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:28Z", "role": "primary", "sha256": "7eaa9a5430d3a45049e612a117da345c1daafc54277a35a7cf56b42fbb1e8618", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2606.05646%2C2606.05670%2C2606.06556%2C2606.06891%2C2606.07367%2C2606.07594%2C2606.07682%2C2606.07723%2C2606.07867%2C2606.10394%2C2606.10525%2C2606.11290%2C2606.12203%2C2606.12736%2C2606.13040%2C2606.13368%2C2606.13578%2C2606.13669%2C2606.13802%2C2606.13898%2C2606.14397%2C2606.15057%2C2606.15300%2C2606.15441%2C2606.17162%2C2606.18425%2C2606.19336%2C2606.19409%2C2606.19704%2C2606.20950%2C2606.21033%2C2606.21565%2C2606.23521%2C2606.23654%2C2606.24775%2C2606.25084%2C2606.26080%2C2606.27406%2C2606.27634%2C2606.28430%2C2606.28480%2C2606.29955%2C2606.30616%2C2607.00692%2C2607.01084%2C2607.02032%2C2607.02448%2C2607.02490%2C2607.02577%2C2607.02911&max_results=50"}], "id": "arxiv:2606.07594", "identifiers": {"arxiv": "2606.07594"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2606.07594"}], "name": "Syll: Open-Source Personal Automation with Cross-Surface Execution", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified.", "published_at": "2026-05-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "Syll combines tool calls, shell execution and visual GUI control in a personal-automation runtime. It turns user demonstrations into reusable skills and exposes execution logs, keyframes and approval checkpoints for inspection.", "topics": ["automation", "human-in-the-loop", "workflow", "memory", "recording", "observability"], "updated_at": "2026-05-28", "url": "https://arxiv.org/abs/2606.07594"}
{"aliases": [], "authors": ["Jiaxin Ai", "Tao Hu", "Xuemeng Yang", "Shu Zou", "Hairong Zhang", "Daocheng Fu", "Yu Yang", "Hongbin Zhou", "Nianchen Deng", "Pinlong Cai", "Zhongyuan Wang", "Botian Shi", "Kaipeng Zhang", "Licheng Wen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "edf7e63803efba89551aa297bff1da9b0babf8ec898a2971fa6c8a20cc58dea8", "submitted_at": "2026-06-11T11:53:32Z", "updated_at": "2026-06-30T03:31:20Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.13239v2"}}, "environments": ["desktop", "windows"], "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"], "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:2606.13239", "identifiers": {"arxiv": "2606.13239"}, "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/2606.13239"}], "name": "ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-06-11", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "ComAct proposes COM program synthesis as an alternative interface for manipulating professional software and introduces ComCADBench with GUI-based comparison agents. ComActor adds a staged training and correction approach, supported by a Windows-container training platform.", "topics": ["automation", "evaluation", "tool-integration", "science"], "updated_at": "2026-06-30", "url": "https://arxiv.org/abs/2606.13239"}
{"aliases": [], "authors": ["Bojie Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "19fd8d8363ef6a7c58e42309f25dea1b9c5b6bca09b5d823f8a7cc7a80d61f0f", "submitted_at": "2026-06-16T13:40:21Z", "updated_at": "2026-06-16T13:40:21Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.17929v1"}}, "environments": ["cross-platform"], "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:2606.17929", "identifiers": {"arxiv": "2606.17929"}, "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/2606.17929"}], "name": "PreAct: Computer-Using Agents that Get Faster on Repeated Tasks", "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": "2026-06-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "PreAct compiles successful screen-interaction runs into guarded state-machine programs for repeated tasks. It validates programs from clean states before storage and returns control to the agent when replayed screen expectations fail, with tests across mobile, desktop and web.", "topics": ["recording", "memory", "efficiency", "automation"], "updated_at": "2026-06-16", "url": "https://arxiv.org/abs/2606.17929"}
{"aliases": [], "authors": ["Li Gu", "Zihuan Jiang", "Linqiang Guo", "Zhixiang Chi", "Ziqiang Wang", "Huan Liu", "Yuanhao Yu", "Tse-Hsun Chen", "Yang Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9bf8b07e08b275d90fcbfc63d867f54f5579509132cc9cf694d01447b7f91b78", "submitted_at": "2026-06-16T02:36:22Z", "updated_at": "2026-06-16T02:36:22Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.19388v1"}}, "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"], "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:2606.19388", "identifiers": {"arxiv": "2606.19388"}, "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/2606.19388"}], "name": "Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-06-16", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "This study compares general coding agents using mobile command-line access with reproducible GUI agents on AndroidWorld and MobileWorld. It also supplies oracle CLI analyses and a separate task suite for operations such as bulk changes, filtering and hidden device state.", "topics": ["evaluation", "automation", "cross-app", "tool-integration"], "updated_at": "2026-06-16", "url": "https://arxiv.org/abs/2606.19388"}
{"aliases": [], "authors": ["Shoufa Chen", "Luyuan Wang", "Xuan Yang", "Zhiheng Liu", "Yuren Cong", "Yuanfeng Ji", "Feiyan Zhou", "Xiaohui Zhang", "Fanny Yang", "Belinda Zeng"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6164c42541650e5120adc881b19524cb3b268f08d6eb77fbe91d8c1a02823786", "submitted_at": "2026-06-26T17:59:51Z", "updated_at": "2026-06-26T17:59:51Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.28480v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:28Z", "role": "primary", "sha256": "7eaa9a5430d3a45049e612a117da345c1daafc54277a35a7cf56b42fbb1e8618", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2606.05646%2C2606.05670%2C2606.06556%2C2606.06891%2C2606.07367%2C2606.07594%2C2606.07682%2C2606.07723%2C2606.07867%2C2606.10394%2C2606.10525%2C2606.11290%2C2606.12203%2C2606.12736%2C2606.13040%2C2606.13368%2C2606.13578%2C2606.13669%2C2606.13802%2C2606.13898%2C2606.14397%2C2606.15057%2C2606.15300%2C2606.15441%2C2606.17162%2C2606.18425%2C2606.19336%2C2606.19409%2C2606.19704%2C2606.20950%2C2606.21033%2C2606.21565%2C2606.23521%2C2606.23654%2C2606.24775%2C2606.25084%2C2606.26080%2C2606.27406%2C2606.27634%2C2606.28430%2C2606.28480%2C2606.29955%2C2606.30616%2C2607.00692%2C2607.01084%2C2607.02032%2C2607.02448%2C2607.02490%2C2607.02577%2C2607.02911&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:28Z", "role": "primary", "sha256": "7eaa9a5430d3a45049e612a117da345c1daafc54277a35a7cf56b42fbb1e8618", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2606.05646%2C2606.05670%2C2606.06556%2C2606.06891%2C2606.07367%2C2606.07594%2C2606.07682%2C2606.07723%2C2606.07867%2C2606.10394%2C2606.10525%2C2606.11290%2C2606.12203%2C2606.12736%2C2606.13040%2C2606.13368%2C2606.13578%2C2606.13669%2C2606.13802%2C2606.13898%2C2606.14397%2C2606.15057%2C2606.15300%2C2606.15441%2C2606.17162%2C2606.18425%2C2606.19336%2C2606.19409%2C2606.19704%2C2606.20950%2C2606.21033%2C2606.21565%2C2606.23521%2C2606.23654%2C2606.24775%2C2606.25084%2C2606.26080%2C2606.27406%2C2606.27634%2C2606.28430%2C2606.28480%2C2606.29955%2C2606.30616%2C2607.00692%2C2607.01084%2C2607.02032%2C2607.02448%2C2607.02490%2C2607.02577%2C2607.02911&max_results=50"}], "id": "arxiv:2606.28480", "identifiers": {"arxiv": "2606.28480"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2606.28480"}], "name": "TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified. Adjacent general computer-operation benchmark: the evaluated interface is a terminal; GUI benchmarks are a contrast, not its execution modality.", "published_at": "2026-06-26", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "TUA-Bench evaluates terminal-use agents on general digital tasks, including document editing, email, web information seeking and specialist software workflows. Tasks run in real terminals with deterministic setup and execution-based scoring.", "topics": ["evaluation", "automation"], "updated_at": "2026-06-26", "url": "https://arxiv.org/abs/2606.28480"}
{"aliases": [], "authors": ["Yogeswar Reddy Thota"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f3f2ae1438986c11146fec508dd61fd3e848ddcbf830f86a7dfa759280d730a", "submitted_at": "2026-06-29T03:19:40Z", "updated_at": "2026-06-29T03:19:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.30697v1"}}, "environments": ["web"], "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:2606.30697", "identifiers": {"arxiv": "2606.30697"}, "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/2606.30697"}], "name": "LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents", "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": "2026-06-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "LUMOS converts native accessibility metadata and browser UI structure into semantic interface blueprints with stable element identifiers and available actions. It combines live pointer-to-element grounding with an observe-act loop constrained to visible-UI primitives.", "topics": ["grounding", "screen-understanding", "tool-integration", "automation"], "updated_at": "2026-06-29", "url": "https://arxiv.org/abs/2606.30697"}
{"aliases": [], "authors": ["Yong Liu", "Zhenyi Zhong", "Zhanpeng Shi"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a779b2c1ff9ba3b531d399204b0986e3affcea81c67fdd7951e3b7da343b0e17", "submitted_at": "2026-07-16T00:35:25Z", "updated_at": "2026-07-16T00:35:25Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.14443v1"}}, "environments": ["desktop", "macos"], "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:2607.14443", "identifiers": {"arxiv": "2607.14443"}, "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/2607.14443"}], "name": "Tactile: Giving Computer-Using Agents Hands and Feet", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-07-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "Tactile turns accessibility, OCR and visual evidence into explicit desktop targets with executable actions and verification cues. Its execution loop chooses semantic actions or coordinate fallbacks while retaining provenance for replay and diagnosis.", "topics": ["grounding", "automation", "observability", "tool-integration", "robustness", "evaluation"], "updated_at": "2026-07-16", "url": "https://arxiv.org/abs/2607.14443"}
{"aliases": [], "authors": ["Hang Yan", "Zhangxuan GU", "Beitong Zhou", "Jiaxuan Chen", "Runze Li", "Yusong Hu", "Shuheng Shen", "Changhua Meng"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dfffaffc68695489e2a705515378112b232e66b6f9e8e3a9bd5df04be95bd2c9", "submitted_at": "2026-07-31T11:51:04Z", "updated_at": "2026-07-31T11:51:04Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.29320v1"}}, "environments": ["cross-platform"], "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:2607.29320", "identifiers": {"arxiv": "2607.29320"}, "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/2607.29320"}], "name": "MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation", "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": "2026-07-31", "relations": [], "review_status": "curated", "scope": "core", "summary": "MAGA distills specialized GUI agents into one policy by allocating supervision according to structured-action correctness rather than treating all response tokens equally. A training-only teacher hint supports fusion across mobile, web and desktop settings without changing student inputs.", "topics": ["imitation-learning", "grounding", "automation"], "updated_at": "2026-07-31", "url": "https://arxiv.org/abs/2607.29320"}
{"aliases": [], "authors": ["Rui Xie", "Lu Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e1626d5190f145c668c9b7f363b7f84904c12daae485e63b858e440ded5ea6df", "submitted_at": "2026-08-27T11:38:19Z", "updated_at": "2026-08-27T11:38:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.26991v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:35Z", "role": "primary", "sha256": "6499b4f4917eec0765d16d6e26a08d7edc5146a30753b19cf8218517656bb070", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2608.16211%2C2608.16391%2C2608.17067%2C2608.17975%2C2608.19741%2C2608.21500%2C2608.22301%2C2608.22510%2C2608.23035%2C2608.23320%2C2608.26238%2C2608.26546%2C2608.26991%2C2608.27260%2C2608.29814%2C2608.31076%2C2609.02292%2C2609.04173%2C2609.04298%2C2609.05776%2C2609.06059%2C2609.07529%2C2609.08149%2C2609.08418%2C2609.09187%2C2609.11561%2C2609.12533%2C2609.15096%2C2609.15544%2C2609.20732%2C2609.21293%2C2609.23986%2C2609.24971%2C2609.24997%2C2609.27455%2C2609.29647%2C2609.29964%2C2609.30798%2C2609.32835%2C2609.34428%2C2609.35002%2C2609.35232%2C2609.35394%2C2609.35581%2C2609.36071%2C2609.36352%2C2609.36777%2C2609.37017%2C2609.38923%2C2609.39222&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:35Z", "role": "primary", "sha256": "6499b4f4917eec0765d16d6e26a08d7edc5146a30753b19cf8218517656bb070", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2608.16211%2C2608.16391%2C2608.17067%2C2608.17975%2C2608.19741%2C2608.21500%2C2608.22301%2C2608.22510%2C2608.23035%2C2608.23320%2C2608.26238%2C2608.26546%2C2608.26991%2C2608.27260%2C2608.29814%2C2608.31076%2C2609.02292%2C2609.04173%2C2609.04298%2C2609.05776%2C2609.06059%2C2609.07529%2C2609.08149%2C2609.08418%2C2609.09187%2C2609.11561%2C2609.12533%2C2609.15096%2C2609.15544%2C2609.20732%2C2609.21293%2C2609.23986%2C2609.24971%2C2609.24997%2C2609.27455%2C2609.29647%2C2609.29964%2C2609.30798%2C2609.32835%2C2609.34428%2C2609.35002%2C2609.35232%2C2609.35394%2C2609.35581%2C2609.36071%2C2609.36352%2C2609.36777%2C2609.37017%2C2609.38923%2C2609.39222&max_results=50"}], "id": "arxiv:2608.26991", "identifiers": {"arxiv": "2608.26991"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:35Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2608.26991"}], "name": "ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified.", "published_at": "2026-08-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "ASIL exposes application state as structured JSON and provides code-executable semantic actions. Its application benchmark compares this interface with screenshot control and application-native APIs, and studies supervised and reinforcement learning on the structured interface.", "topics": ["automation", "tool-integration", "evaluation", "reinforcement-learning", "imitation-learning"], "updated_at": "2026-08-27", "url": "https://arxiv.org/abs/2608.26991"}
{"aliases": [], "authors": ["Venus Team", "Zhuohan Cai", "Haoxing Chen", "Jiaxuan Chen", "Weizhi Chen", "Changlong Gao", "Zhangxuan Gu", "Yuan Guo", "Yusong Hu", "Jianrong Jiang", "Jianguo Li", "Runze Li", "Jinzhen Lin", "Zhenyu Ma", "Changhua Meng", "Han Peng", "Xinyu Qiu", "Shuheng Shen", "Zhongyi Shui", "Weiqiang Wang", "Ming Wen", "Zhuoer Xu", "Hang Yan", "Kaiwen Yang", "Ruilin Yao", "Nanjun Yu", "Zhengwen Zeng", "Lianrui Zhang", "Yunzhu Zhang", "Zhe Zhao", "Beitong Zhou"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "34383fa6c6e5cca059c53fd0452d93eec9ac6a96271ddc14f81ddb96fdeaceec", "submitted_at": "2026-08-27T17:15:33Z", "updated_at": "2026-08-27T17:15:33Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.00028v1"}}, "environments": ["web", "desktop", "cross-platform"], "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:2609.00028", "identifiers": {"arxiv": "2609.00028"}, "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/2609.00028"}], "name": "UI-Venus-2 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": "2026-08-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "Describes a GUI foundation agent trained through expanded environments, function-grounded tasks, and trajectory verification with safety-aware execution mechanisms.", "topics": ["automation", "reinforcement-learning", "safety-security"], "updated_at": "2026-08-27", "url": "https://arxiv.org/abs/2609.00028"}
{"aliases": [], "authors": ["Yixiong Xiao", "Lang An", "Hucheng Yang", "Pinxue Ma", "Yongquan Chen", "Jingjia Cao", "Yusai Zhao", "Ting Wang", "Ting Liu", "Siqi Bao", "Jingbo Zhou", "Hua Wu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "52849171f507e126093411ba81dc580d460b84f831358b08bd57cb54ca41b665", "submitted_at": "2026-09-02T06:03:18Z", "updated_at": "2026-09-10T15:52:42Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2609.02149v3"}}, "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", "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:2609.02149", "identifiers": {"arxiv": "2609.02149"}, "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/2609.02149"}], "name": "OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-09-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "OmegaUse-SOP converts expert GUI demonstrations into configurable procedures and refines them with domain rules and human input. It records, abstracts, grounds and verifies live execution, with a case study of photovoltaic simulation workflows in PVsyst 7.2.", "topics": ["human-in-the-loop", "recording", "workflow", "automation"], "updated_at": "2026-09-10", "url": "https://arxiv.org/abs/2609.02149"}
{"aliases": [], "authors": ["Bowei He", "Xiaokun Zhang", "Meng Ding", "Xue Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "edbe52f304634dfa06e0f232090a4fe998c7ea111418f57942976d348c4e0997", "submitted_at": "2026-08-31T08:16:56Z", "updated_at": "2026-08-31T08:16:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.05511v1"}}, "environments": ["web"], "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:2609.05511", "identifiers": {"arxiv": "2609.05511"}, "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/2609.05511"}], "name": "SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-08-31", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces SCAFFOLD, which extracts executable skills from web trajectories, composes them into a hierarchy, and compresses redundant skills through behavioral checks. It periodically distills skill-guided trajectories into the policy and studies repeated improvement across web benchmarks.", "topics": ["memory", "automation", "web-navigation"], "updated_at": "2026-08-31", "url": "https://arxiv.org/abs/2609.05511"}
{"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": ["Yao Zhao", "Aditya Shanmugham", "Swastik Roy", "Yanxun Xu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e8dcd34beebb8a4660d8d7b9f4c76c3f86069926b9856d26b1c20d87dec83bb5", "submitted_at": "2026-09-15T04:56:17Z", "updated_at": "2026-09-15T04:56:17Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.16635v1"}}, "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", "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:2609.16635", "identifiers": {"arxiv": "2609.16635"}, "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/2609.16635"}], "name": "EchoPath: Execution-Level Replayable Memory 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": "2026-09-15", "relations": [], "review_status": "curated", "scope": "core", "summary": "EchoPath turns validated GUI trajectories into parameterized replay procedures with explicit runtime preconditions. Image-based target matching adjusts stored coordinates, while ambiguous steps fall back to bounded repair or fresh planning.", "topics": ["memory", "workflow", "automation", "grounding", "efficiency", "robustness"], "updated_at": "2026-09-15", "url": "https://arxiv.org/abs/2609.16635"}
{"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": ["Hyewon Suh", "Thanh Minh Nguyen", "Chih-Lun Lee", "Darrow Hartman", "Lizhao Liu", "Xin Eric Wang", "Ang Li", "Jiachen Yang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fdd9890482c07ef44f6e274c802bae5decd9d883b381545b3034ebd4001cdb34", "submitted_at": "2026-09-29T07:44:22Z", "updated_at": "2026-09-29T07:44:22Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.36927v1"}}, "environments": ["desktop"], "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:2609.36927", "identifiers": {"arxiv": "2609.36927"}, "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/2609.36927"}], "name": "Neuro-Symbolic Computer Use: Learning Reusable Policies for Reliable and Efficient Execution", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-09-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "Learns reusable computer-use policies that encode stable workflow logic in programs while delegating grounding and state checks to neural models. Policy iteration executes variants, diagnoses failures, revises the program, and adds verification before state-changing actions.", "topics": ["automation", "workflow", "efficiency"], "updated_at": "2026-09-29", "url": "https://arxiv.org/abs/2609.36927"}
{"aliases": [], "authors": ["Geyi Yang", "Zikun Qu", "Xiang Li", "Zhiyong Wang", "Min Zhang", "Shipei Zeng", "Zhongxiang Dai"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5c43224c865fba2a9f4c826a8e912ab0c07297716e4b7640bf312cce9c9c510e", "submitted_at": "2026-10-01T02:31:20Z", "updated_at": "2026-10-01T02:31:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.00948v1"}}, "environments": ["desktop", "windows"], "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:2610.00948", "identifiers": {"arxiv": "2610.00948"}, "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/2610.00948"}], "name": "GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-10-01", "relations": [], "review_status": "curated", "scope": "core", "summary": "Improves GUI-agent execution code by analyzing action effects and repeated-task failures, then validating bounded changes with frozen model weights.", "topics": ["automation", "observability", "robustness"], "updated_at": "2026-10-01", "url": "https://arxiv.org/abs/2610.00948"}
{"aliases": [], "authors": ["Yulong Ming", "Jie Xu", "Zihan Wu", "Xiaohua Jia"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "923a2e8c6f95b38f84e66e4d2cacdfd54aae8348e17b3fab858d2d7151e82d5b", "submitted_at": "2026-10-02T07:22:46Z", "updated_at": "2026-10-02T07:22:46Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.02932v1"}}, "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:2610.02932", "identifiers": {"arxiv": "2610.02932"}, "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/2610.02932"}], "name": "When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-10-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces PACE, a protocol and online decision rule for deciding when repeated GUI procedures are worth compiling into programs. It accounts for failed compilation attempts, measured per-use savings, uncertain reuse, and execution costs under an explicit cumulative budget.", "topics": ["automation", "efficiency", "workflow"], "updated_at": "2026-10-02", "url": "https://arxiv.org/abs/2610.02932"}
{"aliases": [], "authors": ["Wayne Chi", "I-Hung Hsu", "Li Chen", "Wei-Lin Chiang", "Ion Stoica", "Anastasios Nikolas Angelopoulos", "Ameet Talwalkar", "Chris Donahue", "Cho-Jui Hsieh"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "14d2128155d1540955e54c3bdf9010724f27cf2e101079650315602856c98efa", "submitted_at": "2026-10-13T07:49:50Z", "updated_at": "2026-10-14T06:37:47Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2610.17895v2"}}, "environments": ["web", "desktop"], "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"}], "id": "arxiv:2610.17895", "identifiers": {"arxiv": "2610.17895"}, "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/2610.17895"}], "name": "Interaction-as-a-Judge", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-10-13", "relations": [], "review_status": "curated", "scope": "core", "summary": "Uses computer-use agents to interact with generated applications, studying whether interaction improves preference judging, requirement checks, and feedback for application generation.", "topics": ["evaluation", "data-generation", "automation"], "updated_at": "2026-10-14", "url": "https://arxiv.org/abs/2610.17895"}
{"aliases": [], "authors": [], "details": {"availability": "Public Web Agent source and Chrome-extension archive manifest with local setup instructions.", "component_path": "real_agents/web_agent", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/xlang-ai/OpenAgents/HEAD/LICENSE"], "reason": "OpenAgents source license, scoped here to the reviewed Web Agent component; bundled third-party components retain their notices."}}, "repository_revision": "ff2e46440699af1324eb25655b622c4a131265bb"}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:54Z", "role": "primary", "sha256": "fb6ef7fdb133612467e27ffa642ccbe73cfb4bd8fb0c63c1bc629ad686694e1d", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations"], "url": "https://raw.githubusercontent.com/xlang-ai/OpenAgents/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:54Z", "role": "primary", "sha256": "b843b0519dc74bf6dbf693e0274e8ef8eb1ade94a656d3ab23faac2df4f7c9fa", "supports": ["identity"], "url": "https://api.github.com/repos/xlang-ai/OpenAgents"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:05Z", "role": "primary", "sha256": "cf5a65d5a6b7ba2a9cf950421f6902534d523f7e8d850d1b23bd5395fd3d04c8", "supports": ["release_status", "details.repository_revision"], "url": "https://api.github.com/repos/xlang-ai/OpenAgents/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:34:10Z", "role": "primary", "sha256": "bcd2232e1ec4ad9ba0628cddd30031c364d62c6f112d8ecc2c24b9a4d35696af", "supports": ["release_status", "notes", "environments"], "url": "https://raw.githubusercontent.com/xlang-ai/OpenAgents/HEAD/frontend/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:45:23Z", "role": "primary", "sha256": "5b7084cfe6149602740cf4cd85e958142aed3aea0a0a0345a82ec1618ceb7b19", "supports": ["summary", "environments", "scope"], "url": "https://raw.githubusercontent.com/xlang-ai/OpenAgents/HEAD/real_agents/web_agent/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:34:09Z", "role": "primary", "sha256": "a86eea1027b8d92a68ded4231671379388df757992fa69d3e8fc8f8115d124fc", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/xlang-ai/OpenAgents/HEAD/LICENSE"}], "id": "component:xlang-ai/openagents/web_agent", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-17T12:30:54Z", "licenses": {"code": {"basis": "OpenAgents source license, scoped here to the reviewed Web Agent component; bundled third-party components retain their notices.", "declared": "Apache-2.0", "retrieved_at": "2026-10-17T12:34:09Z", "url": "https://raw.githubusercontent.com/xlang-ai/OpenAgents/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/xlang-ai/OpenAgents/tree/main/real_agents/web_agent"}], "name": "OpenAgents Web Agent", "notes": "This component record covers real_agents/web_agent and the documented WeBot Chrome-extension integration. The broader Data Agent and Plugins Agent are not treated as GUI-control assets. The source manifest includes the agent implementation and frontend/webot_extension.zip; the archive was not downloaded or executed. The README describes Docker deployment as under development and recommends source deployment. Apache-2.0 applies to project source; third-party extension/dependency notices remain separate.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/xlang-ai/OpenAgents/HEAD/README.md", "target_id": "arxiv:2310.10634", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "The OpenAgents browser-control component, connecting a Chrome extension to a web agent and local chat platform for navigating sites and completing interface tasks.", "topics": ["web-navigation", "automation", "tool-integration"], "updated_at": null, "url": "https://github.com/xlang-ai/OpenAgents/tree/main/real_agents/web_agent"}
{"aliases": [], "authors": [], "details": {}, "environments": ["desktop", "windows"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T13:14:29Z", "role": "primary", "sha256": "281793fe6b875bd1a63591502345ac9523b1127acd9f41d5c2c88933a357e4f2", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/Alokia/COLA-demo/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:38Z", "role": "primary", "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78", "supports": ["relations", "environments"], "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": "github:alokia/cola-demo", "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/Alokia/COLA-demo"}], "name": "COLA demo", "notes": "The publisher describes this as demonstration code and states that the full implementation is not released.", "published_at": null, "relations": [{"evidence_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", "target_id": "arxiv:2503.09263", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Research demonstration of collaborative Windows GUI automation with dynamic task scheduling and recovery mechanisms.", "topics": ["automation", "planning", "human-in-the-loop"], "updated_at": null, "url": "https://github.com/Alokia/COLA-demo"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android", "ios"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:04Z", "role": "primary", "sha256": "ecd5b8033cbc17a2ce5aebf1b35260b77c4906aea7c549a0b86e5d55b9ebe135", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/appium/appium/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:06Z", "role": "primary", "sha256": "5cb791a45cafc4bdaef57f3ba49fb7691a98c756e8148467f9e241295728490f", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/appium/appium/HEAD/LICENSE"}], "id": "github:appium/appium", "identifiers": {}, "kind": "infrastructure", "last_verified_at": "2026-10-16T06:36:04Z", "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/appium/appium/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/appium/appium"}], "name": "Appium", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Open-source WebDriver-based automation server for mobile, desktop and IoT apps, extended by per-platform drivers for iOS, Android, macOS and Windows, plugins, and clients in Java, Python, Ruby and C#.", "topics": ["automation"], "updated_at": null, "url": "https://github.com/appium/appium"}
{"aliases": [], "authors": [], "details": {}, "environments": ["desktop"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:04Z", "role": "primary", "sha256": "9e7a23adb62bd05d0fd45e5c95a57fcfc3cc4d19ab89d6801c5bf1e23d3c678c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/asweigart/pyautogui/HEAD/README.md"}], "id": "github:asweigart/pyautogui", "identifiers": {}, "kind": "infrastructure", "last_verified_at": "2026-10-16T06:36:04Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/asweigart/pyautogui"}], "name": "PyAutoGUI", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Cross-platform Python module for scripted mouse and keyboard control, message boxes and screenshots with on-screen image search, working on the primary monitor under Windows, macOS and Linux.", "topics": ["automation"], "updated_at": null, "url": "https://github.com/asweigart/pyautogui"}
{"aliases": [], "authors": [], "details": {}, "environments": ["unspecified"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:43:11Z", "role": "primary", "sha256": "dc60f683b0f44ccee4e54e5cbe1552ee3454e1ec4ed5c04635fedb83a325f51f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/bz-lab/AUITestAgent/HEAD/README.md"}], "id": "github:bz-lab/auitestagent", "identifiers": {}, "kind": "tool", "last_verified_at": "2026-10-16T10:43:11Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/bz-lab/AUITestAgent"}], "name": "AUITestAgent", "notes": "Its README describes mobile apps without naming an operating system.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/bz-lab/AUITestAgent/HEAD/README.md", "target_id": "arxiv:2407.09018", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Generates mobile GUI interactions from natural-language test requirements and checks application behavior against those requirements.", "topics": ["automation", "evaluation"], "updated_at": null, "url": "https://github.com/bz-lab/AUITestAgent"}
{"aliases": [], "authors": [], "details": {}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:40:53Z", "role": "primary", "sha256": "059a0349daaef6bda98eae6d9384ed349ac94b8033b18be817c317a01b472024", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/ChromeDevTools/chrome-devtools-mcp/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:07Z", "role": "primary", "sha256": "58d1e17ffe5109a7ae296caafcadfdbe6a7d176f0bc4ab01e12a689b0499d8bd", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/ChromeDevTools/chrome-devtools-mcp/HEAD/LICENSE"}], "id": "github:chromedevtools/chrome-devtools-mcp", "identifiers": {}, "kind": "tool", "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/ChromeDevTools/chrome-devtools-mcp/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/ChromeDevTools/chrome-devtools-mcp"}], "name": "Chrome DevTools MCP", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "MCP tools for browser control and inspection through Chrome DevTools.", "topics": ["automation", "tool-integration"], "updated_at": null, "url": "https://github.com/ChromeDevTools/chrome-devtools-mcp"}
{"aliases": [], "authors": [], "details": {"availability": "Published source; official release metadata inspected", "release_tag": "v0.8.8"}, "environments": ["windows", "desktop", "web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "bbec20828c8a0f5483be68f6a00c47b202e9431268d96c1195fbf0745aca1364", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/CursorTouch/Windows-MCP/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "ef43250ad8e57c3267f2a8e0aaeb655eb3445ade8d2dee8c243dc6e241a9d2d8", "supports": ["identity"], "url": "https://api.github.com/repos/CursorTouch/Windows-MCP"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "652b580c99ac2de9d56d124225ba302f0dd83430ccc9b5162e16f683c56b952f", "supports": ["release_status"], "url": "https://api.github.com/repos/CursorTouch/Windows-MCP/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:00:58Z", "role": "primary", "sha256": "db3de978027106a991da3f7f2d78b216cfffee9b08604872fa3216927acc7a2d", "supports": ["release_status"], "url": "https://api.github.com/repos/CursorTouch/Windows-MCP/releases/latest"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:00:59Z", "role": "primary", "sha256": "20ced59173768e20e91a43e3a80443aa1200b129c134f07f0cc45779747a1743", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/CursorTouch/Windows-MCP/HEAD/LICENSE.md"}, {"method": "license_header", "retrieved_at": "2026-10-17T04:00:59Z", "role": "primary", "sha256": "20ced59173768e20e91a43e3a80443aa1200b129c134f07f0cc45779747a1743", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/CursorTouch/Windows-MCP/HEAD/LICENSE.md"}], "id": "github:cursortouch/windows-mcp", "identifiers": {}, "kind": "tool", "last_verified_at": "2026-10-17T03:59:53Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-17T04:00:59Z", "url": "https://raw.githubusercontent.com/CursorTouch/Windows-MCP/HEAD/LICENSE.md"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/CursorTouch/Windows-MCP"}], "name": "Windows-MCP", "notes": "Public source and official release metadata are present. The README explicitly supports Windows 10 and 11 and includes a browser DOM inspection mode. Code is MIT-licensed. This is an execution tool, not a trained model; runtime behavior and latency claims were not independently tested.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "A Windows MCP bridge exposing application, window, keyboard and mouse operations plus native UI-state inspection for agents.", "topics": ["tool-integration", "automation", "screen-understanding"], "updated_at": null, "url": "https://github.com/CursorTouch/Windows-MCP"}
{"aliases": [], "authors": [], "details": {}, "environments": ["android", "ios"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:42:12Z", "role": "primary", "sha256": "0d05433c730e74f13be753fa6156737f797a69d61d8793e47f5a56b3a63ee790", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/droidrun/mobile-harness/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T10:48:41Z", "role": "primary", "sha256": "de215a2914d50cb87fcab9e19efc856b9e600a68eefec5c63e284dae34977133", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/droidrun/mobile-harness/HEAD/LICENSE"}], "id": "github:droidrun/mobile-harness", "identifiers": {}, "kind": "tool", "last_verified_at": "2026-10-16T10:42:12Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T10:48:41Z", "url": "https://raw.githubusercontent.com/droidrun/mobile-harness/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/droidrun/mobile-harness"}], "name": "Mobile Harness", "notes": "The publisher describes this as a Markdown harness, not an agent runtime. Published benchmark results have not been independently reproduced.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Portable agent instructions and integration tooling for local or cloud phone control through mobilerun-core.", "topics": ["automation", "tool-integration"], "updated_at": null, "url": "https://github.com/droidrun/mobile-harness"}
{"aliases": ["STEVE", "STEVE-R1"], "authors": [], "details": {}, "environments": ["desktop", "windows", "linux"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T13:14:29Z", "role": "primary", "sha256": "52aa383fdf5d91951f5d9a73f4ebed4454a82b35edae296918116e9f0895dd83", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/FanbinLu/STEVE/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["relations", "environments"], "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": "github:fanbinlu/steve-r1", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-16T13:14:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/FanbinLu/STEVE-R1"}], "name": "STEVE / STEVE-R1 research code", "notes": "The repository has moved to STEVE-R1. Its README reports an SFT release, with RL tuning in progress, and describes evaluations using multiple attempts per task. These results are not independently reproduced here.", "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=700&max_results=100&sortBy=submittedDate&sortOrder=descending", "target_id": "arxiv:2503.12532", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Research code and linked models for step-verified computer-use training; the current repository describes STEVE-R1 and its trajectory releases.", "topics": ["data-generation", "automation", "evaluation"], "updated_at": null, "url": "https://github.com/FanbinLu/STEVE-R1"}
{"aliases": [], "authors": [], "details": {"license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/GAIR-NLP/PC-Agent-E/HEAD/LICENSE"], "reason": "Reviewed repository license declaration for code; third-party dependencies, data, weights and executable environment images are separate."}}, "repository_tree_sha": "9b1b00b907b99a4a8dbfc9c01ea49010878dfbd6", "repository_url": "https://github.com/GAIR-NLP/PC-Agent-E"}, "environments": ["desktop", "windows", "linux"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:27:13Z", "role": "primary", "sha256": "3ffb8c843c6acb8c2d5bbba11ba49d6b36cd566553a89974b6252a2bfd289d5d", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations"], "url": "https://raw.githubusercontent.com/GAIR-NLP/PC-Agent-E/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T15:37:01Z", "role": "primary", "sha256": "30761141ea62c5f20183f359bbc3fc8ccc5b458886d38c5426bae4802a23ee0b", "supports": ["identity"], "url": "https://api.github.com/repos/GAIR-NLP/PC-Agent-E"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:25:23Z", "role": "primary", "sha256": "2fb2aa4ee6f02ccadb631dab4972f96c3fdf545cd92c5854fc191e81cf4ae88a", "supports": ["identity", "release_status", "details.repository_tree_sha"], "url": "https://api.github.com/repos/GAIR-NLP/PC-Agent-E/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:35:19Z", "role": "primary", "sha256": "39e37b84c067596361c491e2e9e22af8805386a24b8352b87e9aca3bddf4f92c", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/GAIR-NLP/PC-Agent-E/HEAD/LICENSE"}], "id": "github:gair-nlp/pc-agent-e", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-18T04:27:13Z", "licenses": {"code": {"basis": "Reviewed repository license declaration for code; third-party dependencies, data, weights and executable environment images are separate.", "declared": "MIT", "retrieved_at": "2026-10-18T04:35:19Z", "url": "https://raw.githubusercontent.com/GAIR-NLP/PC-Agent-E/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/GAIR-NLP/PC-Agent-E"}], "name": "PC-Agent-E training and deployment", "notes": "README demonstrates Windows and Linux operation and describes thought completion and trajectory augmentation. The released source tree contains postprocess, train and deploy code. The checkpoint, data archive and WindowsAgentArena-V2 are separate resources; external model APIs and a training framework are required.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/GAIR-NLP/PC-Agent-E/HEAD/README.md", "target_id": "arxiv:2505.13909", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Tools for refining and augmenting human computer-use trajectories, preparing supervised training data, and deploying a native PC-Agent-E scaffold.", "topics": ["data-generation", "imitation-learning", "automation"], "updated_at": null, "url": "https://github.com/GAIR-NLP/PC-Agent-E"}
{"aliases": [], "authors": [], "details": {}, "environments": ["desktop"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:42:12Z", "role": "primary", "sha256": "2e42f01578710d91145412f7d1ecb93979db96c698f677915284da1a1d592588", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/GaryYang12345/GUI-HARVEST/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "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=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "license_header", "retrieved_at": "2026-10-16T10:48:42Z", "role": "primary", "sha256": "cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/GaryYang12345/GUI-HARVEST/HEAD/LICENSE"}], "id": "github:garyyang12345/gui-harvest", "identifiers": {}, "kind": "framework", "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": "2026-10-16T10:48:42Z", "url": "https://raw.githubusercontent.com/GaryYang12345/GUI-HARVEST/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/GaryYang12345/GUI-HARVEST"}], "name": "GUI-HARVEST", "notes": "Requires a separately installed benchmark and seed agent harness; benchmark tasks and model weights remain fixed during its optimization procedure.", "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=0&max_results=100&sortBy=submittedDate&sortOrder=descending", "target_id": "arxiv:2610.00948", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Optimizes GUI-agent execution code from repeated rollout evidence and checks proposed changes against fixed validation gates.", "topics": ["automation", "observability", "robustness"], "updated_at": null, "url": "https://github.com/GaryYang12345/GUI-HARVEST"}
{"aliases": ["github:deepmind/android_env", "deepmind/android_env", "https://github.com/deepmind/android_env"], "authors": [], "details": {}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:42:12Z", "role": "primary", "sha256": "b8dd2ea004647008265f4fb5c5a122569992311b6758f413080984266e53c25a", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/google-deepmind/android_env/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T10:48:41Z", "role": "primary", "sha256": "58d1e17ffe5109a7ae296caafcadfdbe6a7d176f0bc4ab01e12a689b0499d8bd", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/google-deepmind/android_env/HEAD/LICENSE"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-17T15:37:19Z", "role": "primary", "sha256": "de82c4101e81a6980789904be59c3733ab13f2c1f0e769e5fcb1ab35f847cb3e", "supports": ["aliases"], "url": "https://api.github.com/repos/deepmind/android_env"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-17T15:37:20Z", "role": "primary", "sha256": "de82c4101e81a6980789904be59c3733ab13f2c1f0e769e5fcb1ab35f847cb3e", "supports": ["aliases"], "url": "https://api.github.com/repos/google-deepmind/android_env"}], "id": "github:google-deepmind/android_env", "identifiers": {}, "kind": "infrastructure", "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/google-deepmind/android_env/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/google-deepmind/android_env"}], "name": "AndroidEnv", "notes": "Formerly published as deepmind/android_env. That address now redirects to this repository, and both paths serve the same reviewed README, so the project is counted once.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/google-deepmind/android_env/HEAD/README.md", "target_id": "arxiv:2105.13231", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Android device-control platform with screenshots, accessibility telemetry, input actions, and an optional reinforcement-learning task interface.", "topics": ["sandbox", "reinforcement-learning", "automation"], "updated_at": null, "url": "https://github.com/google-deepmind/android_env"}
{"aliases": ["github:dvlab-research/arpo", "dvlab-research/ARPO", "https://github.com/dvlab-research/ARPO"], "authors": [], "details": {"license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/JIA-Lab-research/ARPO/HEAD/LICENSE"], "reason": "Reviewed repository license declaration for code; third-party dependencies, data, weights and executable environment images are separate."}}, "repository_tree_sha": "7489ae309e90d8b3b9e823f495b63e5116434060", "repository_url": "https://github.com/JIA-Lab-research/ARPO"}, "environments": ["desktop", "linux"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:27:12Z", "role": "primary", "sha256": "839b2de0e0c614fe8d2df4782d0f6a6e7d33f5c60d8020c9d4a01c61d533f39e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations"], "url": "https://raw.githubusercontent.com/JIA-Lab-research/ARPO/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:40:39Z", "role": "primary", "sha256": "bb64c7fc1b5d88fc070e919516a51eefac4acb89e86773464cfa0b3de18f1898", "supports": ["identity"], "url": "https://api.github.com/repos/JIA-Lab-research/ARPO"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:25:23Z", "role": "primary", "sha256": "b3ff7f4e350223827cae0fffd986ee672e0b4466349c262ed2dc9e63a8480aeb", "supports": ["identity", "release_status", "details.repository_tree_sha"], "url": "https://api.github.com/repos/JIA-Lab-research/ARPO/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T15:37:00Z", "role": "primary", "sha256": "bb64c7fc1b5d88fc070e919516a51eefac4acb89e86773464cfa0b3de18f1898", "supports": ["identity"], "url": "https://api.github.com/repos/dvlab-research/ARPO"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:35:19Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/JIA-Lab-research/ARPO/HEAD/LICENSE"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-17T15:37:00Z", "role": "primary", "sha256": "bb64c7fc1b5d88fc070e919516a51eefac4acb89e86773464cfa0b3de18f1898", "supports": ["aliases"], "url": "https://api.github.com/repos/dvlab-research/ARPO"}, {"method": "github_repository_identity", "retrieved_at": "2026-10-18T04:40:39Z", "role": "primary", "sha256": "bb64c7fc1b5d88fc070e919516a51eefac4acb89e86773464cfa0b3de18f1898", "supports": ["aliases"], "url": "https://api.github.com/repos/JIA-Lab-research/ARPO"}], "id": "github:jia-lab-research/arpo", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-18T04:27:12Z", "licenses": {"code": {"basis": "Reviewed repository license declaration for code; third-party dependencies, data, weights and executable environment images are separate.", "declared": "Apache-2.0", "retrieved_at": "2026-10-18T04:35:19Z", "url": "https://raw.githubusercontent.com/JIA-Lab-research/ARPO/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/JIA-Lab-research/ARPO"}], "name": "ARPO training framework", "notes": "Official GitHub API resolves the former dvlab-research/ARPO URL to JIA-Lab-research/ARPO with the same numeric repository ID. Training/evaluation scripts are released; OSWorld environments and the separate model checkpoint are not bundled into this code record. Reported benchmark scores were not reproduced.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/JIA-Lab-research/ARPO/HEAD/README.md", "target_id": "arxiv:2505.16282", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Replay-based policy-optimization framework for GUI agents, with distributed OSWorld rollouts and screenshot/action histories.", "topics": ["reinforcement-learning", "long-horizon", "automation"], "updated_at": null, "url": "https://github.com/JIA-Lab-research/ARPO"}
{"aliases": [], "authors": [], "details": {}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:04Z", "role": "primary", "sha256": "0a6a9dddcbf1295b61e83462ee7aa130289a4d4e60bac1a0deccd661f8fc8146", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/microsoft/playwright/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:06Z", "role": "primary", "sha256": "45873d00a0dd243596deb4aa23b2493b3d1f0671921bf2538ea431d7380220eb", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/microsoft/playwright/HEAD/LICENSE"}], "id": "github:microsoft/playwright", "identifiers": {}, "kind": "infrastructure", "last_verified_at": "2026-10-16T06:36:04Z", "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/microsoft/playwright/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/microsoft/playwright"}], "name": "Playwright", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Browser automation library used as an execution layer by agents.", "topics": ["automation"], "updated_at": null, "url": "https://github.com/microsoft/playwright"}
{"aliases": [], "authors": [], "details": {}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:40:53Z", "role": "primary", "sha256": "b33aa71a13d655e96e6b736d0c9de1e5ddea52f205916ca20b876387ff830e87", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/microsoft/playwright-mcp/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:07Z", "role": "primary", "sha256": "9a7110fc2d2f964038e5dc49128f908f29f47a574c961cba16085914e879cbda", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/microsoft/playwright-mcp/HEAD/LICENSE"}], "id": "github:microsoft/playwright-mcp", "identifiers": {}, "kind": "tool", "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/microsoft/playwright-mcp/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/microsoft/playwright-mcp"}], "name": "Playwright MCP", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "MCP server that lets LLM clients drive Playwright browsers through structured accessibility snapshots instead of screenshots, with opt-in vision, PDF and devtools capabilities.", "topics": ["automation", "tool-integration"], "updated_at": null, "url": "https://github.com/microsoft/playwright-mcp"}
{"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": {"availability": "Published source; official release metadata inspected", "release_tag": "v0.3.0"}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:54Z", "role": "primary", "sha256": "4d8a0b0d6286c4bab116c155f087948062166e7e169d6bbaf504fedb4f32dc67", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/nanobrowser/nanobrowser/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "6b48386f32a971a724906de8b6d5ea53036f3813411ddc12931be3010c034400", "supports": ["identity"], "url": "https://api.github.com/repos/nanobrowser/nanobrowser"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:54Z", "role": "primary", "sha256": "afd0b71b01d3d89033d8f32abaf9871f38e8fb0c50442ed3a8cbb3079d4a4fe0", "supports": ["release_status"], "url": "https://api.github.com/repos/nanobrowser/nanobrowser/git/trees/master?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:00Z", "role": "primary", "sha256": "c7b28db1b1c8e78d100da066b08db713bc144baff99941b6c94489ef61baee8f", "supports": ["release_status"], "url": "https://api.github.com/repos/nanobrowser/nanobrowser/releases/latest"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:00Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/nanobrowser/nanobrowser/HEAD/LICENSE"}, {"method": "license_header", "retrieved_at": "2026-10-17T04:01:00Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/nanobrowser/nanobrowser/HEAD/LICENSE"}], "id": "github:nanobrowser/nanobrowser", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-17T03:59:54Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-17T04:01:00Z", "url": "https://raw.githubusercontent.com/nanobrowser/nanobrowser/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/nanobrowser/nanobrowser"}], "name": "Nanobrowser", "notes": "The official repository publishes extension source and a v0.3.0 ZIP release. It names Chrome and Edge as supported browsers. Apache-2.0 is declared for the code. Ask/Auto behavior and provider choices are documented, but no security guarantee, model performance or service-price claim is inferred.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "A browser-extension agent that reads pages, interacts with elements and moves between tabs from a side-panel task interface.", "topics": ["web-navigation", "automation", "human-in-the-loop"], "updated_at": null, "url": "https://github.com/nanobrowser/nanobrowser"}
{"aliases": [], "authors": [], "details": {}, "environments": ["desktop"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:04Z", "role": "primary", "sha256": "41a6435d6c27a647b4d2170cba476fa6a941b12f8a4ffe41674a508df9e0ea1d", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/nut-tree/nut.js/HEAD/README.md"}], "id": "github:nut-tree/nut.js", "identifiers": {}, "kind": "infrastructure", "last_verified_at": "2026-10-16T06:36:04Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/nut-tree/nut.js"}], "name": "Nut.js", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Desktop automation library for keyboard, mouse, and screen interaction.", "topics": ["automation"], "updated_at": null, "url": "https://github.com/nut-tree/nut.js"}
{"aliases": ["Oculix", "SikuliX continuation"], "authors": [], "details": {"availability": "Public source and official stable release assets.", "license_components_note": "Project source declares MIT; the retained third-party dependency notices describe additional component terms.", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/oculix-org/Oculix/HEAD/LICENSE"], "reason": "Publisher project-source LICENSE. Third-party dependency notices are separately retained and no blanket MIT assertion is made for the compiled distribution."}}, "release_tag": "v4.0.0", "repository_revision": "02ea8844483a83a2963db8016cd7ad421e15bc91"}, "environments": ["desktop", "windows", "macos", "linux", "android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:14Z", "role": "primary", "sha256": "41d32f40bfb960f38b77ebb62a73ae20454be6c52829c9cbf0b8fedd27de2297", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations"], "url": "https://raw.githubusercontent.com/oculix-org/Oculix/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:14Z", "role": "primary", "sha256": "151ed1aaf544b9afcfd2d8f13d0fa682d8cf8f8a68496af20c3597b082070801", "supports": ["identity"], "url": "https://api.github.com/repos/oculix-org/Oculix"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:19:48Z", "role": "primary", "sha256": "cba4541e5d89210b570e42cc69c1529ca36e698622c69b4bb0eeffe56339a759", "supports": ["release_status", "details.repository_revision"], "url": "https://api.github.com/repos/oculix-org/Oculix/git/trees/master?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:08Z", "role": "primary", "sha256": "1022eb9591a2f01833e88c2bae2869faeac9b92e535901d2c79e93a714278777", "supports": ["release_status", "details.release_tag", "environments", "notes"], "url": "https://api.github.com/repos/oculix-org/Oculix/releases/latest"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:14Z", "role": "primary", "sha256": "8994ff2000b0871aca819ecd7233430bb82cea3f0134a555cebbfa9e02e0f4da", "supports": ["identity", "relations", "notes"], "url": "https://raw.githubusercontent.com/oculix-org/SikuliX1/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:13Z", "role": "primary", "sha256": "102b86e9019fe5e936486b3213d2bbd9e80d6c7ad393284b1a4298b0be555ce7", "supports": ["identity"], "url": "https://api.github.com/repos/RaiMan/SikuliX1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:03Z", "role": "primary", "sha256": "cea4b6292d59625e14968ec666faa7ae6e237b510d846a96875bd6a282677f3a", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/oculix-org/Oculix/HEAD/LICENSE"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:27:50Z", "role": "primary", "sha256": "f0e0d8aa91c1c60bac2250688248c85503036aeac37ec02b8a75fe9d50b6ae4c", "supports": ["licenses.code", "notes"], "url": "https://raw.githubusercontent.com/oculix-org/Oculix/HEAD/API/src/main/resources/Settings/THIRD-PARTY.txt"}], "id": "github:oculix-org/oculix", "identifiers": {}, "kind": "tool", "last_verified_at": "2026-10-17T11:18:14Z", "licenses": {"code": {"basis": "Publisher project-source LICENSE. Third-party dependency notices are separately retained and no blanket MIT assertion is made for the compiled distribution.", "declared": "MIT", "retrieved_at": "2026-10-17T11:23:03Z", "url": "https://raw.githubusercontent.com/oculix-org/Oculix/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/oculix-org/Oculix"}], "name": "OculiX (SikuliX continuation)", "notes": "The official stable-release API lists v4.0.0 with platform-specific API/IDE JARs and an MCP server JAR; no binary was downloaded. The default README still advertises 3.0.3, so release-specific compatibility follows the release notes rather than that older badge. The RaiMan/SikuliX1 API resolves to oculix-org/SikuliX1, whose README calls itself a historical mirror and directs current users here; it is not separately counted. MIT describes the project source. Retained dependency notices also include GPL/LGPL, Apache, BSD and MPL declarations; a bundled artifact is not asserted to be uniformly MIT.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/oculix-org/Oculix/HEAD/README.md", "target_id": "github:sikuli/sikuli", "type": "variant_of"}], "review_status": "curated", "scope": "core", "summary": "A maintained continuation of SikuliX that locates on-screen targets with image matching and OCR, drives desktop or Android interfaces, and exposes scripting and optional MCP interfaces.", "topics": ["automation", "grounding", "tool-integration"], "updated_at": null, "url": "https://github.com/oculix-org/Oculix"}
{"aliases": [], "authors": [], "details": {"availability": "Public browser-agent source and npm release metadata.", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/omxyz/lumen/HEAD/LICENSE"], "reason": "Publisher project-source license; external model and browser-service terms are separate."}}, "package_version": "0.2.0", "repository_revision": "b1ad26a0784645ac3a97d402db99cd5d17f86334"}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:55Z", "role": "primary", "sha256": "7708f434142498959bb5ed5de35ac1b945f9ad6e070e436b4e73819b7db1df7f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://raw.githubusercontent.com/omxyz/lumen/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:55Z", "role": "primary", "sha256": "32b02ea43d19929d82e8b8c52bb8e448553aebdd96a8754d144927cb0f34c5b6", "supports": ["identity"], "url": "https://api.github.com/repos/omxyz/lumen"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:05Z", "role": "primary", "sha256": "9911953e501a245d657f3835b22c6822ad7d990b96f03e3cba93a15ebe4f70a6", "supports": ["release_status", "details.repository_revision"], "url": "https://api.github.com/repos/omxyz/lumen/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:34:10Z", "role": "primary", "sha256": "34a03b6dd8cd1960d5592a6569e2a1c1f6c1b2697da1386a58d0ca64157f059e", "supports": ["identity", "release_status", "details.package_version", "notes"], "url": "https://registry.npmjs.org/@omxyz%2Flumen/latest"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:34:10Z", "role": "primary", "sha256": "30dd5336a8a45b548b9051e751d45923a9864b3810a36c836df9b07447ca3c5c", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/omxyz/lumen/HEAD/LICENSE"}], "id": "github:omxyz/lumen", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-17T12:30:55Z", "licenses": {"code": {"basis": "Publisher project-source license; external model and browser-service terms are separate.", "declared": "MIT", "retrieved_at": "2026-10-17T12:34:10Z", "url": "https://raw.githubusercontent.com/omxyz/lumen/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/omxyz/lumen"}], "name": "Lumen browser agent", "notes": "Public TypeScript source and npm package metadata are available; the inspected package version is 0.2.0. The package declares Node ^20.19.0 or >=22.12.0 and requires a browser and model provider. Its README benchmark is explicitly preliminary and uses a small WebVoyager subset; this catalog makes no comparative performance or independent safety claim. Referenced research influences are not asserted as papers introducing Lumen.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "A screenshot-driven browser agent over Chrome DevTools Protocol, with resumable sessions, context compression, action replay and configurable completion checks.", "topics": ["web-navigation", "memory", "automation", "observability"], "updated_at": null, "url": "https://github.com/omxyz/lumen"}
{"aliases": [], "authors": [], "details": {"availability": "Public archived client source; remote benchmark services and images are not verified usable.", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/openai/universe/HEAD/LICENSE"], "reason": "Official Universe client-source LICENSE; no license or availability claim is transferred to external remote applications or container contents."}}, "maintenance_status": "archived and deprecated", "repository_revision": "cc9ce6ec241821bfb0f3b85dd455bd36e4ee7a8c"}, "environments": ["web", "desktop"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:20:17Z", "role": "primary", "sha256": "b1ca938480d4d36c76fa939c5b10cef11c24465cc1a6a8ee857cec4b939f9d61", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://raw.githubusercontent.com/openai/universe/HEAD/README.rst"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:15Z", "role": "primary", "sha256": "94a7a4d383f754b96601bc0486b90e62760b8bfc35abc607077c8eb6e7934b2d", "supports": ["identity", "details.availability", "notes"], "url": "https://api.github.com/repos/openai/universe"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:19:47Z", "role": "primary", "sha256": "1808d7524506d1386dad507de8a8fa0f89080443a970ae032cea4c204699d113", "supports": ["release_status", "details.repository_revision"], "url": "https://api.github.com/repos/openai/universe/git/trees/master?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:05Z", "role": "primary", "sha256": "ecd4a4aacc4512a31bbdc3252ffc014d37ac7ef56ed34bc2a5d0f6337df6daa5", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/openai/universe/HEAD/LICENSE"}], "id": "github:openai/universe", "identifiers": {}, "kind": "infrastructure", "last_verified_at": "2026-10-17T11:20:17Z", "licenses": {"code": {"basis": "Official Universe client-source LICENSE; no license or availability claim is transferred to external remote applications or container contents.", "declared": "MIT", "retrieved_at": "2026-10-17T11:23:05Z", "url": "https://raw.githubusercontent.com/openai/universe/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/openai/universe"}], "name": "Universe legacy GUI interaction client", "notes": "GitHub marks this repository archived, and the README declares the library deprecated. It contains the client side of Universe; the README says remote-environment source repositories would be released separately. Original MiniWoB task-server or container availability was not established: alpha.openai.com no longer resolved in this audit and the official Quay tag metadata endpoint returned 401. This entry records the released client infrastructure, not a currently runnable original MiniWoB benchmark. Legacy host requirements are documented; no container or code was executed.", "published_at": null, "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "An archived Gym-compatible client that exposes screen observations and keyboard/mouse actions over VNC for remote application and browser environments, including the historical World of Bits integration.", "topics": ["automation", "reinforcement-learning", "history"], "updated_at": null, "url": "https://github.com/openai/universe"}
{"aliases": [], "authors": [], "details": {}, "environments": ["desktop", "windows", "macos"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:09:28Z", "role": "primary", "sha256": "ad5553270b67c335df4d4e909f1549f43af8e74ad687f9cbcc812761affcad5c", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/showlab/ShowUI-Aloha/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T11:15:55Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/showlab/ShowUI-Aloha/HEAD/LICENSE"}], "id": "github:showlab/showui-aloha", "identifiers": {}, "kind": "agent", "last_verified_at": "2026-10-16T11:09:28Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T11:15:55Z", "url": "https://raw.githubusercontent.com/showlab/ShowUI-Aloha/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/showlab/ShowUI-Aloha"}], "name": "ShowUI-Aloha", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/showlab/ShowUI-Aloha/HEAD/README.md", "target_id": "arxiv:2601.07181", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Desktop agent that records demonstrations, derives semantic action traces, and uses them to plan and execute related workflows.", "topics": ["recording", "workflow", "automation"], "updated_at": null, "url": "https://github.com/showlab/ShowUI-Aloha"}
{"aliases": ["ShowUI-pi", "ShowUI Pi"], "authors": [], "details": {}, "environments": ["desktop"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:09:28Z", "role": "primary", "sha256": "88df552ccbe80efd7020905d77d526f4f9efe2d09a11fed2714b083988f9dcef", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/showlab/showui-pi/HEAD/README.md"}], "id": "github:showlab/showui-pi", "identifiers": {}, "kind": "model", "last_verified_at": "2026-10-16T11:09:28Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/showlab/showui-pi"}], "name": "ShowUI-π", "notes": "", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/showlab/showui-pi/HEAD/README.md", "target_id": "arxiv:2512.24965", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Vision-language-action model and training code for GUI dragging, with links to checkpoints and continuous-action evaluation data.", "topics": ["grounding", "automation"], "updated_at": null, "url": "https://github.com/showlab/showui-pi"}
{"aliases": [], "authors": [], "details": {"availability": "Public legacy source and original documentation; maintainers explicitly state it is no longer supported.", "license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/sikuli/sikuli/HEAD/copyright.txt"], "reason": "Original Sikuli copyright/license file for project source; bundled third-party libraries are not relicensed by this assertion."}}, "maintenance_status": "unsupported legacy research code", "repository_revision": "4adaab7880d2f3e14702ca7287ae9c9e4f4de9ab"}, "environments": ["desktop", "macos", "linux", "windows"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:28:12Z", "role": "primary", "sha256": "e752b2226af679a778e21506e660742376be3d7effe621f63c0b8816d3323729", "supports": ["name", "kind", "summary", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/sikuli/sikuli/HEAD/docs/source/index.rst"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:12Z", "role": "primary", "sha256": "90d840ab98d35b90c0f91f93dc2dc752eac631a4bdc299601bffe8856610dd4c", "supports": ["identity"], "url": "https://api.github.com/repos/sikuli/sikuli"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:19:49Z", "role": "primary", "sha256": "8ee5f1e75659bfbce0d9b22967ff2b51335be5f19a3dc9e645273cc51333153e", "supports": ["release_status", "details.repository_revision"], "url": "https://api.github.com/repos/sikuli/sikuli/git/trees/develop?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:13Z", "role": "primary", "sha256": "ed7659fff11dac079b99ad3c264f7e1e0a97f313a75379067e1c7fccca23ef88", "supports": ["notes", "details.availability", "relations"], "url": "https://raw.githubusercontent.com/sikuli/sikuli/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:28:13Z", "role": "primary", "sha256": "bab2f2dae13092e9c94f5d4b077bc96a6aa7da5257b54089f76ff5c0b0f61402", "supports": ["summary", "environments"], "url": "https://raw.githubusercontent.com/sikuli/sikuli/HEAD/docs/source/tutorials/helloworld/helloworld-mac.rst"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:28:13Z", "role": "primary", "sha256": "28354a06091997d233cc5124958d85b75a5d815677c58b4fbabd492a6b0038d3", "supports": ["environments"], "url": "https://raw.githubusercontent.com/sikuli/sikuli/HEAD/build-linux.txt"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:28:13Z", "role": "primary", "sha256": "b7c66064d08c6a768a4ed93fee0f86f837b41d51e60785d44a59d7a13bd2452a", "supports": ["environments"], "url": "https://raw.githubusercontent.com/sikuli/sikuli/HEAD/build-win32.txt"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:03Z", "role": "primary", "sha256": "717e5c54ef8201b2307c9828a6bacb7710385e5014adba93e5f1dc444339fdab", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/sikuli/sikuli/HEAD/copyright.txt"}], "id": "github:sikuli/sikuli", "identifiers": {}, "kind": "tool", "last_verified_at": "2026-10-17T11:28:12Z", "licenses": {"code": {"basis": "Original Sikuli copyright/license file for project source; bundled third-party libraries are not relicensed by this assertion.", "declared": "MIT", "retrieved_at": "2026-10-17T11:23:03Z", "url": "https://raw.githubusercontent.com/sikuli/sikuli/HEAD/copyright.txt"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/sikuli/sikuli"}], "name": "Sikuli legacy research implementation", "notes": "This is the retained Sikuli X-1.0rc3 source line, explicitly marked unsupported by its maintainers. Its documented build targets include historical macOS, Linux and Windows setups; present-day build compatibility was not tested. The official documentation cites the 2009 search/automation and 2010 visual-testing papers. Follow-up SikuliX and current OculiX are distinguished from this legacy research implementation. MIT applies to project code; external libraries keep their own terms.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/sikuli/sikuli/HEAD/docs/source/index.rst", "target_id": "url:a4cdb2ee0d07d3980651", "type": "documented_by"}, {"evidence_url": "https://raw.githubusercontent.com/sikuli/sikuli/HEAD/docs/source/index.rst", "target_id": "url:6262c757080f8838e62c", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "The original Sikuli source distribution combines screenshot targets with a Jython scripting library and IDE for visual GUI automation and testing.", "topics": ["automation", "grounding", "screen-understanding", "history"], "updated_at": null, "url": "https://github.com/sikuli/sikuli"}
{"aliases": [], "authors": [], "details": {"license_review": {"code": {"evidence_urls": ["https://raw.githubusercontent.com/sunblaze-ucb/AgentSynth/HEAD/LICENSE"], "reason": "Reviewed repository license declaration for code; third-party dependencies, data, weights and executable environment images are separate."}}, "repository_tree_sha": "cd42a4bd158fe3f0a1b0f376b9428d6a5fcb81b2", "repository_url": "https://github.com/sunblaze-ucb/AgentSynth"}, "environments": ["desktop", "web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:27:12Z", "role": "primary", "sha256": "42e8b8dead7caea3f8b21e93a075e8c895dfc30a25e1470bf97a90940bbf0106", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "relations"], "url": "https://raw.githubusercontent.com/sunblaze-ucb/AgentSynth/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T15:37:00Z", "role": "primary", "sha256": "e08f08a99b8cb3a4bb857a9fac976b2820f9ad406d66675b0286e880dfeeceaa", "supports": ["identity"], "url": "https://api.github.com/repos/sunblaze-ucb/AgentSynth"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:25:20Z", "role": "primary", "sha256": "b0998652a9b6b465444c2bbeef015bdbef50e83984a3bd15725f0e811645ca62", "supports": ["identity", "release_status", "details.repository_tree_sha"], "url": "https://api.github.com/repos/sunblaze-ucb/AgentSynth/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:35:19Z", "role": "primary", "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/sunblaze-ucb/AgentSynth/HEAD/LICENSE"}], "id": "github:sunblaze-ucb/agentsynth", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-18T04:27:12Z", "licenses": {"code": {"basis": "Reviewed repository license declaration for code; third-party dependencies, data, weights and executable environment images are separate.", "declared": "Apache-2.0", "retrieved_at": "2026-10-18T04:35:19Z", "url": "https://raw.githubusercontent.com/sunblaze-ucb/AgentSynth/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/sunblaze-ucb/AgentSynth"}], "name": "AgentSynth task-generation pipeline", "notes": "Released code includes task-generation and training-format conversion scripts. OSWorld/InSTA environments and model services require separate setup; the repository is not a bundled VM or model checkpoint. Code and the separately published dataset have distinct license declarations.", "published_at": null, "relations": [{"evidence_url": "https://raw.githubusercontent.com/sunblaze-ucb/AgentSynth/HEAD/README.md", "target_id": "arxiv:2506.14205", "type": "documented_by"}], "review_status": "curated", "scope": "core", "summary": "Generates synthetic computer-use tasks and records trajectories in OSWorld desktop environments and InSTA browser environments.", "topics": ["data-generation", "long-horizon", "automation"], "updated_at": null, "url": "https://github.com/sunblaze-ucb/AgentSynth"}
{"aliases": [], "authors": [], "details": {"availability": "Published source; official release metadata inspected", "release_tag": "v0.39.1"}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "4a9783ee8ebee10caaedfe2bdd2182539368e60e8eefadaee4cb7bab7fc75c12", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/vercel-labs/agent-browser/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "6b1120e122d5d110b0da568fbbf0560fd81a4cf8d50602c397a8382617343329", "supports": ["identity"], "url": "https://api.github.com/repos/vercel-labs/agent-browser"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:53Z", "role": "primary", "sha256": "6a90f0b79089f895fab5d35443fd113faa056f404c807966b23210c1c427e62e", "supports": ["release_status"], "url": "https://api.github.com/repos/vercel-labs/agent-browser/git/trees/main?recursive=1"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:00:55Z", "role": "primary", "sha256": "1a4213f48240031c7837e9651bda8cebb84d69d0d97a65f012082a53a7a1f702", "supports": ["release_status"], "url": "https://api.github.com/repos/vercel-labs/agent-browser/releases/latest"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:00:56Z", "role": "primary", "sha256": "014bb31e83d5c2e76aea1cc6e82217346ab41362f32cb355ad0f5c10aa0aeaff", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/vercel-labs/agent-browser/HEAD/LICENSE"}, {"method": "license_header", "retrieved_at": "2026-10-17T04:00:56Z", "role": "primary", "sha256": "014bb31e83d5c2e76aea1cc6e82217346ab41362f32cb355ad0f5c10aa0aeaff", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/vercel-labs/agent-browser/HEAD/LICENSE"}], "id": "github:vercel-labs/agent-browser", "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": "2026-10-17T04:00:56Z", "url": "https://raw.githubusercontent.com/vercel-labs/agent-browser/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/vercel-labs/agent-browser"}], "name": "agent-browser", "notes": "The repository publishes a Rust-based CLI and platform-specific release binaries. The inspected release is v0.39.1. Apache-2.0 is declared for the code; Chrome and other external browser components retain separate terms. No package or browser was installed.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "A browser-automation command-line interface that exposes browser state and interaction commands for AI agents.", "topics": ["web-navigation", "automation", "tool-integration"], "updated_at": null, "url": "https://github.com/vercel-labs/agent-browser"}
{"aliases": [], "authors": [], "details": {}, "environments": ["cross-platform"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:40:53Z", "role": "primary", "sha256": "8cd83b12f4e1c1b22c27b6ae3ee5415564e61ff4072349ec512982a548ea6ec3", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://raw.githubusercontent.com/web-infra-dev/midscene/HEAD/README.md"}, {"method": "license_header", "retrieved_at": "2026-10-16T06:42:06Z", "role": "primary", "sha256": "9d26ef3ec511840e10eeaaf1e1b211e196c838823baf6bf9033761f27ab349ce", "supports": ["licenses.code"], "url": "https://raw.githubusercontent.com/web-infra-dev/midscene/HEAD/LICENSE"}], "id": "github:web-infra-dev/midscene", "identifiers": {}, "kind": "framework", "last_verified_at": "2026-10-16T06:40:53Z", "licenses": {"code": {"basis": "repository LICENSE header; not a weights/data license", "declared": "MIT", "retrieved_at": "2026-10-16T06:42:06Z", "url": "https://raw.githubusercontent.com/web-infra-dev/midscene/HEAD/LICENSE"}, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/web-infra-dev/midscene"}], "name": "Midscene.js", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Visual automation toolkit for web, mobile, and desktop interfaces.", "topics": ["automation", "grounding"], "updated_at": null, "url": "https://github.com/web-infra-dev/midscene"}
{"aliases": [], "authors": ["Tsung-Hsiang Chang", "Tom Yeh", "Robert C. Miller"], "details": {"publication": {"authors": ["Tsung-Hsiang Chang", "Tom Yeh", "Robert C. Miller"], "date_basis": "Supplied month precision: 2010-04. Date Issued: April 2010", "date_parts": [2010, 4], "doi": "10.1145/1753326.1753555", "event_dates": null, "evidence_urls": ["https://dspace.mit.edu/entities/publication/6a6097ba-1d97-43cf-bc70-04b5af02efd5"], "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": "Distinct visual-testing contribution from the 2009 Sikuli paper. The institutional abstract and published-version citation supply the retained evidence. Exact publication day and operating-system coverage are not established in the accessible institutional abstract.", "pages": "1535-1544", "pdf_url": null, "publisher": null, "series": null, "title": "GUI Testing Using Computer Vision", "type": "conference-paper", "url": "https://doi.org/10.1145/1753326.1753555", "venue": "Proceedings of the 28th International Conference on Human Factors in Computing Systems (CHI '10)", "volume": null}}, "environments": ["unspecified"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:21Z", "role": "primary", "sha256": "dbace77c54d1b4ed5dcf825dcb0f4525c32e33ac885e70312e8bb4a731a94e80", "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.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://dspace.mit.edu/entities/publication/6a6097ba-1d97-43cf-bc70-04b5af02efd5"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:21Z", "role": "primary", "sha256": "dbace77c54d1b4ed5dcf825dcb0f4525c32e33ac885e70312e8bb4a731a94e80", "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.title", "details.publication.type", "details.publication.url", "details.publication.venue", "environments", "kind", "name", "scope", "summary", "topics"], "url": "https://dspace.mit.edu/entities/publication/6a6097ba-1d97-43cf-bc70-04b5af02efd5"}], "id": "url:6262c757080f8838e62c", "identifiers": {"doi": "10.1145/1753326.1753555"}, "kind": "paper", "last_verified_at": "2026-10-17T09:53:21Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://doi.org/10.1145/1753326.1753555"}], "name": "GUI Testing Using Computer Vision", "notes": "The annotation was reviewed against retained primary publication sources. Experiments have not been independently reproduced. This is a separate visual-testing contribution from the 2009 Sikuli paper, not another version of the same article. MIT PDF download returned HTTP 429; its complete institutional abstract and citation metadata remain the retained review source.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents visual GUI test scripts that use images to specify actions and expected screen feedback. Recording both input events and screenshots can generate tests from demonstrations, supporting unit, regression, and test-driven workflows.", "topics": ["evaluation", "grounding", "automation"], "updated_at": null, "url": "https://doi.org/10.1145/1753326.1753555"}
{"aliases": [], "authors": ["Sarah E. Chasins", "Maria Mueller", "Rastislav Bodik"], "details": {"publication": {"authors": ["Sarah E. Chasins", "Maria Mueller", "Rastislav Bodik"], "date_basis": "Supplied year precision: 2018. Rousillon entry: UIST 2018", "date_parts": [2018], "doi": "10.1145/3242587.3242661", "event_dates": null, "evidence_urls": ["https://schasins.com/papers/", "https://schasins.com/assets/papers/rousillon.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": "This is browser interaction learned from demonstrations, rather than a generic server-side crawling library. Final proceedings page range and volume are not established. Manuscript pages 1-13 are not substituted for publisher pagination. Exact publication month/day is not inferred from conference dates.", "pages": null, "pdf_url": "https://schasins.com/assets/papers/rousillon.pdf", "publisher": null, "series": null, "title": "Rousillon: Scraping Distributed Hierarchical Web Data", "type": "conference-paper", "url": "https://doi.org/10.1145/3242587.3242661", "venue": "Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology", "volume": null}}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:57:38Z", "role": "primary", "sha256": "6b7e584bb3862e0de51ca164d0f311c2a853e97bd63d56658ce62f0b49d86557", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.notes", "details.publication.type", "details.publication.venue"], "url": "https://schasins.com/papers/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:55:12Z", "role": "primary", "sha256": "764dd1f5fe1db398188f403b4b1f6e3658e3238e4d8aac9ceed360dcad87e818", "supports": ["details.publication.authors", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pdf_url", "details.publication.title", "details.publication.url"], "url": "https://schasins.com/assets/papers/rousillon.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:55:12Z", "role": "primary", "sha256": "764dd1f5fe1db398188f403b4b1f6e3658e3238e4d8aac9ceed360dcad87e818", "supports": ["details.publication.authors", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pdf_url", "details.publication.title", "details.publication.url", "environments", "name", "scope", "summary", "topics"], "url": "https://schasins.com/assets/papers/rousillon.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:57:38Z", "role": "primary", "sha256": "6b7e584bb3862e0de51ca164d0f311c2a853e97bd63d56658ce62f0b49d86557", "supports": ["details.publication.date_basis", "details.publication.date_parts", "details.publication.notes", "details.publication.type", "details.publication.venue", "kind"], "url": "https://schasins.com/papers/"}], "id": "url:97c0b1896525632434e2", "identifiers": {"doi": "10.1145/3242587.3242661"}, "kind": "paper", "last_verified_at": "2026-10-17T09:55:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://doi.org/10.1145/3242587.3242661"}, {"rel": "publication_pdf", "url": "https://schasins.com/assets/papers/rousillon.pdf"}], "name": "Rousillon: Scraping Distributed Hierarchical Web Data", "notes": "The annotation was reviewed against retained primary publication sources. Experiments have not been independently reproduced. This is browser interaction learned from demonstrations, rather than a generic server-side crawling library.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Rousillon, which generalizes a demonstration of collecting one hierarchical data row into a browser-automation program that traverses related pages. The paper develops relation-selection and generalization methods and evaluates users building such scripts.", "topics": ["web-navigation", "recording", "automation"], "updated_at": null, "url": "https://doi.org/10.1145/3242587.3242661"}
{"aliases": [], "authors": ["Tom Yeh", "Tsung-Hsiang Chang", "Robert C. Miller"], "details": {"publication": {"authors": ["Tom Yeh", "Tsung-Hsiang Chang", "Robert C. Miller"], "date_basis": "Supplied month precision: 2009-10. Date Issued: October 2009", "date_parts": [2009, 10], "doi": "10.1145/1622176.1622213", "event_dates": null, "evidence_urls": ["https://dspace.mit.edu/entities/publication/604a3f79-451d-4186-a94e-d12690ffe40a"], "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": "Institutional abstract and published-version citation supply the retained evidence; the institution identifies an author final manuscript record. Exact publication day is not supplied. Operating-system-specific experiments are not asserted.", "pages": "183-192", "pdf_url": null, "publisher": null, "series": null, "title": "Sikuli: Using GUI screenshots for search and automation", "type": "conference-paper", "url": "https://doi.org/10.1145/1622176.1622213", "venue": "Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology (UIST '09)", "volume": null}}, "environments": ["unspecified"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:21Z", "role": "primary", "sha256": "dbaaf21982522b34857be014b39d6c43fedcda20f808efe40d04958c77243a5a", "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.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://dspace.mit.edu/entities/publication/604a3f79-451d-4186-a94e-d12690ffe40a"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:21Z", "role": "primary", "sha256": "dbaaf21982522b34857be014b39d6c43fedcda20f808efe40d04958c77243a5a", "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.title", "details.publication.type", "details.publication.url", "details.publication.venue", "environments", "kind", "name", "scope", "summary", "topics"], "url": "https://dspace.mit.edu/entities/publication/604a3f79-451d-4186-a94e-d12690ffe40a"}], "id": "url:a4cdb2ee0d07d3980651", "identifiers": {"doi": "10.1145/1622176.1622213"}, "kind": "paper", "last_verified_at": "2026-10-17T09:53:21Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://doi.org/10.1145/1622176.1622213"}], "name": "Sikuli: Using GUI screenshots for search and automation", "notes": "The annotation was reviewed against retained primary publication sources. Experiments have not been independently reproduced. MIT identifies the retained content as an author final manuscript record. Its PDF download returned HTTP 429; no retry was made. The complete institutional abstract and bibliographic record were read.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces screenshot-based GUI search and visual scripting, using image patterns to locate interface targets and direct mouse and keyboard events. It evaluates screenshot queries and demonstrates automation and interactive-help tasks.", "topics": ["grounding", "automation", "screen-understanding"], "updated_at": null, "url": "https://doi.org/10.1145/1622176.1622213"}
{"aliases": [], "authors": ["Allen Cypher"], "details": {"publication": {"authors": ["Allen Cypher"], "date_basis": "Supplied year precision: 1991. Opening CHI 1991 citation and copyright", "date_parts": [1991], "doi": null, "event_dates": null, "evidence_urls": ["https://acypher.com/Eager/", "https://acypher.com/Publications/CHI91/EagerCHI.html"], "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 1991 conference paper is kept distinct from the 1991 video and 1993/1995 reprints listed on the author project page. Macintosh/HyperCard is tagged desktop; it is not represented as support for contemporary macOS. DOI not verified in a retained first-party source. Exact publication month/day is not inferred from conference dates.", "pages": "33-39", "pdf_url": null, "publisher": null, "series": null, "title": "Eager: Programming Repetitive Tasks by Example", "type": "conference-paper", "url": "https://acypher.com/Publications/CHI91/EagerCHI.html", "venue": "Proceedings of CHI '91", "volume": null}}, "environments": ["desktop"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:27Z", "role": "primary", "sha256": "64cffd3fca934465e1ea28bdf62e087bc9abdf50b9b72d04c2e57df0bcf41adb", "supports": ["details.publication.identity_basis", "details.publication.notes", "details.publication.title"], "url": "https://acypher.com/Eager/"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:55:21Z", "role": "primary", "sha256": "876d4c8dfac48443336a5ee97b463642db013631a2b97cacd090e61afd95ad59", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://acypher.com/Publications/CHI91/EagerCHI.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:55:21Z", "role": "primary", "sha256": "876d4c8dfac48443336a5ee97b463642db013631a2b97cacd090e61afd95ad59", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.type", "details.publication.url", "details.publication.venue", "environments", "kind", "scope", "summary", "topics"], "url": "https://acypher.com/Publications/CHI91/EagerCHI.html"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:27Z", "role": "primary", "sha256": "64cffd3fca934465e1ea28bdf62e087bc9abdf50b9b72d04c2e57df0bcf41adb", "supports": ["details.publication.identity_basis", "details.publication.notes", "details.publication.title", "name"], "url": "https://acypher.com/Eager/"}], "id": "url:bf0c11018e49dff6aeec", "identifiers": {}, "kind": "paper", "last_verified_at": "2026-10-17T09:55:21Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://acypher.com/Publications/CHI91/EagerCHI.html"}], "name": "Eager: Programming Repetitive Tasks by Example", "notes": "The annotation was reviewed against retained primary publication sources. Experiments have not been independently reproduced. The 1991 conference paper is kept distinct from the 1991 video and 1993/1995 reprints listed on the author project page. Macintosh/HyperCard is tagged desktop; it is not represented as support for contemporary macOS.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Describes Eager, which detects repeated HyperCard interactions, generalizes them into loops, and previews predicted actions by highlighting interface objects. Users can then ask it to execute the inferred repetitive task.", "topics": ["automation", "human-in-the-loop", "interaction-history"], "updated_at": null, "url": "https://acypher.com/Publications/CHI91/EagerCHI.html"}
{"aliases": ["Nova Act"], "authors": [], "details": {}, "environments": ["web"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T17:18:21Z", "role": "primary", "sha256": "4e4e60092351a85d0b99186a745d6295b170958be59092a786eda369923bd691", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://aws.amazon.com/nova/act/"}], "id": "url:dec156cbf0cb1181f7b6", "identifiers": {}, "kind": "product", "last_verified_at": "2026-10-17T17:18:21Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://aws.amazon.com/nova/act/"}], "name": "Amazon Nova Act", "notes": "", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "AWS service for building and deploying agents that automate browser-based UI workflows from natural language and Python, powered by a custom Nova 2 Lite model.", "topics": ["automation", "web-navigation"], "updated_at": null, "url": "https://aws.amazon.com/nova/act/"}