[ { "URL": "https://arxiv.org/abs/1808.09132v2", "archive": "arXiv", "archive_location": "1808.09132", "author": [ { "literal": "Panupong Pasupat" }, { "literal": "Tian-Shun Jiang" }, { "literal": "Evan Zheran Liu" }, { "literal": "Kelvin Guu" }, { "literal": "Percy Liang" } ], "citation-key": "arxiv_1808_09132", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f368116f70e987cde111835a05b5b36e0d345dabb4e8351610e2bbfb691b3440", "submitted_at": "2018-08-28T06:09:39Z", "updated_at": "2018-10-01T03:22:58Z", "version": 2, "versioned_url": "https://arxiv.org/abs/1808.09132v2" }, "canonical_source_url": "https://arxiv.org/abs/1808.09132", "catalog_id": "arxiv:1808.09132", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2018-08-28", "identifiers": { "arxiv": "1808.09132" }, "record_updated_at": "2018-10-01" }, "genre": "preprint", "id": "arxiv:1808.09132", "issued": { "date-parts": [ [ 2018, 8, 28 ] ] }, "note": "First published: 2018-08-28; Recorded arXiv version: v2; Recorded version updated: 2018-10-01T03:22:58Z.", "title": "Mapping Natural Language Commands to Web Elements", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2005.03776v2", "archive": "arXiv", "archive_location": "2005.03776", "author": [ { "literal": "Yang Li" }, { "literal": "Jiacong He" }, { "literal": "Xin Zhou" }, { "literal": "Yuan Zhang" }, { "literal": "Jason Baldridge" } ], "citation-key": "arxiv_2005_03776", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3af7b45455ffbd616e8cdf5612b19275ecb7bf07b1065af9f5b724ae19e96fb4", "submitted_at": "2020-05-07T21:41:40Z", "updated_at": "2020-06-05T02:11:56Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2005.03776v2" }, "canonical_source_url": "https://arxiv.org/abs/2005.03776", "catalog_id": "arxiv:2005.03776", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2020-05-07", "identifiers": { "arxiv": "2005.03776" }, "publication": { "authors": [ "Yang Li", "Jiacong He", "Xin Zhou", "Yuan Zhang", "Jason Baldridge" ], "date_basis": "Explicit publisher metadata: 2020/7; precision=month.", "date_parts": [ 2020, 7 ], "doi": "10.18653/v1/2020.acl-main.729", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2020.acl-main.729/" ], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "8198-8210", "pdf_url": "https://aclanthology.org/2020.acl-main.729.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Mapping Natural Language Instructions to Mobile UI Action Sequences", "type": "conference-paper", "url": "https://aclanthology.org/2020.acl-main.729/", "venue": "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", "volume": null }, "record_updated_at": "2020-06-05" }, "genre": "preprint", "id": "arxiv:2005.03776", "issued": { "date-parts": [ [ 2020, 5, 7 ] ] }, "note": "First published: 2020-05-07; Recorded arXiv version: v2; Recorded version updated: 2020-06-05T02:11:56Z.", "title": "Mapping Natural Language Instructions to Mobile UI Action Sequences", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2105.11941v2", "archive": "arXiv", "archive_location": "2105.11941", "author": [ { "literal": "Jingwen Fu" }, { "literal": "Xiaoyi Zhang" }, { "literal": "Yuwang Wang" }, { "literal": "Wenjun Zeng" }, { "literal": "Sam Yang" }, { "literal": "Grayson Hilliard" } ], "citation-key": "arxiv_2105_11941", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8788e419d1a901f8ad9dd6089a12fe129baee764b1c285bbeb4ea60d7046afa2", "submitted_at": "2021-05-25T13:45:54Z", "updated_at": "2022-04-14T11:00:58Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2105.11941v2" }, "canonical_source_url": "https://arxiv.org/abs/2105.11941", "catalog_id": "arxiv:2105.11941", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2021-05-25", "identifiers": { "arxiv": "2105.11941" }, "record_updated_at": "2022-04-14" }, "genre": "preprint", "id": "arxiv:2105.11941", "issued": { "date-parts": [ [ 2021, 5, 25 ] ] }, "note": "First published: 2021-05-25; Recorded arXiv version: v2; Recorded version updated: 2022-04-14T11:00:58Z.", "title": "Understanding Mobile GUI: from Pixel-Words to Screen-Sentences", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2201.04100v2", "archive": "arXiv", "archive_location": "2201.04100", "author": [ { "literal": "Gang Li" }, { "literal": "Gilles Baechler" }, { "literal": "Manuel Tragut" }, { "literal": "Yang Li" } ], "citation-key": "arxiv_2201_04100", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d971ee06cafd46fe27a01d40bc16e3604e1d153c38ee92be970328d9935b0708", "submitted_at": "2022-01-11T17:52:40Z", "updated_at": "2022-01-13T17:53:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2201.04100v2" }, "canonical_source_url": "https://arxiv.org/abs/2201.04100", "catalog_id": "arxiv:2201.04100", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2022-01-11", "identifiers": { "arxiv": "2201.04100" }, "record_updated_at": "2022-01-13" }, "genre": "preprint", "id": "arxiv:2201.04100", "issued": { "date-parts": [ [ 2022, 1, 11 ] ] }, "note": "First published: 2022-01-11; Recorded arXiv version: v2; Recorded version updated: 2022-01-13T17:53:31Z.", "title": "Learning to Denoise Raw Mobile UI Layouts for Improving Datasets at Scale", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2210.02663v1", "archive": "arXiv", "archive_location": "2210.02663", "author": [ { "literal": "Srinivas Sunkara" }, { "literal": "Maria Wang" }, { "literal": "Lijuan Liu" }, { "literal": "Gilles Baechler" }, { "literal": "Yu-Chung Hsiao" }, { "literal": "Jindong" }, { "literal": "Chen" }, { "literal": "Abhanshu Sharma" }, { "literal": "James Stout" } ], "citation-key": "arxiv_2210_02663", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "24d037f1abeb7708852ac5517ce02cc46622e359d9feab407f188c0657cc72f4", "submitted_at": "2022-10-06T03:48:54Z", "updated_at": "2022-10-06T03:48:54Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2210.02663v1" }, "canonical_source_url": "https://arxiv.org/abs/2210.02663", "catalog_id": "arxiv:2210.02663", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2022-10-06", "identifiers": { "arxiv": "2210.02663" }, "record_updated_at": "2022-10-06" }, "genre": "preprint", "id": "arxiv:2210.02663", "issued": { "date-parts": [ [ 2022, 10, 6 ] ] }, "note": "First published: 2022-10-06; Recorded arXiv version: v1; Recorded version updated: 2022-10-06T03:48:54Z.", "title": "Towards Better Semantic Understanding of Mobile Interfaces", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2210.03347v2", "archive": "arXiv", "archive_location": "2210.03347", "author": [ { "literal": "Kenton Lee" }, { "literal": "Mandar Joshi" }, { "literal": "Iulia Turc" }, { "literal": "Hexiang Hu" }, { "literal": "Fangyu Liu" }, { "literal": "Julian Eisenschlos" }, { "literal": "Urvashi Khandelwal" }, { "literal": "Peter Shaw" }, { "literal": "Ming-Wei Chang" }, { "literal": "Kristina Toutanova" } ], "citation-key": "arxiv_2210_03347", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7ebb243c4690aba5f1a92b0d1e050399560998a7f304ea483dae2f451cf51ec0", "submitted_at": "2022-10-07T06:42:06Z", "updated_at": "2023-06-15T21:34:23Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2210.03347v2" }, "canonical_source_url": "https://arxiv.org/abs/2210.03347", "catalog_id": "arxiv:2210.03347", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2022-10-07", "identifiers": { "arxiv": "2210.03347" }, "record_updated_at": "2023-06-15" }, "genre": "preprint", "id": "arxiv:2210.03347", "issued": { "date-parts": [ [ 2022, 10, 7 ] ] }, "note": "First published: 2022-10-07; Recorded arXiv version: v2; Recorded version updated: 2023-06-15T21:34:23Z.", "title": "Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2210.03945v2", "archive": "arXiv", "archive_location": "2210.03945", "author": [ { "literal": "Izzeddin Gur" }, { "literal": "Ofir Nachum" }, { "literal": "Yingjie Miao" }, { "literal": "Mustafa Safdari" }, { "literal": "Austin Huang" }, { "literal": "Aakanksha Chowdhery" }, { "literal": "Sharan Narang" }, { "literal": "Noah Fiedel" }, { "literal": "Aleksandra Faust" } ], "citation-key": "arxiv_2210_03945", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9b9089164b5c784735d8915596fe902840e01c8215f507caed0e10d4361d13ec", "submitted_at": "2022-10-08T07:27:17Z", "updated_at": "2023-05-19T17:42:56Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2210.03945v2" }, "canonical_source_url": "https://arxiv.org/abs/2210.03945", "catalog_id": "arxiv:2210.03945", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2022-10-08", "identifiers": { "arxiv": "2210.03945" }, "record_updated_at": "2023-05-19" }, "genre": "preprint", "id": "arxiv:2210.03945", "issued": { "date-parts": [ [ 2022, 10, 8 ] ] }, "note": "First published: 2022-10-08; Recorded arXiv version: v2; Recorded version updated: 2023-05-19T17:42:56Z.", "title": "Understanding HTML with Large Language Models", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2301.10165v1", "archive": "arXiv", "archive_location": "2301.10165", "author": [ { "literal": "Pratyay Banerjee" }, { "literal": "Shweti Mahajan" }, { "literal": "Kushal Arora" }, { "literal": "Chitta Baral" }, { "literal": "Oriana Riva" } ], "citation-key": "arxiv_2301_10165", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bb647a96c7f8263786e85a5061c8c5284cb92ed0b2ebc4c405e1243b2ca3fa2b", "submitted_at": "2023-01-23T09:05:49Z", "updated_at": "2023-01-23T09:05:49Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2301.10165v1" }, "canonical_source_url": "https://arxiv.org/abs/2301.10165", "catalog_id": "arxiv:2301.10165", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2023-01-23", "identifiers": { "arxiv": "2301.10165" }, "record_updated_at": "2023-01-23" }, "genre": "preprint", "id": "arxiv:2301.10165", "issued": { "date-parts": [ [ 2023, 1, 23 ] ] }, "note": "First published: 2023-01-23; Recorded arXiv version: v1; Recorded version updated: 2023-01-23T09:05:49Z.", "title": "Lexi: Self-Supervised Learning of the UI Language", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2301.13280v1", "archive": "arXiv", "archive_location": "2301.13280", "author": [ { "literal": "Jason Wu" }, { "literal": "Siyan Wang" }, { "literal": "Siman Shen" }, { "literal": "Yi-Hao Peng" }, { "literal": "Jeffrey Nichols" }, { "literal": "Jeffrey P. Bigham" } ], "citation-key": "arxiv_2301_13280", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0cc3b91aa85bc8c7d88a878c7b24926943eea0bcc92e25f517915242f2a82a39", "submitted_at": "2023-01-30T20:47:12Z", "updated_at": "2023-01-30T20:47:12Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2301.13280v1" }, "canonical_source_url": "https://arxiv.org/abs/2301.13280", "catalog_id": "arxiv:2301.13280", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2023-01-30", "identifiers": { "arxiv": "2301.13280" }, "record_updated_at": "2023-01-30" }, "genre": "preprint", "id": "arxiv:2301.13280", "issued": { "date-parts": [ [ 2023, 1, 30 ] ] }, "note": "First published: 2023-01-30; Recorded arXiv version: v1; Recorded version updated: 2023-01-30T20:47:12Z.", "title": "WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2306.06070v3", "archive": "arXiv", "archive_location": "2306.06070", "author": [ { "literal": "Xiang Deng" }, { "literal": "Yu Gu" }, { "literal": "Boyuan Zheng" }, { "literal": "Shijie Chen" }, { "literal": "Samuel Stevens" }, { "literal": "Boshi Wang" }, { "literal": "Huan Sun" }, { "literal": "Yu Su" } ], "citation-key": "arxiv_2306_06070", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "de055dfa452130f3576839c99c007053c62a0c96c9bfbcdd79ecad1a9f74f830", "submitted_at": "2023-06-09T17:44:31Z", "updated_at": "2023-12-09T05:57:46Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2306.06070v3" }, "canonical_source_url": "https://arxiv.org/abs/2306.06070", "catalog_id": "arxiv:2306.06070", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2023-06-09", "identifiers": { "arxiv": "2306.06070" }, "record_updated_at": "2023-12-09" }, "genre": "preprint", "id": "arxiv:2306.06070", "issued": { "date-parts": [ [ 2023, 6, 9 ] ] }, "note": "First published: 2023-06-09; Recorded arXiv version: v3; Recorded version updated: 2023-12-09T05:57:46Z.", "title": "Mind2Web: Towards a Generalist Agent for the Web", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2307.10088v2", "archive": "arXiv", "archive_location": "2307.10088", "author": [ { "literal": "Christopher Rawles" }, { "literal": "Alice Li" }, { "literal": "Daniel Rodriguez" }, { "literal": "Oriana Riva" }, { "literal": "Timothy Lillicrap" } ], "citation-key": "arxiv_2307_10088", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "def4616f7cb13fe839e500c4b3171eafbe37b155b5d14301137806d6a5cde939", "submitted_at": "2023-07-19T15:57:24Z", "updated_at": "2023-10-27T14:24:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2307.10088v2" }, "canonical_source_url": "https://arxiv.org/abs/2307.10088", "catalog_id": "arxiv:2307.10088", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2023-07-19", "identifiers": { "arxiv": "2307.10088" }, "publication": { "authors": [ "Christopher Rawles", "Alice Li", "Daniel Rodriguez", "Oriana Riva", "Timothy Lillicrap" ], "date_basis": "Explicit publisher citation_publication_date: 2023-12-15. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2023, 12, 15 ], "doi": "10.52202/075280-2609", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "59708-59728", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2023/file/bbbb6308b402fe909c39dd29950c32e0-Paper-Datasets_and_Benchmarks.pdf", "publisher": null, "series": null, "title": "AndroidInTheWild: A Large-Scale Dataset For Android Device Control", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html", "venue": "Advances in Neural Information Processing Systems", "volume": "36" }, "record_updated_at": "2023-10-27" }, "genre": "preprint", "id": "arxiv:2307.10088", "issued": { "date-parts": [ [ 2023, 7, 19 ] ] }, "note": "First published: 2023-07-19; Recorded arXiv version: v2; Recorded version updated: 2023-10-27T14:24:31Z.", "title": "Android in the Wild: A Large-Scale Dataset for Android Device Control", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2310.04869v1", "archive": "arXiv", "archive_location": "2310.04869", "author": [ { "literal": "Yue Jiang" }, { "literal": "Eldon Schoop" }, { "literal": "Amanda Swearngin" }, { "literal": "Jeffrey Nichols" } ], "citation-key": "arxiv_2310_04869", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a49e879891017071fce4df0ff4b07bd9e8b5a6e14385af565549aadbde1bc1cf", "submitted_at": "2023-10-07T16:32:34Z", "updated_at": "2023-10-07T16:32:34Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2310.04869v1" }, "canonical_source_url": "https://arxiv.org/abs/2310.04869", "catalog_id": "arxiv:2310.04869", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2023-10-07", "identifiers": { "arxiv": "2310.04869" }, "record_updated_at": "2023-10-07" }, "genre": "preprint", "id": "arxiv:2310.04869", "issued": { "date-parts": [ [ 2023, 10, 7 ] ] }, "note": "First published: 2023-10-07; Recorded arXiv version: v1; Recorded version updated: 2023-10-07T16:32:34Z.", "title": "ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine Conversations", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2312.15820v1", "archive": "arXiv", "archive_location": "2312.15820", "author": [ { "literal": "Qi Chen" }, { "literal": "Dileepa Pitawela" }, { "literal": "Chongyang Zhao" }, { "literal": "Gengze Zhou" }, { "literal": "Hsiang-Ting Chen" }, { "literal": "Qi Wu" } ], "citation-key": "arxiv_2312_15820", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "47dedddced8f06bf436ab5a101d1ec4ecf4380c710e457dc7a35fc86d2e1f230", "submitted_at": "2023-12-25T22:13:26Z", "updated_at": "2023-12-25T22:13:26Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2312.15820v1" }, "canonical_source_url": "https://arxiv.org/abs/2312.15820", "catalog_id": "arxiv:2312.15820", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2023-12-25", "identifiers": { "arxiv": "2312.15820" }, "record_updated_at": "2023-12-25" }, "genre": "preprint", "id": "arxiv:2312.15820", "issued": { "date-parts": [ [ 2023, 12, 25 ] ] }, "note": "First published: 2023-12-25; Recorded arXiv version: v1; Recorded version updated: 2023-12-25T22:13:26Z.", "title": "WebVLN: Vision-and-Language Navigation on Websites", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2401.10935v2", "archive": "arXiv", "archive_location": "2401.10935", "author": [ { "literal": "Kanzhi Cheng" }, { "literal": "Qiushi Sun" }, { "literal": "Yougang Chu" }, { "literal": "Fangzhi Xu" }, { "literal": "Yantao Li" }, { "literal": "Jianbing Zhang" }, { "literal": "Zhiyong Wu" } ], "citation-key": "arxiv_2401_10935", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c92ec9323eec9362aa07984f9fb1cbfbe98ecae426a9f8adc9d436328a87aed3", "submitted_at": "2024-01-17T08:10:35Z", "updated_at": "2024-02-23T04:36:51Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2401.10935v2" }, "canonical_source_url": "https://arxiv.org/abs/2401.10935", "catalog_id": "arxiv:2401.10935", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-01-17", "identifiers": { "arxiv": "2401.10935" }, "publication": { "authors": [ "Kanzhi Cheng", "Qiushi Sun", "Yougang Chu", "Fangzhi Xu", "Yantao Li", "Jianbing Zhang", "Zhiyong Wu" ], "date_basis": "Explicit publisher metadata: 2024/8; precision=month.", "date_parts": [ 2024, 8 ], "doi": "10.18653/v1/2024.acl-long.505", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.acl-long.505/", "https://aclanthology.org/2024.acl-long.505.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 ACL landing metadata spells the fifth author Li YanTao. The formal PDF title page spells Yantao Li; the publication author field uses the PDF. The retained arXiv author list is untouched. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "9313-9332", "pdf_url": "https://aclanthology.org/2024.acl-long.505.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.acl-long.505/", "venue": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2024-02-23" }, "genre": "preprint", "id": "arxiv:2401.10935", "issued": { "date-parts": [ [ 2024, 1, 17 ] ] }, "note": "First published: 2024-01-17; Recorded arXiv version: v2; Recorded version updated: 2024-02-23T04:36:51Z.", "title": "SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2402.04615v3", "archive": "arXiv", "archive_location": "2402.04615", "author": [ { "literal": "Gilles Baechler" }, { "literal": "Srinivas Sunkara" }, { "literal": "Maria Wang" }, { "literal": "Fedir Zubach" }, { "literal": "Hassan Mansoor" }, { "literal": "Vincent Etter" }, { "literal": "Victor Cărbune" }, { "literal": "Jason Lin" }, { "literal": "Jindong Chen" }, { "literal": "Abhanshu Sharma" } ], "citation-key": "arxiv_2402_04615", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b293ab33fe0f3607eccc2b99cbf06fb459792444433a4179bb65e081f33e426c", "submitted_at": "2024-02-07T06:42:33Z", "updated_at": "2024-07-04T07:08:15Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2402.04615v3" }, "canonical_source_url": "https://arxiv.org/abs/2402.04615", "catalog_id": "arxiv:2402.04615", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-02-07", "identifiers": { "arxiv": "2402.04615" }, "record_updated_at": "2024-07-04" }, "genre": "preprint", "id": "arxiv:2402.04615", "issued": { "date-parts": [ [ 2024, 2, 7 ] ] }, "note": "First published: 2024-02-07; Recorded arXiv version: v3; Recorded version updated: 2024-07-04T07:08:15Z.", "title": "ScreenAI: A Vision-Language Model for UI and Infographics Understanding", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2402.05930v2", "archive": "arXiv", "archive_location": "2402.05930", "author": [ { "literal": "Xing Han Lù" }, { "literal": "Zdeněk Kasner" }, { "literal": "Siva Reddy" } ], "citation-key": "arxiv_2402_05930", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6a7c1a1f260f9287e8999525e1adc5534a70f7b96271d469973fceee1ac23609", "submitted_at": "2024-02-08T18:58:02Z", "updated_at": "2024-09-10T22:22:43Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2402.05930v2" }, "canonical_source_url": "https://arxiv.org/abs/2402.05930", "catalog_id": "arxiv:2402.05930", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-02-08", "identifiers": { "arxiv": "2402.05930" }, "publication": { "authors": [ "Xing Han Lù", "Zdeněk Kasner", "Siva Reddy" ], "date_basis": "Explicit publisher metadata: 2024/07/08; precision=day.", "date_parts": [ 2024, 7, 8 ], "doi": null, "event_dates": "21--27 Jul 2024", "evidence_urls": [ "https://proceedings.mlr.press/v235/lu24e.html", "https://raw.githubusercontent.com/mlresearch/v235/main/assets/lu24e/lu24e.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 PMLR landing renders Xing Han Lu; the paper title page has Xing Han Lù. Publication authors use the PDF. The publisher issue date comes from citation_publication_date; the conference date range is retained separately and does not replace it. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "33007-33056", "pdf_url": "https://raw.githubusercontent.com/mlresearch/v235/main/assets/lu24e/lu24e.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "WebLINX: Real-World Website Navigation with Multi-Turn Dialogue", "type": "conference-paper", "url": "https://proceedings.mlr.press/v235/lu24e.html", "venue": "Proceedings of the 41st International Conference on Machine Learning", "volume": "235" }, "record_updated_at": "2024-09-10" }, "genre": "preprint", "id": "arxiv:2402.05930", "issued": { "date-parts": [ [ 2024, 2, 8 ] ] }, "note": "First published: 2024-02-08; Recorded arXiv version: v2; Recorded version updated: 2024-09-10T22:22:43Z.", "title": "WebLINX: Real-World Website Navigation with Multi-Turn Dialogue", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2403.10170v2", "archive": "arXiv", "archive_location": "2403.10170", "author": [ { "literal": "Andrés Muñoz" }, { "literal": "Daniel Borrajo" } ], "citation-key": "arxiv_2403_10170", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aacb4d2cac31e478aa56ee25b6b39e5ba8fe164f89102e665f8fb25cf3822e7b", "submitted_at": "2024-03-15T10:26:52Z", "updated_at": "2024-08-27T18:36:12Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2403.10170v2" }, "canonical_source_url": "https://arxiv.org/abs/2403.10170", "catalog_id": "arxiv:2403.10170", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-03-15", "identifiers": { "arxiv": "2403.10170" }, "record_updated_at": "2024-08-27" }, "genre": "preprint", "id": "arxiv:2403.10170", "issued": { "date-parts": [ [ 2024, 3, 15 ] ] }, "note": "First published: 2024-03-15; Recorded arXiv version: v2; Recorded version updated: 2024-08-27T18:36:12Z.", "title": "Computer User Interface Understanding. A New Dataset and a Learning Framework", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2404.03648v2", "archive": "arXiv", "archive_location": "2404.03648", "author": [ { "literal": "Hanyu Lai" }, { "literal": "Xiao Liu" }, { "literal": "Iat Long Iong" }, { "literal": "Shuntian Yao" }, { "literal": "Yuxuan Chen" }, { "literal": "Pengbo Shen" }, { "literal": "Hao Yu" }, { "literal": "Hanchen Zhang" }, { "literal": "Xiaohan Zhang" }, { "literal": "Yuxiao Dong" }, { "literal": "Jie Tang" } ], "citation-key": "arxiv_2404_03648", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "340206da25df688ff73da617fd66a872586d1e36981c431d18331cee9b9669e0", "submitted_at": "2024-04-04T17:58:40Z", "updated_at": "2024-10-12T05:05:38Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2404.03648v2" }, "canonical_source_url": "https://arxiv.org/abs/2404.03648", "catalog_id": "arxiv:2404.03648", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-04-04", "identifiers": { "arxiv": "2404.03648" }, "record_updated_at": "2024-10-12" }, "genre": "preprint", "id": "arxiv:2404.03648", "issued": { "date-parts": [ [ 2024, 4, 4 ] ] }, "note": "First published: 2024-04-04; Recorded arXiv version: v2; Recorded version updated: 2024-10-12T05:05:38Z.", "title": "AutoWebGLM: A Large Language Model-based Web Navigating Agent", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2404.05902v1", "archive": "arXiv", "archive_location": "2404.05902", "author": [ { "literal": "Michael Lutz" }, { "literal": "Arth Bohra" }, { "literal": "Manvel Saroyan" }, { "literal": "Artem Harutyunyan" }, { "literal": "Giovanni Campagna" } ], "citation-key": "arxiv_2404_05902", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4c18dbfedcccf6434b3a50a9aa62552372df8b772ccda6a1aa699a8f052476bc", "submitted_at": "2024-04-08T23:10:47Z", "updated_at": "2024-04-08T23:10:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2404.05902v1" }, "canonical_source_url": "https://arxiv.org/abs/2404.05902", "catalog_id": "arxiv:2404.05902", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-04-08", "identifiers": { "arxiv": "2404.05902" }, "record_updated_at": "2024-04-08" }, "genre": "preprint", "id": "arxiv:2404.05902", "issued": { "date-parts": [ [ 2024, 4, 8 ] ] }, "note": "First published: 2024-04-08; Recorded arXiv version: v1; Recorded version updated: 2024-04-08T23:10:47Z.", "title": "WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2404.16048v2", "archive": "arXiv", "archive_location": "2404.16048", "author": [ { "literal": "Rajat Chawla" }, { "literal": "Adarsh Jha" }, { "literal": "Muskaan Kumar" }, { "literal": "Mukunda NS" }, { "literal": "Ishaan Bhola" } ], "citation-key": "arxiv_2404_16048", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e29d14a41d59942c88938b8e83217484a1cb619847c5dff0ec1f516095ee5654", "submitted_at": "2024-04-09T11:59:41Z", "updated_at": "2024-10-27T05:54:50Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2404.16048v2" }, "canonical_source_url": "https://arxiv.org/abs/2404.16048", "catalog_id": "arxiv:2404.16048", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-04-09", "identifiers": { "arxiv": "2404.16048" }, "record_updated_at": "2024-10-27" }, "genre": "preprint", "id": "arxiv:2404.16048", "issued": { "date-parts": [ [ 2024, 4, 9 ] ] }, "note": "First published: 2024-04-09; Recorded arXiv version: v2; Recorded version updated: 2024-10-27T05:54:50Z.", "title": "GUIDE: Graphical User Interface Data for Execution", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2405.07090v1", "archive": "arXiv", "archive_location": "2405.07090", "author": [ { "literal": "Sidong Feng" }, { "literal": "Suyu Ma" }, { "literal": "Han Wang" }, { "literal": "David Kong" }, { "literal": "Chunyang Chen" } ], "citation-key": "arxiv_2405_07090", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d200a997596ea919d5210b5ca5760241f9dfa3ad581e090a541871cd6e117522", "submitted_at": "2024-05-11T20:32:16Z", "updated_at": "2024-05-11T20:32:16Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2405.07090v1" }, "canonical_source_url": "https://arxiv.org/abs/2405.07090", "catalog_id": "arxiv:2405.07090", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-05-11", "identifiers": { "arxiv": "2405.07090" }, "record_updated_at": "2024-05-11" }, "genre": "preprint", "id": "arxiv:2405.07090", "issued": { "date-parts": [ [ 2024, 5, 11 ] ] }, "note": "First published: 2024-05-11; Recorded arXiv version: v1; Recorded version updated: 2024-05-11T20:32:16Z.", "title": "MUD: Towards a Large-Scale and Noise-Filtered UI Dataset for Modern Style UI Modeling", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2405.20309v2", "archive": "arXiv", "archive_location": "2405.20309", "author": [ { "literal": "Ajay Patel" }, { "literal": "Markus Hofmarcher" }, { "literal": "Claudiu Leoveanu-Condrei" }, { "literal": "Marius-Constantin Dinu" }, { "literal": "Chris Callison-Burch" }, { "literal": "Sepp Hochreiter" } ], "citation-key": "arxiv_2405_20309", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "77b292052a2ab4e8db61606ffe1da8bd5e63b3ce8c84b2e0e4b7a2fdc2f926ca", "submitted_at": "2024-05-30T17:52:36Z", "updated_at": "2024-10-01T21:28:29Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2405.20309v2" }, "canonical_source_url": "https://arxiv.org/abs/2405.20309", "catalog_id": "arxiv:2405.20309", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-05-30", "identifiers": { "arxiv": "2405.20309" }, "record_updated_at": "2024-10-01" }, "genre": "preprint", "id": "arxiv:2405.20309", "issued": { "date-parts": [ [ 2024, 5, 30 ] ] }, "note": "First published: 2024-05-30; Recorded arXiv version: v2; Recorded version updated: 2024-10-01T21:28:29Z.", "title": "Large Language Models Can Self-Improve At Web Agent Tasks", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2406.03679v6", "archive": "arXiv", "archive_location": "2406.03679", "author": [ { "literal": "Wei Li" }, { "literal": "William Bishop" }, { "literal": "Alice Li" }, { "literal": "Chris Rawles" }, { "literal": "Folawiyo Campbell-Ajala" }, { "literal": "Divya Tyamagundlu" }, { "literal": "Oriana Riva" } ], "citation-key": "arxiv_2406_03679", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6eb3209d8e2a431987fe19f01cd0818f9fb490e684d7369e7d3002dc388ff271", "submitted_at": "2024-06-06T01:49:29Z", "updated_at": "2024-11-13T16:42:22Z", "version": 6, "versioned_url": "https://arxiv.org/abs/2406.03679v6" }, "canonical_source_url": "https://arxiv.org/abs/2406.03679", "catalog_id": "arxiv:2406.03679", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-06-06", "identifiers": { "arxiv": "2406.03679" }, "publication": { "authors": [ "Wei Li", "William Bishop", "Alice Li", "Chris Rawles", "Folawiyo Campbell-Ajala", "Divya Tyamagundlu", "Oriana Riva" ], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 12, 16 ], "doi": "10.52202/079017-2925", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "92130-92154", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/a79f3ef3b445fd4659f44648f7ea8ffd-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "On the Effects of Data Scale on UI Control Agents", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "record_updated_at": "2024-11-13" }, "genre": "preprint", "id": "arxiv:2406.03679", "issued": { "date-parts": [ [ 2024, 6, 6 ] ] }, "note": "First published: 2024-06-06; Recorded arXiv version: v6; Recorded version updated: 2024-11-13T16:42:22Z.", "title": "On the Effects of Data Scale on UI Control Agents", "type": "article", "version": "6" }, { "URL": "https://arxiv.org/abs/2406.07822v2", "archive": "arXiv", "archive_location": "2406.07822", "author": [ { "literal": "Andrea Burns" }, { "literal": "Kate Saenko" }, { "literal": "Bryan A. Plummer" } ], "citation-key": "arxiv_2406_07822", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "47d0ca0467a104f9b8be037ec73131f12b66a22b0a89fe975bec7680073c8f39", "submitted_at": "2024-06-12T02:43:19Z", "updated_at": "2024-08-08T02:36:04Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2406.07822v2" }, "canonical_source_url": "https://arxiv.org/abs/2406.07822", "catalog_id": "arxiv:2406.07822", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-06-12", "identifiers": { "arxiv": "2406.07822" }, "record_updated_at": "2024-08-08" }, "genre": "preprint", "id": "arxiv:2406.07822", "issued": { "date-parts": [ [ 2024, 6, 12 ] ] }, "note": "First published: 2024-06-12; Recorded arXiv version: v2; Recorded version updated: 2024-08-08T02:36:04Z.", "title": "Tell Me What's Next: Textual Foresight for Generic UI Representations", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2406.08451v2", "archive": "arXiv", "archive_location": "2406.08451", "author": [ { "literal": "Quanfeng Lu" }, { "literal": "Wenqi Shao" }, { "literal": "Zitao Liu" }, { "literal": "Lingxiao Du" }, { "literal": "Fanqing Meng" }, { "literal": "Boxuan Li" }, { "literal": "Botong Chen" }, { "literal": "Siyuan Huang" }, { "literal": "Kaipeng Zhang" }, { "literal": "Ping Luo" } ], "citation-key": "arxiv_2406_08451", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8b45039151353cc0fede71e2e9ba109ec53d0c1f495037a82d8fb742c9e97bbb", "submitted_at": "2024-06-12T17:44:26Z", "updated_at": "2025-08-01T03:37:57Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2406.08451v2" }, "canonical_source_url": "https://arxiv.org/abs/2406.08451", "catalog_id": "arxiv:2406.08451", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-06-12", "identifiers": { "arxiv": "2406.08451" }, "record_updated_at": "2025-08-01" }, "genre": "preprint", "id": "arxiv:2406.08451", "issued": { "date-parts": [ [ 2024, 6, 12 ] ] }, "note": "First published: 2024-06-12; Recorded arXiv version: v2; Recorded version updated: 2025-08-01T03:37:57Z.", "title": "GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2408.06327v1", "archive": "arXiv", "archive_location": "2408.06327", "author": [ { "literal": "Xiao Liu" }, { "literal": "Tianjie Zhang" }, { "literal": "Yu Gu" }, { "literal": "Iat Long Iong" }, { "literal": "Yifan Xu" }, { "literal": "Xixuan Song" }, { "literal": "Shudan Zhang" }, { "literal": "Hanyu Lai" }, { "literal": "Xinyi Liu" }, { "literal": "Hanlin Zhao" }, { "literal": "Jiadai Sun" }, { "literal": "Xinyue Yang" }, { "literal": "Yu Yang" }, { "literal": "Zehan Qi" }, { "literal": "Shuntian Yao" }, { "literal": "Xueqiao Sun" }, { "literal": "Siyi Cheng" }, { "literal": "Qinkai Zheng" }, { "literal": "Hao Yu" }, { "literal": "Hanchen Zhang" }, { "literal": "Wenyi Hong" }, { "literal": "Ming Ding" }, { "literal": "Lihang Pan" }, { "literal": "Xiaotao Gu" }, { "literal": "Aohan Zeng" }, { "literal": "Zhengxiao Du" }, { "literal": "Chan Hee Song" }, { "literal": "Yu Su" }, { "literal": "Yuxiao Dong" }, { "literal": "Jie Tang" } ], "citation-key": "arxiv_2408_06327", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "603bfa4357617bfeb7a718065e77c71d77614f7240258684938dd4e6fd1a20df", "submitted_at": "2024-08-12T17:44:17Z", "updated_at": "2024-08-12T17:44:17Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2408.06327v1" }, "canonical_source_url": "https://arxiv.org/abs/2408.06327", "catalog_id": "arxiv:2408.06327", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2024-08-12", "identifiers": { "arxiv": "2408.06327" }, "record_updated_at": "2024-08-12" }, "genre": "preprint", "id": "arxiv:2408.06327", "issued": { "date-parts": [ [ 2024, 8, 12 ] ] }, "note": "First published: 2024-08-12; Recorded arXiv version: v1; Recorded version updated: 2024-08-12T17:44:17Z.", "title": "VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2409.14337v3", "archive": "arXiv", "archive_location": "2409.14337", "author": [ { "literal": "Longxi Gao" }, { "literal": "Li Zhang" }, { "literal": "Shihe Wang" }, { "literal": "Pengzhi Gao" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Shangguang Wang" }, { "literal": "Yuanchun Li" }, { "literal": "Mengwei Xu" } ], "citation-key": "arxiv_2409_14337", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4bb00ad1be49c9bd51881827556b3a168d34c69a45e31053406f780ad2a62af1", "submitted_at": "2024-09-22T06:45:38Z", "updated_at": "2025-11-25T02:43:11Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2409.14337v3" }, "canonical_source_url": "https://arxiv.org/abs/2409.14337", "catalog_id": "arxiv:2409.14337", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-09-22", "identifiers": { "arxiv": "2409.14337" }, "record_updated_at": "2025-11-25" }, "genre": "preprint", "id": "arxiv:2409.14337", "issued": { "date-parts": [ [ 2024, 9, 22 ] ] }, "note": "First published: 2024-09-22; Recorded arXiv version: v3; Recorded version updated: 2025-11-25T02:43:11Z.", "title": "MobileViews: A Million-scale and Diverse Mobile GUI Dataset", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2409.14818v2", "archive": "arXiv", "archive_location": "2409.14818", "author": [ { "literal": "Qinzhuo Wu" }, { "literal": "Weikai Xu" }, { "literal": "Wei Liu" }, { "literal": "Tao Tan" }, { "literal": "Jianfeng Liu" }, { "literal": "Ang Li" }, { "literal": "Jian Luan" }, { "literal": "Bin Wang" }, { "literal": "Shuo Shang" } ], "citation-key": "arxiv_2409_14818", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cc22337ef29946dffcf7149df1008fd6cf02350c68d21ec0386e6485f5a14ebf", "submitted_at": "2024-09-23T08:47:54Z", "updated_at": "2024-10-03T05:23:22Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.14818v2" }, "canonical_source_url": "https://arxiv.org/abs/2409.14818", "catalog_id": "arxiv:2409.14818", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-09-23", "identifiers": { "arxiv": "2409.14818" }, "publication": { "authors": [ "Qinzhuo Wu", "Weikai Xu", "Wei Liu", "Tao Tan", "Jianfeng Liu", "Ang Li", "Jian Luan", "Bin Wang", "Shuo Shang" ], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 11 ], "doi": "10.18653/v1/2024.findings-emnlp.599", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.findings-emnlp.599/", "https://aclanthology.org/2024.findings-emnlp.599.pdf" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the publisher PDF, page 1. The landing page and its BibTeX list the fifth author as Liujian Liujianfeng; the PDF names Jianfeng Liu.", "pages": "10231-10251", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.599.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.599/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null }, "record_updated_at": "2024-10-03" }, "genre": "preprint", "id": "arxiv:2409.14818", "issued": { "date-parts": [ [ 2024, 9, 23 ] ] }, "note": "First published: 2024-09-23; Recorded arXiv version: v2; Recorded version updated: 2024-10-03T05:23:22Z.", "title": "MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2409.15637v2", "archive": "arXiv", "archive_location": "2409.15637", "author": [ { "literal": "Tianyue Ou" }, { "literal": "Frank F. Xu" }, { "literal": "Aman Madaan" }, { "literal": "Jiarui Liu" }, { "literal": "Robert Lo" }, { "literal": "Abishek Sridhar" }, { "literal": "Sudipta Sengupta" }, { "literal": "Dan Roth" }, { "literal": "Graham Neubig" }, { "literal": "Shuyan Zhou" } ], "citation-key": "arxiv_2409_15637", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6c19b869b10f0b4c985b88b032f78e0e72f83e7ca8d9f346417054cd2a9002e3", "submitted_at": "2024-09-24T00:51:45Z", "updated_at": "2024-11-27T16:34:52Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.15637v2" }, "canonical_source_url": "https://arxiv.org/abs/2409.15637", "catalog_id": "arxiv:2409.15637", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-09-24", "identifiers": { "arxiv": "2409.15637" }, "publication": { "authors": [ "Tianyue Ou", "Frank F. Xu", "Aman Madaan", "Jiarui Liu", "Robert Lo", "Abishek Sridhar", "Sudipta Sengupta", "Dan Roth", "Graham Neubig", "Shuyan Zhou" ], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 12, 16 ], "doi": "10.52202/079017-2908", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a6a6891cf1dfc64d664f086cf5976e93-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "91618-91652", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/a6a6891cf1dfc64d664f086cf5976e93-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a6a6891cf1dfc64d664f086cf5976e93-Abstract-Conference.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "record_updated_at": "2024-11-27" }, "genre": "preprint", "id": "arxiv:2409.15637", "issued": { "date-parts": [ [ 2024, 9, 24 ] ] }, "note": "First published: 2024-09-24; Recorded arXiv version: v2; Recorded version updated: 2024-11-27T16:34:52Z.", "title": "Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2410.00201v1", "archive": "arXiv", "archive_location": "2410.00201", "author": [ { "literal": "Yi-Hao Peng" }, { "literal": "Faria Huq" }, { "literal": "Yue Jiang" }, { "literal": "Jason Wu" }, { "literal": "Amanda Xin Yue Li" }, { "literal": "Jeffrey Bigham" }, { "literal": "Amy Pavel" } ], "citation-key": "arxiv_2410_00201", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a85dca895f00b442a60123c7c85cd26a90e3d1c2a810c91c32385f877bcd755a", "submitted_at": "2024-09-30T19:55:54Z", "updated_at": "2024-09-30T19:55:54Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2410.00201v1" }, "canonical_source_url": "https://arxiv.org/abs/2410.00201", "catalog_id": "arxiv:2410.00201", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-09-30", "identifiers": { "arxiv": "2410.00201" }, "record_updated_at": "2024-09-30" }, "genre": "preprint", "id": "arxiv:2410.00201", "issued": { "date-parts": [ [ 2024, 9, 30 ] ] }, "note": "First published: 2024-09-30; Recorded arXiv version: v1; Recorded version updated: 2024-09-30T19:55:54Z.", "title": "DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2410.02907v2", "archive": "arXiv", "archive_location": "2410.02907", "author": [ { "literal": "Shikhar Murty" }, { "literal": "Hao Zhu" }, { "literal": "Dzmitry Bahdanau" }, { "literal": "Christopher D. Manning" } ], "citation-key": "arxiv_2410_02907", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5e227f3686b3234745ca1749cb8fb7c2b19383ac9dfebf68976f61f07d1ddf3b", "submitted_at": "2024-10-03T18:56:51Z", "updated_at": "2025-02-05T18:56:51Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.02907v2" }, "canonical_source_url": "https://arxiv.org/abs/2410.02907", "catalog_id": "arxiv:2410.02907", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-10-03", "identifiers": { "arxiv": "2410.02907" }, "record_updated_at": "2025-02-05" }, "genre": "preprint", "id": "arxiv:2410.02907", "issued": { "date-parts": [ [ 2024, 10, 3 ] ] }, "note": "First published: 2024-10-03; Recorded arXiv version: v2; Recorded version updated: 2025-02-05T18:56:51Z.", "title": "NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2410.05243v3", "archive": "arXiv", "archive_location": "2410.05243", "author": [ { "literal": "Boyu Gou" }, { "literal": "Ruohan Wang" }, { "literal": "Boyuan Zheng" }, { "literal": "Yanan Xie" }, { "literal": "Cheng Chang" }, { "literal": "Yiheng Shu" }, { "literal": "Huan Sun" }, { "literal": "Yu Su" } ], "citation-key": "arxiv_2410_05243", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "08ece826d135b9ab9dfed2a3baf9deeab99489120da749cd67517b636649c5a6", "submitted_at": "2024-10-07T17:47:50Z", "updated_at": "2025-06-17T15:06:02Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.05243v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.05243", "catalog_id": "arxiv:2410.05243", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-10-07", "identifiers": { "arxiv": "2410.05243" }, "publication": { "authors": [ "Boyu Gou", "Demi Ruohan Wang", "Boyuan Zheng", "Yanan Xie", "Cheng Chang", "Yiheng Shu", "Huan Sun", "Yu Su" ], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 5, 1 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://proceedings.iclr.cc/paper_files/paper/2025/hash/4ca0e369689dadb25a5345ba9755ad6f-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "30851-30883", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/4ca0e369689dadb25a5345ba9755ad6f-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/4ca0e369689dadb25a5345ba9755ad6f-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "record_updated_at": "2025-06-17" }, "genre": "preprint", "id": "arxiv:2410.05243", "issued": { "date-parts": [ [ 2024, 10, 7 ] ] }, "note": "First published: 2024-10-07; Recorded arXiv version: v3; Recorded version updated: 2025-06-17T15:06:02Z.", "title": "Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2410.13824v3", "archive": "arXiv", "archive_location": "2410.13824", "author": [ { "literal": "Junpeng Liu" }, { "literal": "Tianyue Ou" }, { "literal": "Yifan Song" }, { "literal": "Yuxiao Qu" }, { "literal": "Wai Lam" }, { "literal": "Chenyan Xiong" }, { "literal": "Wenhu Chen" }, { "literal": "Graham Neubig" }, { "literal": "Xiang Yue" } ], "citation-key": "arxiv_2410_13824", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2a3bcd26dff4f1d21a8a2772929c0c97cd1cc180a7606b0744e630dabae94609", "submitted_at": "2024-10-17T17:48:54Z", "updated_at": "2024-11-06T08:29:22Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.13824v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.13824", "catalog_id": "arxiv:2410.13824", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-10-17", "identifiers": { "arxiv": "2410.13824" }, "publication": { "authors": [ "Junpeng Liu", "Tianyue Ou", "Yifan Song", "Yuxiao Qu", "Wai Lam", "Chenyan Xiong", "Wenhu Chen", "Graham Neubig", "Xiang Yue" ], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 5, 1 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://proceedings.iclr.cc/paper_files/paper/2025/hash/2da53cd1abdae59150e35f4693834f32-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "17971-18005", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/2da53cd1abdae59150e35f4693834f32-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Harnessing Webpage UIs for Text-Rich Visual Understanding", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/2da53cd1abdae59150e35f4693834f32-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "record_updated_at": "2024-11-06" }, "genre": "preprint", "id": "arxiv:2410.13824", "issued": { "date-parts": [ [ 2024, 10, 17 ] ] }, "note": "First published: 2024-10-17; Recorded arXiv version: v3; Recorded version updated: 2024-11-06T08:29:22Z.", "title": "Harnessing Webpage UIs for Text-Rich Visual Understanding", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2410.19461v2", "archive": "arXiv", "archive_location": "2410.19461", "author": [ { "literal": "Xuetian Chen" }, { "literal": "Hangcheng Li" }, { "literal": "Jiaqing Liang" }, { "literal": "Sihang Jiang" }, { "literal": "Deqing Yang" } ], "citation-key": "arxiv_2410_19461", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dce2e22787c6e2cce95ecc4f5583bf94d7670b4b87ab75d2b8c7efb66fbcd1a8", "submitted_at": "2024-10-25T10:46:17Z", "updated_at": "2024-11-02T08:54:21Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.19461v2" }, "canonical_source_url": "https://arxiv.org/abs/2410.19461", "catalog_id": "arxiv:2410.19461", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-10-25", "identifiers": { "arxiv": "2410.19461" }, "record_updated_at": "2024-11-02" }, "genre": "preprint", "id": "arxiv:2410.19461", "issued": { "date-parts": [ [ 2024, 10, 25 ] ] }, "note": "First published: 2024-10-25; Recorded arXiv version: v2; Recorded version updated: 2024-11-02T08:54:21Z.", "title": "EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2410.19609v1", "archive": "arXiv", "archive_location": "2410.19609", "author": [ { "literal": "Hongliang He" }, { "literal": "Wenlin Yao" }, { "literal": "Kaixin Ma" }, { "literal": "Wenhao Yu" }, { "literal": "Hongming Zhang" }, { "literal": "Tianqing Fang" }, { "literal": "Zhenzhong Lan" }, { "literal": "Dong Yu" } ], "citation-key": "arxiv_2410_19609", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "db2a115281f831ea9333a03fc2a9ebb2f09528eb082060f00a33b125f9ef7762", "submitted_at": "2024-10-25T15:01:27Z", "updated_at": "2024-10-25T15:01:27Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2410.19609v1" }, "canonical_source_url": "https://arxiv.org/abs/2410.19609", "catalog_id": "arxiv:2410.19609", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-10-25", "identifiers": { "arxiv": "2410.19609" }, "publication": { "authors": [ "Hongliang He", "Wenlin Yao", "Kaixin Ma", "Wenhao Yu", "Hongming Zhang", "Tianqing Fang", "Zhenzhong Lan", "Dong Yu" ], "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.1336", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.1336/" ], "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": "27545-27564", "pdf_url": "https://aclanthology.org/2025.acl-long.1336.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.1336/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2024-10-25" }, "genre": "preprint", "id": "arxiv:2410.19609", "issued": { "date-parts": [ [ 2024, 10, 25 ] ] }, "note": "First published: 2024-10-25; Recorded arXiv version: v1; Recorded version updated: 2024-10-25T15:01:27Z.", "title": "OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2410.23218v1", "archive": "arXiv", "archive_location": "2410.23218", "author": [ { "literal": "Zhiyong Wu" }, { "literal": "Zhenyu Wu" }, { "literal": "Fangzhi Xu" }, { "literal": "Yian Wang" }, { "literal": "Qiushi Sun" }, { "literal": "Chengyou Jia" }, { "literal": "Kanzhi Cheng" }, { "literal": "Zichen Ding" }, { "literal": "Liheng Chen" }, { "literal": "Paul Pu Liang" }, { "literal": "Yu Qiao" } ], "citation-key": "arxiv_2410_23218", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e0dbd8ef8807e7886c02ed6296c9d188503fe7b676062fcff1890fd0652f10f3", "submitted_at": "2024-10-30T17:10:19Z", "updated_at": "2024-10-30T17:10:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2410.23218v1" }, "canonical_source_url": "https://arxiv.org/abs/2410.23218", "catalog_id": "arxiv:2410.23218", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-10-30", "identifiers": { "arxiv": "2410.23218" }, "record_updated_at": "2024-10-30" }, "genre": "preprint", "id": "arxiv:2410.23218", "issued": { "date-parts": [ [ 2024, 10, 30 ] ] }, "note": "First published: 2024-10-30; Recorded arXiv version: v1; Recorded version updated: 2024-10-30T17:10:19Z.", "title": "OS-ATLAS: A Foundation Action Model for Generalist GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2410.24024v2", "archive": "arXiv", "archive_location": "2410.24024", "author": [ { "literal": "Yifan Xu" }, { "literal": "Xiao Liu" }, { "literal": "Xueqiao Sun" }, { "literal": "Siyi Cheng" }, { "literal": "Hao Yu" }, { "literal": "Hanyu Lai" }, { "literal": "Shudan Zhang" }, { "literal": "Dan Zhang" }, { "literal": "Jie Tang" }, { "literal": "Yuxiao Dong" } ], "citation-key": "arxiv_2410_24024", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d29fe5262adf8677bbd5fead628c5fc28707af263aa7e800d1dee1f7e499784c", "submitted_at": "2024-10-31T15:25:20Z", "updated_at": "2024-11-04T05:57:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.24024v2" }, "canonical_source_url": "https://arxiv.org/abs/2410.24024", "catalog_id": "arxiv:2410.24024", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-10-31", "identifiers": { "arxiv": "2410.24024" }, "publication": { "authors": [ "Yifan Xu", "Xiao Liu", "Xueqiao Sun", "Siyi Cheng", "Hao Yu (余浩)", "Hanyu Lai", "Shudan Zhang", "Dan Zhang", "Jie Tang", "Yuxiao Dong" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.acl-long.107", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.107/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "2144-2166", "pdf_url": "https://aclanthology.org/2025.acl-long.107.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.107/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2024-11-04" }, "genre": "preprint", "id": "arxiv:2410.24024", "issued": { "date-parts": [ [ 2024, 10, 31 ] ] }, "note": "First published: 2024-10-31; Recorded arXiv version: v2; Recorded version updated: 2024-11-04T05:57:31Z.", "title": "AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2411.13451v1", "archive": "arXiv", "archive_location": "2411.13451", "author": [ { "literal": "Gaurav Verma" }, { "literal": "Rachneet Kaur" }, { "literal": "Nishan Srishankar" }, { "literal": "Zhen Zeng" }, { "literal": "Tucker Balch" }, { "literal": "Manuela Veloso" } ], "citation-key": "arxiv_2411_13451", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "94d908dd89ff27434805fe7915c5a93d5c2b1d873449babc1c566c5582cca734", "submitted_at": "2024-11-20T16:54:15Z", "updated_at": "2024-11-20T16:54:15Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2411.13451v1" }, "canonical_source_url": "https://arxiv.org/abs/2411.13451", "catalog_id": "arxiv:2411.13451", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-11-20", "identifiers": { "arxiv": "2411.13451" }, "publication": { "authors": [ "Gaurav Verma", "Rachneet Kaur", "Nishan Srishankar", "Zhen Zeng", "Tucker Balch", "Manuela Veloso" ], "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.1008", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.1008/" ], "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": "20635-20651", "pdf_url": "https://aclanthology.org/2025.acl-long.1008.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.1008/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2024-11-20" }, "genre": "preprint", "id": "arxiv:2411.13451", "issued": { "date-parts": [ [ 2024, 11, 20 ] ] }, "note": "First published: 2024-11-20; Recorded arXiv version: v1; Recorded version updated: 2024-11-20T16:54:15Z.", "title": "AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2412.00402v1", "archive": "arXiv", "archive_location": "2412.00402", "author": [ { "literal": "Weikai Xie" }, { "literal": "Li Zhang" }, { "literal": "Shihe Wang" }, { "literal": "Rongjie Yi" }, { "literal": "Mengwei Xu" } ], "citation-key": "arxiv_2412_00402", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9c22d6a9aafb89e5628198fb4f6ea50fe40b1e955a2fa367571459753cea61df", "submitted_at": "2024-11-30T08:55:39Z", "updated_at": "2024-11-30T08:55:39Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2412.00402v1" }, "canonical_source_url": "https://arxiv.org/abs/2412.00402", "catalog_id": "arxiv:2412.00402", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2024-11-30", "identifiers": { "arxiv": "2412.00402" }, "record_updated_at": "2024-11-30" }, "genre": "preprint", "id": "arxiv:2412.00402", "issued": { "date-parts": [ [ 2024, 11, 30 ] ] }, "note": "First published: 2024-11-30; Recorded arXiv version: v1; Recorded version updated: 2024-11-30T08:55:39Z.", "title": "DroidCall: A Dataset for LLM-powered Android Intent Invocation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2412.04454v2", "archive": "arXiv", "archive_location": "2412.04454", "author": [ { "literal": "Yiheng Xu" }, { "literal": "Zekun Wang" }, { "literal": "Junli Wang" }, { "literal": "Dunjie Lu" }, { "literal": "Tianbao Xie" }, { "literal": "Amrita Saha" }, { "literal": "Doyen Sahoo" }, { "literal": "Tao Yu" }, { "literal": "Caiming Xiong" } ], "citation-key": "arxiv_2412_04454", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "89dbdf874ace87db12fa321e67ecf818d3964622b045ea7d95e109101820d407", "submitted_at": "2024-12-05T18:58:26Z", "updated_at": "2025-05-05T16:17:20Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2412.04454v2" }, "canonical_source_url": "https://arxiv.org/abs/2412.04454", "catalog_id": "arxiv:2412.04454", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-12-05", "identifiers": { "arxiv": "2412.04454" }, "record_updated_at": "2025-05-05" }, "genre": "preprint", "id": "arxiv:2412.04454", "issued": { "date-parts": [ [ 2024, 12, 5 ] ] }, "note": "First published: 2024-12-05; Recorded arXiv version: v2; Recorded version updated: 2025-05-05T16:17:20Z.", "title": "Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2412.09362v1", "archive": "arXiv", "archive_location": "2412.09362", "author": [ { "literal": "Huawen Shen" }, { "literal": "Chang Liu" }, { "literal": "Gengluo Li" }, { "literal": "Xinlong Wang" }, { "literal": "Yu Zhou" }, { "literal": "Can Ma" }, { "literal": "Xiangyang Ji" } ], "citation-key": "arxiv_2412_09362", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ee5840bbd1404674f0e9509b305e995c4dece9257e3f2a79348dde9aee99928b", "submitted_at": "2024-12-12T15:29:36Z", "updated_at": "2024-12-12T15:29:36Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2412.09362v1" }, "canonical_source_url": "https://arxiv.org/abs/2412.09362", "catalog_id": "arxiv:2412.09362", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-12-12", "identifiers": { "arxiv": "2412.09362" }, "record_updated_at": "2024-12-12" }, "genre": "preprint", "id": "arxiv:2412.09362", "issued": { "date-parts": [ [ 2024, 12, 12 ] ] }, "note": "First published: 2024-12-12; Recorded arXiv version: v1; Recorded version updated: 2024-12-12T15:29:36Z.", "title": "Falcon-UI: Understanding GUI Before Following User Instructions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2412.09605v2", "archive": "arXiv", "archive_location": "2412.09605", "author": [ { "literal": "Yiheng Xu" }, { "literal": "Dunjie Lu" }, { "literal": "Zhennan Shen" }, { "literal": "Junli Wang" }, { "literal": "Zekun Wang" }, { "literal": "Yuchen Mao" }, { "literal": "Caiming Xiong" }, { "literal": "Tao Yu" } ], "citation-key": "arxiv_2412_09605", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8ee630d434cef63f63c368752aeae14b0a60d49c3fde33b3a79ecbfc8fc4d06e", "submitted_at": "2024-12-12T18:59:27Z", "updated_at": "2025-03-03T18:59:36Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2412.09605v2" }, "canonical_source_url": "https://arxiv.org/abs/2412.09605", "catalog_id": "arxiv:2412.09605", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-12-12", "identifiers": { "arxiv": "2412.09605" }, "record_updated_at": "2025-03-03" }, "genre": "preprint", "id": "arxiv:2412.09605", "issued": { "date-parts": [ [ 2024, 12, 12 ] ] }, "note": "First published: 2024-12-12; Recorded arXiv version: v2; Recorded version updated: 2025-03-03T18:59:36Z.", "title": "AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2412.10047v2", "archive": "arXiv", "archive_location": "2412.10047", "author": [ { "literal": "Lu Wang" }, { "literal": "Fangkai Yang" }, { "literal": "Chaoyun Zhang" }, { "literal": "Junting Lu" }, { "literal": "Jiaxu Qian" }, { "literal": "Shilin He" }, { "literal": "Pu Zhao" }, { "literal": "Bo Qiao" }, { "literal": "Ray Huang" }, { "literal": "Si Qin" }, { "literal": "Qisheng Su" }, { "literal": "Jiayi Ye" }, { "literal": "Yudi Zhang" }, { "literal": "Jian-Guang Lou" }, { "literal": "Qingwei Lin" }, { "literal": "Saravan Rajmohan" }, { "literal": "Dongmei Zhang" }, { "literal": "Qi Zhang" } ], "citation-key": "arxiv_2412_10047", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2412.10047", "catalog_id": "arxiv:2412.10047", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-12-13", "identifiers": { "arxiv": "2412.10047" }, "record_updated_at": "2025-01-13" }, "genre": "preprint", "id": "arxiv:2412.10047", "issued": { "date-parts": [ [ 2024, 12, 13 ] ] }, "note": "First published: 2024-12-13; Recorded arXiv version: v2; Recorded version updated: 2025-01-13T06:47:21Z.", "title": "Large Action Models: From Inception to Implementation", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2412.13194v1", "archive": "arXiv", "archive_location": "2412.13194", "author": [ { "literal": "Yifei Zhou" }, { "literal": "Qianlan Yang" }, { "literal": "Kaixiang Lin" }, { "literal": "Min Bai" }, { "literal": "Xiong Zhou" }, { "literal": "Yu-Xiong Wang" }, { "literal": "Sergey Levine" }, { "literal": "Erran Li" } ], "citation-key": "arxiv_2412_13194", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "362d2a470603bece43d2205e56dd633e7310cfad2ba2d91b0b765abcbcc41b2f", "submitted_at": "2024-12-17T18:59:50Z", "updated_at": "2024-12-17T18:59:50Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2412.13194v1" }, "canonical_source_url": "https://arxiv.org/abs/2412.13194", "catalog_id": "arxiv:2412.13194", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-12-17", "identifiers": { "arxiv": "2412.13194" }, "record_updated_at": "2024-12-17" }, "genre": "preprint", "id": "arxiv:2412.13194", "issued": { "date-parts": [ [ 2024, 12, 17 ] ] }, "note": "First published: 2024-12-17; Recorded arXiv version: v1; Recorded version updated: 2024-12-17T18:59:50Z.", "title": "Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2412.17589v1", "archive": "arXiv", "archive_location": "2412.17589", "author": [ { "literal": "Yanheng He" }, { "literal": "Jiahe Jin" }, { "literal": "Shijie Xia" }, { "literal": "Jiadi Su" }, { "literal": "Runze Fan" }, { "literal": "Haoyang Zou" }, { "literal": "Xiangkun Hu" }, { "literal": "Pengfei Liu" } ], "citation-key": "arxiv_2412_17589", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "db567d35887fe5367e456b35bc347400b1bc2d147730e9d34c158e1fd7c8dd6c", "submitted_at": "2024-12-23T14:02:12Z", "updated_at": "2024-12-23T14:02:12Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2412.17589v1" }, "canonical_source_url": "https://arxiv.org/abs/2412.17589", "catalog_id": "arxiv:2412.17589", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-12-23", "identifiers": { "arxiv": "2412.17589" }, "record_updated_at": "2024-12-23" }, "genre": "preprint", "id": "arxiv:2412.17589", "issued": { "date-parts": [ [ 2024, 12, 23 ] ] }, "note": "First published: 2024-12-23; Recorded arXiv version: v1; Recorded version updated: 2024-12-23T14:02:12Z.", "title": "PC Agent: While You Sleep, AI Works -- A Cognitive Journey into Digital World", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2412.19723v3", "archive": "arXiv", "archive_location": "2412.19723", "author": [ { "literal": "Qiushi Sun" }, { "literal": "Kanzhi Cheng" }, { "literal": "Zichen Ding" }, { "literal": "Chuanyang Jin" }, { "literal": "Yian Wang" }, { "literal": "Fangzhi Xu" }, { "literal": "Zhenyu Wu" }, { "literal": "Chengyou Jia" }, { "literal": "Liheng Chen" }, { "literal": "Zhoumianze Liu" }, { "literal": "Ben Kao" }, { "literal": "Guohao Li" }, { "literal": "Junxian He" }, { "literal": "Yu Qiao" }, { "literal": "Zhiyong Wu" } ], "citation-key": "arxiv_2412_19723", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "40b5e3090c25f80d8d786f623812459b329acc2772f945419a585ffb27c54db3", "submitted_at": "2024-12-27T16:21:58Z", "updated_at": "2025-06-27T08:25:48Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2412.19723v3" }, "canonical_source_url": "https://arxiv.org/abs/2412.19723", "catalog_id": "arxiv:2412.19723", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-12-27", "identifiers": { "arxiv": "2412.19723" }, "publication": { "authors": [ "Qiushi Sun", "Kanzhi Cheng", "Zichen Ding", "Chuanyang Jin", "Yian Wang", "Fangzhi Xu", "Zhenyu Wu", "Chengyou Jia", "Liheng Chen", "Zhoumianze Liu", "Ben Kao", "Guohao Li", "Junxian He", "Yu Qiao", "Zhiyong Wu" ], "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.277", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.277/" ], "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": "5555-5579", "pdf_url": "https://aclanthology.org/2025.acl-long.277.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.277/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-06-27" }, "genre": "preprint", "id": "arxiv:2412.19723", "issued": { "date-parts": [ [ 2024, 12, 27 ] ] }, "note": "First published: 2024-12-27; Recorded arXiv version: v3; Recorded version updated: 2025-06-27T08:25:48Z.", "title": "OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2501.11425v3", "archive": "arXiv", "archive_location": "2501.11425", "author": [ { "literal": "Siyu Yuan" }, { "literal": "Zehui Chen" }, { "literal": "Zhiheng Xi" }, { "literal": "Junjie Ye" }, { "literal": "Zhengyin Du" }, { "literal": "Jiecao Chen" } ], "citation-key": "arxiv_2501_11425", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "692a6984b464367c99beb9c5fbd4bbd8378e79f4a4b749503c8fbb72dd80b16f", "submitted_at": "2025-01-20T11:46:04Z", "updated_at": "2025-03-24T10:18:56Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2501.11425v3" }, "canonical_source_url": "https://arxiv.org/abs/2501.11425", "catalog_id": "arxiv:2501.11425", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2025-01-20", "identifiers": { "arxiv": "2501.11425" }, "record_updated_at": "2025-03-24" }, "genre": "preprint", "id": "arxiv:2501.11425", "issued": { "date-parts": [ [ 2025, 1, 20 ] ] }, "note": "First published: 2025-01-20; Recorded arXiv version: v3; Recorded version updated: 2025-03-24T10:18:56Z.", "title": "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2501.12326v1", "archive": "arXiv", "archive_location": "2501.12326", "author": [ { "literal": "Yujia Qin" }, { "literal": "Yining Ye" }, { "literal": "Junjie Fang" }, { "literal": "Haoming Wang" }, { "literal": "Shihao Liang" }, { "literal": "Shizuo Tian" }, { "literal": "Junda Zhang" }, { "literal": "Jiahao Li" }, { "literal": "Yunxin Li" }, { "literal": "Shijue Huang" }, { "literal": "Wanjun Zhong" }, { "literal": "Kuanye Li" }, { "literal": "Jiale Yang" }, { "literal": "Yu Miao" }, { "literal": "Woyu Lin" }, { "literal": "Longxiang Liu" }, { "literal": "Xu Jiang" }, { "literal": "Qianli Ma" }, { "literal": "Jingyu Li" }, { "literal": "Xiaojun Xiao" }, { "literal": "Kai Cai" }, { "literal": "Chuang Li" }, { "literal": "Yaowei Zheng" }, { "literal": "Chaolin Jin" }, { "literal": "Chen Li" }, { "literal": "Xiao Zhou" }, { "literal": "Minchao Wang" }, { "literal": "Haoli Chen" }, { "literal": "Zhaojian Li" }, { "literal": "Haihua Yang" }, { "literal": "Haifeng Liu" }, { "literal": "Feng Lin" }, { "literal": "Tao Peng" }, { "literal": "Xin Liu" }, { "literal": "Guang Shi" } ], "citation-key": "arxiv_2501_12326", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d19aa758e66411a31dd1fea6f07c83d1c828bd4aad86f1564a9d7f3670c3f79f", "submitted_at": "2025-01-21T17:48:10Z", "updated_at": "2025-01-21T17:48:10Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2501.12326v1" }, "canonical_source_url": "https://arxiv.org/abs/2501.12326", "catalog_id": "arxiv:2501.12326", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-01-21", "identifiers": { "arxiv": "2501.12326" }, "record_updated_at": "2025-01-21" }, "genre": "preprint", "id": "arxiv:2501.12326", "issued": { "date-parts": [ [ 2025, 1, 21 ] ] }, "note": "First published: 2025-01-21; Recorded arXiv version: v1; Recorded version updated: 2025-01-21T17:48:10Z.", "title": "UI-TARS: Pioneering Automated GUI Interaction with Native Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2501.13896v2", "archive": "arXiv", "archive_location": "2501.13896", "author": [ { "literal": "Yue Fan" }, { "literal": "Handong Zhao" }, { "literal": "Ruiyi Zhang" }, { "literal": "Yu Shen" }, { "literal": "Xin Eric Wang" }, { "literal": "Gang Wu" } ], "citation-key": "arxiv_2501_13896", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0804055deb6c3513990ed8d596486400f1cb791338b7866d9e949186a34eb9c5", "submitted_at": "2025-01-23T18:16:21Z", "updated_at": "2025-01-27T18:58:42Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2501.13896v2" }, "canonical_source_url": "https://arxiv.org/abs/2501.13896", "catalog_id": "arxiv:2501.13896", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-01-23", "identifiers": { "arxiv": "2501.13896" }, "record_updated_at": "2025-01-27" }, "genre": "preprint", "id": "arxiv:2501.13896", "issued": { "date-parts": [ [ 2025, 1, 23 ] ] }, "note": "First published: 2025-01-23; Recorded arXiv version: v2; Recorded version updated: 2025-01-27T18:58:42Z.", "title": "GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2502.01977v2", "archive": "arXiv", "archive_location": "2502.01977", "author": [ { "literal": "Hongxin Li" }, { "literal": "Jingfan Chen" }, { "literal": "Jingran Su" }, { "literal": "Yuntao Chen" }, { "literal": "Qing Li" }, { "literal": "Zhaoxiang Zhang" } ], "citation-key": "arxiv_2502_01977", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2b76ab1c6c44db9f86b2bfc11097c54e5c3115c0c498a58d896bef043d2113c8", "submitted_at": "2025-02-04T03:39:59Z", "updated_at": "2025-06-07T05:23:58Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2502.01977v2" }, "canonical_source_url": "https://arxiv.org/abs/2502.01977", "catalog_id": "arxiv:2502.01977", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-02-04", "identifiers": { "arxiv": "2502.01977" }, "record_updated_at": "2025-06-07" }, "genre": "preprint", "id": "arxiv:2502.01977", "issued": { "date-parts": [ [ 2025, 2, 4 ] ] }, "note": "First published: 2025-02-04; Recorded arXiv version: v2; Recorded version updated: 2025-06-07T05:23:58Z.", "title": "AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2502.02955v1", "archive": "arXiv", "archive_location": "2502.02955", "author": [ { "literal": "Qinzhuo Wu" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Bin Wang" } ], "citation-key": "arxiv_2502_02955", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d3e0b19f259bcdb57b0dea92578d0ee1c7c229ea11e622c56e808f17ca2568cc", "submitted_at": "2025-02-05T07:35:23Z", "updated_at": "2025-02-05T07:35:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2502.02955v1" }, "canonical_source_url": "https://arxiv.org/abs/2502.02955", "catalog_id": "arxiv:2502.02955", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2025-02-05", "identifiers": { "arxiv": "2502.02955" }, "publication": { "authors": [ "Qinzhuo Wu", "Wei Liu", "Jian Luan", "Bin Wang" ], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 4 ], "doi": "10.18653/v1/2025.naacl-long.244", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.naacl-long.244/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "4760-4775", "pdf_url": "https://aclanthology.org/2025.naacl-long.244.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-long.244/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-02-05" }, "genre": "preprint", "id": "arxiv:2502.02955", "issued": { "date-parts": [ [ 2025, 2, 5 ] ] }, "note": "First published: 2025-02-05; Recorded arXiv version: v1; Recorded version updated: 2025-02-05T07:35:23Z.", "title": "ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2502.02982v2", "archive": "arXiv", "archive_location": "2502.02982", "author": [ { "literal": "Wenhao Wang" }, { "literal": "Mengying Yuan" }, { "literal": "Zijie Yu" }, { "literal": "Guangyi Liu" }, { "literal": "Rui Ye" }, { "literal": "Tian Jin" }, { "literal": "Siheng Chen" }, { "literal": "Yanfeng Wang" } ], "citation-key": "arxiv_2502_02982", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ecab608111104ac044bb7d28996604e9b87bdad4543c250c57bf432f883b96d5", "submitted_at": "2025-02-05T08:26:17Z", "updated_at": "2025-05-20T07:03:02Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2502.02982v2" }, "canonical_source_url": "https://arxiv.org/abs/2502.02982", "catalog_id": "arxiv:2502.02982", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-02-05", "identifiers": { "arxiv": "2502.02982" }, "record_updated_at": "2025-05-20" }, "genre": "preprint", "id": "arxiv:2502.02982", "issued": { "date-parts": [ [ 2025, 2, 5 ] ] }, "note": "First published: 2025-02-05; Recorded arXiv version: v2; Recorded version updated: 2025-05-20T07:03:02Z.", "title": "MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2502.06395v1", "archive": "arXiv", "archive_location": "2502.06395", "author": [ { "literal": "Georgios Papoudakis" }, { "literal": "Thomas Coste" }, { "literal": "Zhihao Wu" }, { "literal": "Jianye Hao" }, { "literal": "Jun Wang" }, { "literal": "Kun Shao" } ], "citation-key": "arxiv_2502_06395", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "44ec9907c8d536488e59dea307aa05bd8adcadf96cb4f3ba25a355ffe4cf8ff7", "submitted_at": "2025-02-10T12:32:21Z", "updated_at": "2025-02-10T12:32:21Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2502.06395v1" }, "canonical_source_url": "https://arxiv.org/abs/2502.06395", "catalog_id": "arxiv:2502.06395", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-02-10", "identifiers": { "arxiv": "2502.06395" }, "record_updated_at": "2025-02-10" }, "genre": "preprint", "id": "arxiv:2502.06395", "issued": { "date-parts": [ [ 2025, 2, 10 ] ] }, "note": "First published: 2025-02-10; Recorded arXiv version: v1; Recorded version updated: 2025-02-10T12:32:21Z.", "title": "AppVLM: A Lightweight Vision Language Model for Online App Control", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2502.07942v2", "archive": "arXiv", "archive_location": "2502.07942", "author": [ { "literal": "Ruichen Zhang" }, { "literal": "Mufan Qiu" }, { "literal": "Zhen Tan" }, { "literal": "Mohan Zhang" }, { "literal": "Vincent Lu" }, { "literal": "Jie Peng" }, { "literal": "Kaidi Xu" }, { "literal": "Leandro Z. Agudelo" }, { "literal": "Peter Qian" }, { "literal": "Tianlong Chen" } ], "citation-key": "arxiv_2502_07942", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0535de4778b6a31adb64f833733ebf94acf54ba872d98afd40b3e1012fb737fd", "submitted_at": "2025-02-11T20:41:49Z", "updated_at": "2025-03-06T19:40:57Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2502.07942v2" }, "canonical_source_url": "https://arxiv.org/abs/2502.07942", "catalog_id": "arxiv:2502.07942", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-02-11", "identifiers": { "arxiv": "2502.07942" }, "record_updated_at": "2025-03-06" }, "genre": "preprint", "id": "arxiv:2502.07942", "issued": { "date-parts": [ [ 2025, 2, 11 ] ] }, "note": "First published: 2025-02-11; Recorded arXiv version: v2; Recorded version updated: 2025-03-06T19:40:57Z.", "title": "Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2502.11357v4", "archive": "arXiv", "archive_location": "2502.11357", "author": [ { "literal": "Vardaan Pahuja" }, { "literal": "Yadong Lu" }, { "literal": "Corby Rosset" }, { "literal": "Boyu Gou" }, { "literal": "Arindam Mitra" }, { "literal": "Spencer Whitehead" }, { "literal": "Yu Su" }, { "literal": "Ahmed Awadallah" } ], "citation-key": "arxiv_2502_11357", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d9f459a02b7a464d9e1e49579943d1b93d46308c1b00e795c903d2fa1502a2b2", "submitted_at": "2025-02-17T02:13:48Z", "updated_at": "2025-05-30T02:30:57Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2502.11357v4" }, "canonical_source_url": "https://arxiv.org/abs/2502.11357", "catalog_id": "arxiv:2502.11357", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2025-02-17", "identifiers": { "arxiv": "2502.11357" }, "publication": { "authors": [ "Vardaan Pahuja", "Yadong Lu", "Corby Rosset", "Boyu Gou", "Arindam Mitra", "Spencer Whitehead", "Yu Su", "Ahmed Awadallah" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.findings-acl.326", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.326/", "https://aclanthology.org/2025.findings-acl.326.pdf" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the publisher PDF, page 1. Landing-page citation metadata gives Ahmed Hassan for the final author, while the supplied BibTeX expands the name to Ahmed Hassan Awadallah; the PDF uses Ahmed Awadallah.", "pages": "6300-6323", "pdf_url": "https://aclanthology.org/2025.findings-acl.326.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.326/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2025-05-30" }, "genre": "preprint", "id": "arxiv:2502.11357", "issued": { "date-parts": [ [ 2025, 2, 17 ] ] }, "note": "First published: 2025-02-17; Recorded arXiv version: v4; Recorded version updated: 2025-05-30T02:30:57Z.", "title": "Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2503.02197v2", "archive": "arXiv", "archive_location": "2503.02197", "author": [ { "literal": "Zhixun Chen" }, { "literal": "Ming Li" }, { "literal": "Yuxuan Huang" }, { "literal": "Yali Du" }, { "literal": "Meng Fang" }, { "literal": "Tianyi Zhou" } ], "citation-key": "arxiv_2503_02197", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2a58e33cd2b60a8c734968dd92f031b9aa4811932b1a666d947b20ec4c6035a7", "submitted_at": "2025-03-04T02:14:55Z", "updated_at": "2025-06-05T01:42:08Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.02197v2" }, "canonical_source_url": "https://arxiv.org/abs/2503.02197", "catalog_id": "arxiv:2503.02197", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2025-03-04", "identifiers": { "arxiv": "2503.02197" }, "record_updated_at": "2025-06-05" }, "genre": "preprint", "id": "arxiv:2503.02197", "issued": { "date-parts": [ [ 2025, 3, 4 ] ] }, "note": "First published: 2025-03-04; Recorded arXiv version: v2; Recorded version updated: 2025-06-05T01:42:08Z.", "title": "ATLaS: Agent Tuning via Learning Critical Steps", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2503.03196v2", "archive": "arXiv", "archive_location": "2503.03196", "author": [ { "literal": "Zhiyuan Huang" }, { "literal": "Ziming Cheng" }, { "literal": "Junting Pan" }, { "literal": "Zhaohui Hou" }, { "literal": "Mingjie Zhan" } ], "citation-key": "arxiv_2503_03196", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d45cacb33df18242eb3f47f6c89c56e41a146dd110e4b4dc5340062b9b981250", "submitted_at": "2025-03-05T05:30:22Z", "updated_at": "2025-04-16T15:34:51Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.03196v2" }, "canonical_source_url": "https://arxiv.org/abs/2503.03196", "catalog_id": "arxiv:2503.03196", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-03-05", "identifiers": { "arxiv": "2503.03196" }, "record_updated_at": "2025-04-16" }, "genre": "preprint", "id": "arxiv:2503.03196", "issued": { "date-parts": [ [ 2025, 3, 5 ] ] }, "note": "First published: 2025-03-05; Recorded arXiv version: v2; Recorded version updated: 2025-04-16T15:34:51Z.", "title": "SpiritSight Agent: Advanced GUI Agent with One Look", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2503.09572v3", "archive": "arXiv", "archive_location": "2503.09572", "author": [ { "literal": "Lutfi Eren Erdogan" }, { "literal": "Nicholas Lee" }, { "literal": "Sehoon Kim" }, { "literal": "Suhong Moon" }, { "literal": "Hiroki Furuta" }, { "literal": "Gopala Anumanchipalli" }, { "literal": "Kurt Keutzer" }, { "literal": "Amir Gholami" } ], "citation-key": "arxiv_2503_09572", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6b03d84f29bb524d7950039624e0d460d8381f2ba63d70c69f5f958013730db9", "submitted_at": "2025-03-12T17:40:52Z", "updated_at": "2025-04-22T17:56:22Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2503.09572v3" }, "canonical_source_url": "https://arxiv.org/abs/2503.09572", "catalog_id": "arxiv:2503.09572", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-03-12", "identifiers": { "arxiv": "2503.09572" }, "record_updated_at": "2025-04-22" }, "genre": "preprint", "id": "arxiv:2503.09572", "issued": { "date-parts": [ [ 2025, 3, 12 ] ] }, "note": "First published: 2025-03-12; Recorded arXiv version: v3; Recorded version updated: 2025-04-22T17:56:22Z.", "title": "Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2503.11170v1", "archive": "arXiv", "archive_location": "2503.11170", "author": [ { "literal": "Yibin Xu" }, { "literal": "Liang Yang" }, { "literal": "Hao Chen" }, { "literal": "Hua Wang" }, { "literal": "Zhi Chen" }, { "literal": "Yaohua Tang" } ], "citation-key": "arxiv_2503_11170", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d2e6250e87ea9340914b457c4b0d471450f8cf49d2e2d53abd8e9e76105e908a", "submitted_at": "2025-03-14T08:16:02Z", "updated_at": "2025-03-14T08:16:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2503.11170v1" }, "canonical_source_url": "https://arxiv.org/abs/2503.11170", "catalog_id": "arxiv:2503.11170", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-03-14", "identifiers": { "arxiv": "2503.11170" }, "record_updated_at": "2025-03-14" }, "genre": "preprint", "id": "arxiv:2503.11170", "issued": { "date-parts": [ [ 2025, 3, 14 ] ] }, "note": "First published: 2025-03-14; Recorded arXiv version: v1; Recorded version updated: 2025-03-14T08:16:02Z.", "title": "DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2503.12532v2", "archive": "arXiv", "archive_location": "2503.12532", "author": [ { "literal": "Fanbin Lu" }, { "literal": "Zhisheng Zhong" }, { "literal": "Ziqin Wei" }, { "literal": "Shu Liu" }, { "literal": "Chi-Wing Fu" }, { "literal": "Jiaya Jia" } ], "citation-key": "arxiv_2503_12532", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e883289bafee01759a0f4f3f7051cbbebdcd8059e7520d68c25ba313b8da69a6", "submitted_at": "2025-03-16T14:53:43Z", "updated_at": "2025-03-24T16:33:28Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.12532v2" }, "canonical_source_url": "https://arxiv.org/abs/2503.12532", "catalog_id": "arxiv:2503.12532", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-03-16", "identifiers": { "arxiv": "2503.12532" }, "record_updated_at": "2025-03-24" }, "genre": "preprint", "id": "arxiv:2503.12532", "issued": { "date-parts": [ [ 2025, 3, 16 ] ] }, "note": "First published: 2025-03-16; Recorded arXiv version: v2; Recorded version updated: 2025-03-24T16:33:28Z.", "title": "STEVE: A Step Verification Pipeline for Computer-use Agent Training", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2503.14021v1", "archive": "arXiv", "archive_location": "2503.14021", "author": [ { "literal": "Ziwei Wang" }, { "literal": "Weizhi Chen" }, { "literal": "Leyang Yang" }, { "literal": "Sheng Zhou" }, { "literal": "Shengchu Zhao" }, { "literal": "Hanbei Zhan" }, { "literal": "Jiongchao Jin" }, { "literal": "Liangcheng Li" }, { "literal": "Zirui Shao" }, { "literal": "Jiajun Bu" } ], "citation-key": "arxiv_2503_14021", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b260fd1d7e28c8263710f116638e7aa7b51f46aac15199c8a29092161a13f37d", "submitted_at": "2025-03-18T08:32:22Z", "updated_at": "2025-03-18T08:32:22Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2503.14021v1" }, "canonical_source_url": "https://arxiv.org/abs/2503.14021", "catalog_id": "arxiv:2503.14021", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-03-18", "identifiers": { "arxiv": "2503.14021" }, "record_updated_at": "2025-03-18" }, "genre": "preprint", "id": "arxiv:2503.14021", "issued": { "date-parts": [ [ 2025, 3, 18 ] ] }, "note": "First published: 2025-03-18; Recorded arXiv version: v1; Recorded version updated: 2025-03-18T08:32:22Z.", "title": "MP-GUI: Modality Perception with MLLMs for GUI Understanding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2503.17709v1", "archive": "arXiv", "archive_location": "2503.17709", "author": [ { "literal": "Yuchen Sun" }, { "literal": "Shanhui Zhao" }, { "literal": "Tao Yu" }, { "literal": "Hao Wen" }, { "literal": "Samith Va" }, { "literal": "Mengwei Xu" }, { "literal": "Yuanchun Li" }, { "literal": "Chongyang Zhang" } ], "citation-key": "arxiv_2503_17709", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "80bb507bf3cdccf6f023d0c334899d9d7099c362e9f37c314b15ff9388bae65c", "submitted_at": "2025-03-22T09:30:37Z", "updated_at": "2025-03-22T09:30:37Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2503.17709v1" }, "canonical_source_url": "https://arxiv.org/abs/2503.17709", "catalog_id": "arxiv:2503.17709", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-03-22", "identifiers": { "arxiv": "2503.17709" }, "record_updated_at": "2025-03-22" }, "genre": "preprint", "id": "arxiv:2503.17709", "issued": { "date-parts": [ [ 2025, 3, 22 ] ] }, "note": "First published: 2025-03-22; Recorded arXiv version: v1; Recorded version updated: 2025-03-22T09:30:37Z.", "title": "GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2504.09352v1", "archive": "arXiv", "archive_location": "2504.09352", "author": [ { "literal": "Iason Chaimalas" }, { "literal": "Arnas Vyšniauskas" }, { "literal": "Gabriel Brostow" } ], "citation-key": "arxiv_2504_09352", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bf23700bf7626733b0016b773852455c503617adc81025fc9e097879b5534cca", "submitted_at": "2025-04-12T22:02:29Z", "updated_at": "2025-04-12T22:02:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2504.09352v1" }, "canonical_source_url": "https://arxiv.org/abs/2504.09352", "catalog_id": "arxiv:2504.09352", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-12", "identifiers": { "arxiv": "2504.09352" }, "record_updated_at": "2025-04-12" }, "genre": "preprint", "id": "arxiv:2504.09352", "issued": { "date-parts": [ [ 2025, 4, 12 ] ] }, "note": "First published: 2025-04-12; Recorded arXiv version: v1; Recorded version updated: 2025-04-12T22:02:29Z.", "title": "Explorer: Robust Collection of Interactable GUI Elements", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2504.10127v2", "archive": "arXiv", "archive_location": "2504.10127", "author": [ { "literal": "Junlei Zhang" }, { "literal": "Zichen Ding" }, { "literal": "Chang Ma" }, { "literal": "Zijie Chen" }, { "literal": "Qiushi Sun" }, { "literal": "Zhenzhong Lan" }, { "literal": "Junxian He" } ], "citation-key": "arxiv_2504_10127", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "171517999164a3581f71cf363ec6eed357b28ca86908cb97e8498c6958762a5f", "submitted_at": "2025-04-14T11:35:02Z", "updated_at": "2025-04-15T17:13:46Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.10127v2" }, "canonical_source_url": "https://arxiv.org/abs/2504.10127", "catalog_id": "arxiv:2504.10127", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-14", "identifiers": { "arxiv": "2504.10127" }, "record_updated_at": "2025-04-15" }, "genre": "preprint", "id": "arxiv:2504.10127", "issued": { "date-parts": [ [ 2025, 4, 14 ] ] }, "note": "First published: 2025-04-14; Recorded arXiv version: v2; Recorded version updated: 2025-04-15T17:13:46Z.", "title": "Breaking the Data Barrier -- Building GUI Agents Through Task Generalization", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2504.11257v4", "archive": "arXiv", "archive_location": "2504.11257", "author": [ { "literal": "Xinyi Liu" }, { "literal": "Xiaoyi Zhang" }, { "literal": "Ziyun Zhang" }, { "literal": "Yan Lu" } ], "citation-key": "arxiv_2504_11257", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "363e3c3e882fa93a19df74bbf77aa98525cf4639c8f62100c3ddc3e0a438997f", "submitted_at": "2025-04-15T14:56:21Z", "updated_at": "2025-07-30T13:57:49Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2504.11257v4" }, "canonical_source_url": "https://arxiv.org/abs/2504.11257", "catalog_id": "arxiv:2504.11257", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2025-04-15", "identifiers": { "arxiv": "2504.11257" }, "publication": { "authors": [ "Xinyi Liu", "Xiaoyi Zhang", "Ziyun Zhang", "Yan Lu" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.findings-acl.809", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.809/" ], "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": "15668-15684", "pdf_url": "https://aclanthology.org/2025.findings-acl.809.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.809/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2025-07-30" }, "genre": "preprint", "id": "arxiv:2504.11257", "issued": { "date-parts": [ [ 2025, 4, 15 ] ] }, "note": "First published: 2025-04-15; Recorded arXiv version: v4; Recorded version updated: 2025-07-30T13:57:49Z.", "title": "UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2504.12679v4", "archive": "arXiv", "archive_location": "2504.12679", "author": [ { "literal": "Bofei Zhang" }, { "literal": "Zirui Shang" }, { "literal": "Zhi Gao" }, { "literal": "Wang Zhang" }, { "literal": "Rui Xie" }, { "literal": "Xiaojian Ma" }, { "literal": "Tao Yuan" }, { "literal": "Xinxiao Wu" }, { "literal": "Song-Chun Zhu" }, { "literal": "Qing Li" } ], "citation-key": "arxiv_2504_12679", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "346fc4db7f8fbf2dc66c32e36f5cc5ace22228d60bdd4c61b6b7ac65487a4a8c", "submitted_at": "2025-04-17T06:15:56Z", "updated_at": "2025-12-04T15:01:09Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2504.12679v4" }, "canonical_source_url": "https://arxiv.org/abs/2504.12679", "catalog_id": "arxiv:2504.12679", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-17", "identifiers": { "arxiv": "2504.12679" }, "record_updated_at": "2025-12-04" }, "genre": "preprint", "id": "arxiv:2504.12679", "issued": { "date-parts": [ [ 2025, 4, 17 ] ] }, "note": "First published: 2025-04-17; Recorded arXiv version: v4; Recorded version updated: 2025-12-04T15:01:09Z.", "title": "TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2504.16419v2", "archive": "arXiv", "archive_location": "2504.16419", "author": [ { "literal": "Qi Yang" }, { "literal": "Weichen Bi" }, { "literal": "Haiyang Shen" }, { "literal": "Yaoqi Guo" }, { "literal": "Yun Ma" } ], "citation-key": "arxiv_2504_16419", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e1ec3311094166baac4de66ad0f083b66585c933f19cb66fc580bf128ad809ca", "submitted_at": "2025-04-23T05:01:25Z", "updated_at": "2025-04-27T06:52:23Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.16419v2" }, "canonical_source_url": "https://arxiv.org/abs/2504.16419", "catalog_id": "arxiv:2504.16419", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-23", "identifiers": { "arxiv": "2504.16419" }, "record_updated_at": "2025-04-27" }, "genre": "preprint", "id": "arxiv:2504.16419", "issued": { "date-parts": [ [ 2025, 4, 23 ] ] }, "note": "First published: 2025-04-23; Recorded arXiv version: v2; Recorded version updated: 2025-04-27T06:52:23Z.", "title": "PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2504.21024v2", "archive": "arXiv", "archive_location": "2504.21024", "author": [ { "literal": "Tianqing Fang" }, { "literal": "Hongming Zhang" }, { "literal": "Zhisong Zhang" }, { "literal": "Kaixin Ma" }, { "literal": "Wenhao Yu" }, { "literal": "Haitao Mi" }, { "literal": "Dong Yu" } ], "citation-key": "arxiv_2504_21024", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "86ca58c92ffc2cbbcb0297d8c7618dfab966e36a07b141c068998b0f2934d11e", "submitted_at": "2025-04-23T02:54:31Z", "updated_at": "2025-08-21T05:55:43Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.21024v2" }, "canonical_source_url": "https://arxiv.org/abs/2504.21024", "catalog_id": "arxiv:2504.21024", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-23", "identifiers": { "arxiv": "2504.21024" }, "record_updated_at": "2025-08-21" }, "genre": "preprint", "id": "arxiv:2504.21024", "issued": { "date-parts": [ [ 2025, 4, 23 ] ] }, "note": "First published: 2025-04-23; Recorded arXiv version: v2; Recorded version updated: 2025-08-21T05:55:43Z.", "title": "WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2505.00416v1", "archive": "arXiv", "archive_location": "2505.00416", "author": [ { "literal": "Jing Huang" }, { "literal": "Zhixiong Zeng" }, { "literal": "Wenkang Han" }, { "literal": "Yufeng Zhong" }, { "literal": "Liming Zheng" }, { "literal": "Shuai Fu" }, { "literal": "Jingyuan Chen" }, { "literal": "Lin Ma" } ], "citation-key": "arxiv_2505_00416", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e582c92521ec41a0a3daa0ca72b8c00250621289352b28400ee6d311c4a106eb", "submitted_at": "2025-05-01T09:27:13Z", "updated_at": "2025-05-01T09:27:13Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.00416v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.00416", "catalog_id": "arxiv:2505.00416", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-01", "identifiers": { "arxiv": "2505.00416" }, "record_updated_at": "2025-05-01" }, "genre": "preprint", "id": "arxiv:2505.00416", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "First published: 2025-05-01; Recorded arXiv version: v1; Recorded version updated: 2025-05-01T09:27:13Z.", "title": "ScaleTrack: Scaling and back-tracking Automated GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.12299v4", "archive": "arXiv", "archive_location": "2505.12299", "author": [ { "literal": "Kun Huang" }, { "literal": "Weikai Xu" }, { "literal": "Yuxuan Liu" }, { "literal": "Quandong Wang" }, { "literal": "Pengzhi Gao" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Bin Wang" }, { "literal": "Bo An" } ], "citation-key": "arxiv_2505_12299", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9bc92029e16b5afb4b54837d2ab2304c7b8176548061c9deafdca101754128dc", "submitted_at": "2025-05-18T08:28:05Z", "updated_at": "2026-03-21T09:25:27Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2505.12299v4" }, "canonical_source_url": "https://arxiv.org/abs/2505.12299", "catalog_id": "arxiv:2505.12299", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-18", "identifiers": { "arxiv": "2505.12299" }, "record_updated_at": "2026-03-21" }, "genre": "preprint", "id": "arxiv:2505.12299", "issued": { "date-parts": [ [ 2025, 5, 18 ] ] }, "note": "First published: 2025-05-18; Recorded arXiv version: v4; Recorded version updated: 2026-03-21T09:25:27Z.", "title": "MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2505.12493v3", "archive": "arXiv", "archive_location": "2505.12493", "author": [ { "literal": "Longxi Gao" }, { "literal": "Li Zhang" }, { "literal": "Pengzhi Gao" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Mengwei Xu" } ], "citation-key": "arxiv_2505_12493", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "10d826ea7715ab7054522a9dcba622d5dae3e6c3faee421e4b168e16104d184b", "submitted_at": "2025-05-18T16:34:30Z", "updated_at": "2025-10-10T09:28:53Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.12493v3" }, "canonical_source_url": "https://arxiv.org/abs/2505.12493", "catalog_id": "arxiv:2505.12493", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-18", "identifiers": { "arxiv": "2505.12493" }, "record_updated_at": "2025-10-10" }, "genre": "preprint", "id": "arxiv:2505.12493", "issued": { "date-parts": [ [ 2025, 5, 18 ] ] }, "note": "First published: 2025-05-18; Recorded arXiv version: v3; Recorded version updated: 2025-10-10T09:28:53Z.", "title": "GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2505.12632v1", "archive": "arXiv", "archive_location": "2505.12632", "author": [ { "literal": "Yunseok Jang" }, { "literal": "Yeda Song" }, { "literal": "Sungryull Sohn" }, { "literal": "Lajanugen Logeswaran" }, { "literal": "Tiange Luo" }, { "literal": "Dong-Ki Kim" }, { "literal": "Kyunghoon Bae" }, { "literal": "Honglak Lee" } ], "citation-key": "arxiv_2505_12632", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "64672e6a3450256a8b04d9db231e885e2dd4e8688235f6c7853d70d6276610ff", "submitted_at": "2025-05-19T02:39:03Z", "updated_at": "2025-05-19T02:39:03Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.12632v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.12632", "catalog_id": "arxiv:2505.12632", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-19", "identifiers": { "arxiv": "2505.12632" }, "record_updated_at": "2025-05-19" }, "genre": "preprint", "id": "arxiv:2505.12632", "issued": { "date-parts": [ [ 2025, 5, 19 ] ] }, "note": "First published: 2025-05-19; Recorded arXiv version: v1; Recorded version updated: 2025-05-19T02:39:03Z.", "title": "Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.13227v3", "archive": "arXiv", "archive_location": "2505.13227", "author": [ { "literal": "Tianbao Xie" }, { "literal": "Jiaqi Deng" }, { "literal": "Xiaochuan Li" }, { "literal": "Junlin Yang" }, { "literal": "Haoyuan Wu" }, { "literal": "Jixuan Chen" }, { "literal": "Wenjing Hu" }, { "literal": "Xinyuan Wang" }, { "literal": "Yuhui Xu" }, { "literal": "Zekun Wang" }, { "literal": "Yiheng Xu" }, { "literal": "Junli Wang" }, { "literal": "Doyen Sahoo" }, { "literal": "Tao Yu" }, { "literal": "Caiming Xiong" } ], "citation-key": "arxiv_2505_13227", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1bec4ad578c01ebdfb58bd269562d3ca7a2bd8d2687cde07cb867db0b78cb105", "submitted_at": "2025-05-19T15:09:23Z", "updated_at": "2025-10-24T19:08:03Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.13227v3" }, "canonical_source_url": "https://arxiv.org/abs/2505.13227", "catalog_id": "arxiv:2505.13227", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-19", "identifiers": { "arxiv": "2505.13227" }, "record_updated_at": "2025-10-24" }, "genre": "preprint", "id": "arxiv:2505.13227", "issued": { "date-parts": [ [ 2025, 5, 19 ] ] }, "note": "First published: 2025-05-19; Recorded arXiv version: v3; Recorded version updated: 2025-10-24T19:08:03Z.", "title": "Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2505.13909v2", "archive": "arXiv", "archive_location": "2505.13909", "author": [ { "literal": "Yanheng He" }, { "literal": "Jiahe Jin" }, { "literal": "Pengfei Liu" } ], "citation-key": "arxiv_2505_13909", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "026a64046926912a54e6a7c6cf62a17740a6f89a94713615f9750f8bf8302c78", "submitted_at": "2025-05-20T04:20:18Z", "updated_at": "2026-03-03T03:55:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2505.13909v2" }, "canonical_source_url": "https://arxiv.org/abs/2505.13909", "catalog_id": "arxiv:2505.13909", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-20", "identifiers": { "arxiv": "2505.13909" }, "record_updated_at": "2026-03-03" }, "genre": "preprint", "id": "arxiv:2505.13909", "issued": { "date-parts": [ [ 2025, 5, 20 ] ] }, "note": "First published: 2025-05-20; Recorded arXiv version: v2; Recorded version updated: 2026-03-03T03:55:55Z.", "title": "Efficient Agent Training for Computer Use", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2505.15277v2", "archive": "arXiv", "archive_location": "2505.15277", "author": [ { "literal": "Hyungjoo Chae" }, { "literal": "Sunghwan Kim" }, { "literal": "Junhee Cho" }, { "literal": "Seungone Kim" }, { "literal": "Seungjun Moon" }, { "literal": "Gyeom Hwangbo" }, { "literal": "Dongha Lim" }, { "literal": "Minjin Kim" }, { "literal": "Yeonjun Hwang" }, { "literal": "Minju Gwak" }, { "literal": "Dongwook Choi" }, { "literal": "Minseok Kang" }, { "literal": "Gwanhoon Im" }, { "literal": "ByeongUng Cho" }, { "literal": "Hyojun Kim" }, { "literal": "Jun Hee Han" }, { "literal": "Taeyoon Kwon" }, { "literal": "Minju Kim" }, { "literal": "Beong-woo Kwak" }, { "literal": "Dongjin Kang" }, { "literal": "Jinyoung Yeo" } ], "citation-key": "arxiv_2505_15277", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "440abdc75c0a51478cfedc6ee0a9196ccff641ec5a23849ba56be43448bab15f", "submitted_at": "2025-05-21T08:56:55Z", "updated_at": "2025-11-25T21:34:57Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2505.15277v2" }, "canonical_source_url": "https://arxiv.org/abs/2505.15277", "catalog_id": "arxiv:2505.15277", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-21", "identifiers": { "arxiv": "2505.15277" }, "record_updated_at": "2025-11-25" }, "genre": "preprint", "id": "arxiv:2505.15277", "issued": { "date-parts": [ [ 2025, 5, 21 ] ] }, "note": "First published: 2025-05-21; Recorded arXiv version: v2; Recorded version updated: 2025-11-25T21:34:57Z.", "title": "Web-Shepherd: Advancing PRMs for Reinforcing Web Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2505.16827v1", "archive": "arXiv", "archive_location": "2505.16827", "author": [ { "literal": "Bin Xie" }, { "literal": "Rui Shao" }, { "literal": "Gongwei Chen" }, { "literal": "Kaiwen Zhou" }, { "literal": "Yinchuan Li" }, { "literal": "Jie Liu" }, { "literal": "Min Zhang" }, { "literal": "Liqiang Nie" } ], "citation-key": "arxiv_2505_16827", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "641001c49fccac1e1c0659fe765eba5a30cefd2a7ff5d00c821f79092c45a1df", "submitted_at": "2025-05-22T16:01:06Z", "updated_at": "2025-05-22T16:01:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.16827v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.16827", "catalog_id": "arxiv:2505.16827", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2025-05-22", "identifiers": { "arxiv": "2505.16827" }, "publication": { "authors": [ "Bin Xie", "Rui Shao", "Gongwei Chen", "Kaiwen Zhou", "Yinchuan Li", "Jie Liu", "Min Zhang", "Liqiang Nie" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.acl-long.282", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.282/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "5650-5667", "pdf_url": "https://aclanthology.org/2025.acl-long.282.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.282/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-05-22" }, "genre": "preprint", "id": "arxiv:2505.16827", "issued": { "date-parts": [ [ 2025, 5, 22 ] ] }, "note": "First published: 2025-05-22; Recorded arXiv version: v1; Recorded version updated: 2025-05-22T16:01:06Z.", "title": "GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.18121v1", "archive": "arXiv", "archive_location": "2505.18121", "author": [ { "literal": "Danyang Zhang" }, { "literal": "Situo Zhang" }, { "literal": "Ziyue Yang" }, { "literal": "Zichen Zhu" }, { "literal": "Zihan Zhao" }, { "literal": "Ruisheng Cao" }, { "literal": "Lu Chen" }, { "literal": "Kai Yu" } ], "citation-key": "arxiv_2505_18121", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "40cbdc37216c58acd1b7523c48ad735df9bde485405a4e7b439aec85730c5bc0", "submitted_at": "2025-05-23T17:23:11Z", "updated_at": "2025-05-23T17:23:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.18121v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.18121", "catalog_id": "arxiv:2505.18121", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-23", "identifiers": { "arxiv": "2505.18121" }, "record_updated_at": "2025-05-23" }, "genre": "preprint", "id": "arxiv:2505.18121", "issued": { "date-parts": [ [ 2025, 5, 23 ] ] }, "note": "First published: 2025-05-23; Recorded arXiv version: v1; Recorded version updated: 2025-05-23T17:23:11Z.", "title": "ProgRM: Build Better GUI Agents with Progress Rewards", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.19095v1", "archive": "arXiv", "archive_location": "2505.19095", "author": [ { "literal": "Runliang Niu" }, { "literal": "Jinglong Ji" }, { "literal": "Yi Chang" }, { "literal": "Qi Wang" } ], "citation-key": "arxiv_2505_19095", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bb782466eccc7a271c89a4161c7b142f93f8f0d585cad39a1ccad048cf514426", "submitted_at": "2025-05-25T11:13:03Z", "updated_at": "2025-05-25T11:13:03Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.19095v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.19095", "catalog_id": "arxiv:2505.19095", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-25", "identifiers": { "arxiv": "2505.19095" }, "record_updated_at": "2025-05-25" }, "genre": "preprint", "id": "arxiv:2505.19095", "issued": { "date-parts": [ [ 2025, 5, 25 ] ] }, "note": "First published: 2025-05-25; Recorded arXiv version: v1; Recorded version updated: 2025-05-25T11:13:03Z.", "title": "ScreenExplorer: Training a Vision-Language Model for Diverse Exploration in Open GUI World", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.20013v2", "archive": "arXiv", "archive_location": "2505.20013", "author": [ { "literal": "Minda Hu" }, { "literal": "Tianqing Fang" }, { "literal": "Jianshu Zhang" }, { "literal": "Junyu Ma" }, { "literal": "Zhisong Zhang" }, { "literal": "Jingyan Zhou" }, { "literal": "Hongming Zhang" }, { "literal": "Haitao Mi" }, { "literal": "Dong Yu" }, { "literal": "Irwin King" } ], "citation-key": "arxiv_2505_20013", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "171071f26a6dc8b9c8851d2f11d60b113983191c905631e431f352711e0d0e26", "submitted_at": "2025-05-26T14:03:37Z", "updated_at": "2025-09-18T11:32:15Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2505.20013v2" }, "canonical_source_url": "https://arxiv.org/abs/2505.20013", "catalog_id": "arxiv:2505.20013", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-26", "identifiers": { "arxiv": "2505.20013" }, "record_updated_at": "2025-09-18" }, "genre": "preprint", "id": "arxiv:2505.20013", "issued": { "date-parts": [ [ 2025, 5, 26 ] ] }, "note": "First published: 2025-05-26; Recorded arXiv version: v2; Recorded version updated: 2025-09-18T11:32:15Z.", "title": "WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2505.20660v1", "archive": "arXiv", "archive_location": "2505.20660", "author": [ { "literal": "Qinzhuo Wu" }, { "literal": "Pengzhi Gao" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" } ], "citation-key": "arxiv_2505_20660", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d2d51388193e19501b580740969a6e08661c6e0a2cf09e2489c46fe4f19209cd", "submitted_at": "2025-05-27T03:09:06Z", "updated_at": "2025-05-27T03:09:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.20660v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.20660", "catalog_id": "arxiv:2505.20660", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-27", "identifiers": { "arxiv": "2505.20660" }, "record_updated_at": "2025-05-27" }, "genre": "preprint", "id": "arxiv:2505.20660", "issued": { "date-parts": [ [ 2025, 5, 27 ] ] }, "note": "First published: 2025-05-27; Recorded arXiv version: v1; Recorded version updated: 2025-05-27T03:09:06Z.", "title": "BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.21496v1", "archive": "arXiv", "archive_location": "2505.21496", "author": [ { "literal": "Han Xiao" }, { "literal": "Guozhi Wang" }, { "literal": "Yuxiang Chai" }, { "literal": "Zimu Lu" }, { "literal": "Weifeng Lin" }, { "literal": "Hao He" }, { "literal": "Lue Fan" }, { "literal": "Liuyang Bian" }, { "literal": "Rui Hu" }, { "literal": "Liang Liu" }, { "literal": "Shuai Ren" }, { "literal": "Yafei Wen" }, { "literal": "Xiaoxin Chen" }, { "literal": "Aojun Zhou" }, { "literal": "Hongsheng Li" } ], "citation-key": "arxiv_2505_21496", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f19671a527de76b702e68311656e42feea88249716f68911a41ec80be205e4c", "submitted_at": "2025-05-27T17:58:06Z", "updated_at": "2025-05-27T17:58:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.21496v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.21496", "catalog_id": "arxiv:2505.21496", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-27", "identifiers": { "arxiv": "2505.21496" }, "record_updated_at": "2025-05-27" }, "genre": "preprint", "id": "arxiv:2505.21496", "issued": { "date-parts": [ [ 2025, 5, 27 ] ] }, "note": "First published: 2025-05-27; Recorded arXiv version: v1; Recorded version updated: 2025-05-27T17:58:06Z.", "title": "UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.23762v1", "archive": "arXiv", "archive_location": "2505.23762", "author": [ { "literal": "Chenyu Yang" }, { "literal": "Shiqian Su" }, { "literal": "Shi Liu" }, { "literal": "Xuan Dong" }, { "literal": "Yue Yu" }, { "literal": "Weijie Su" }, { "literal": "Xuehui Wang" }, { "literal": "Zhaoyang Liu" }, { "literal": "Jinguo Zhu" }, { "literal": "Hao Li" }, { "literal": "Wenhai Wang" }, { "literal": "Yu Qiao" }, { "literal": "Xizhou Zhu" }, { "literal": "Jifeng Dai" } ], "citation-key": "arxiv_2505_23762", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "799e7b387f7d281f0aa9b182f37b215e3baca2041a0a0f6d414ddf1cec0de003", "submitted_at": "2025-05-29T17:59:51Z", "updated_at": "2025-05-29T17:59:51Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.23762v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.23762", "catalog_id": "arxiv:2505.23762", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-29", "identifiers": { "arxiv": "2505.23762" }, "record_updated_at": "2025-05-29" }, "genre": "preprint", "id": "arxiv:2505.23762", "issued": { "date-parts": [ [ 2025, 5, 29 ] ] }, "note": "First published: 2025-05-29; Recorded arXiv version: v1; Recorded version updated: 2025-05-29T17:59:51Z.", "title": "ZeroGUI: Automating Online GUI Learning at Zero Human Cost", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.24838v2", "archive": "arXiv", "archive_location": "2505.24838", "author": [ { "literal": "Brandon Man" }, { "literal": "Ghadi Nehme" }, { "literal": "Md Ferdous Alam" }, { "literal": "Faez Ahmed" } ], "citation-key": "arxiv_2505_24838", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f913b87f07fdad0e4c45264c58c8d9b9d13ca26695306d9e0644eb856f18ced7", "submitted_at": "2025-05-30T17:39:52Z", "updated_at": "2025-11-08T18:27:03Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2505.24838v2" }, "canonical_source_url": "https://arxiv.org/abs/2505.24838", "catalog_id": "arxiv:2505.24838", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-30", "identifiers": { "arxiv": "2505.24838" }, "record_updated_at": "2025-11-08" }, "genre": "preprint", "id": "arxiv:2505.24838", "issued": { "date-parts": [ [ 2025, 5, 30 ] ] }, "note": "First published: 2025-05-30; Recorded arXiv version: v2; Recorded version updated: 2025-11-08T18:27:03Z.", "title": "VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Video", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2506.02865v2", "archive": "arXiv", "archive_location": "2506.02865", "author": [ { "literal": "Mathieu Andreux" }, { "literal": "Breno Baldas Skuk" }, { "literal": "Hamza Benchekroun" }, { "literal": "Emilien Biré" }, { "literal": "Antoine Bonnet" }, { "literal": "Riaz Bordie" }, { "literal": "Nathan Bout" }, { "literal": "Matthias Brunel" }, { "literal": "Pierre-Louis Cedoz" }, { "literal": "Antoine Chassang" }, { "literal": "Mickaël Chen" }, { "literal": "Alexandra D. Constantinou" }, { "literal": "Antoine d'Andigné" }, { "literal": "Hubert de La Jonquière" }, { "literal": "Aurélien Delfosse" }, { "literal": "Ludovic Denoyer" }, { "literal": "Alexis Deprez" }, { "literal": "Augustin Derupti" }, { "literal": "Michael Eickenberg" }, { "literal": "Mathïs Federico" }, { "literal": "Charles Kantor" }, { "literal": "Xavier Koegler" }, { "literal": "Yann Labbé" }, { "literal": "Matthew C. H. Lee" }, { "literal": "Erwan Le Jumeau de Kergaradec" }, { "literal": "Amir Mahla" }, { "literal": "Avshalom Manevich" }, { "literal": "Adrien Maret" }, { "literal": "Charles Masson" }, { "literal": "Rafaël Maurin" }, { "literal": "Arturo Mena" }, { "literal": "Philippe Modard" }, { "literal": "Axel Moyal" }, { "literal": "Axel Nguyen Kerbel" }, { "literal": "Julien Revelle" }, { "literal": "Mats L. Richter" }, { "literal": "María Santos" }, { "literal": "Laurent Sifre" }, { "literal": "Maxime Theillard" }, { "literal": "Marc Thibault" }, { "literal": "Louis Thiry" }, { "literal": "Léo Tronchon" }, { "literal": "Nicolas Usunier" }, { "literal": "Tony Wu" } ], "citation-key": "arxiv_2506_02865", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "89c2d658e03204b56f6d273da9572820f9a23ca359a441ea87baa451a93c5b58", "submitted_at": "2025-06-03T13:29:03Z", "updated_at": "2025-06-11T09:33:38Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2506.02865v2" }, "canonical_source_url": "https://arxiv.org/abs/2506.02865", "catalog_id": "arxiv:2506.02865", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-03", "identifiers": { "arxiv": "2506.02865" }, "record_updated_at": "2025-06-11" }, "genre": "preprint", "id": "arxiv:2506.02865", "issued": { "date-parts": [ [ 2025, 6, 3 ] ] }, "note": "First published: 2025-06-03; Recorded arXiv version: v2; Recorded version updated: 2025-06-11T09:33:38Z.", "title": "Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2506.03095v1", "archive": "arXiv", "archive_location": "2506.03095", "author": [ { "literal": "Man Luo" }, { "literal": "David Cobbley" }, { "literal": "Xin Su" }, { "literal": "Shachar Rosenman" }, { "literal": "Vasudev Lal" }, { "literal": "Shao-Yen Tseng" }, { "literal": "Phillip Howard" } ], "citation-key": "arxiv_2506_03095", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "068eae2cab9899967850f21616a701f3eeb258b9654c83d34f68be266e48854e", "submitted_at": "2025-06-03T17:27:04Z", "updated_at": "2025-06-03T17:27:04Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2506.03095v1" }, "canonical_source_url": "https://arxiv.org/abs/2506.03095", "catalog_id": "arxiv:2506.03095", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-03", "identifiers": { "arxiv": "2506.03095" }, "record_updated_at": "2025-06-03" }, "genre": "preprint", "id": "arxiv:2506.03095", "issued": { "date-parts": [ [ 2025, 6, 3 ] ] }, "note": "First published: 2025-06-03; Recorded arXiv version: v1; Recorded version updated: 2025-06-03T17:27:04Z.", "title": "DPO Learning with LLMs-Judge Signal for Computer Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2506.03533v2", "archive": "arXiv", "archive_location": "2506.03533", "author": [ { "literal": "Apurva Gandhi" }, { "literal": "Graham Neubig" } ], "citation-key": "arxiv_2506_03533", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2bccee69e390b5170ff264e689c209d13317e7d3be9b37e6d3fbed0e0d089943", "submitted_at": "2025-06-04T03:27:56Z", "updated_at": "2026-03-02T22:31:00Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2506.03533v2" }, "canonical_source_url": "https://arxiv.org/abs/2506.03533", "catalog_id": "arxiv:2506.03533", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-04", "identifiers": { "arxiv": "2506.03533" }, "record_updated_at": "2026-03-02" }, "genre": "preprint", "id": "arxiv:2506.03533", "issued": { "date-parts": [ [ 2025, 6, 4 ] ] }, "note": "First published: 2025-06-04; Recorded arXiv version: v2; Recorded version updated: 2026-03-02T22:31:00Z.", "title": "Go-Browse: Training Web Agents with Structured Exploration", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2506.08012v1", "archive": "arXiv", "archive_location": "2506.08012", "author": [ { "literal": "Penghao Wu" }, { "literal": "Shengnan Ma" }, { "literal": "Bo Wang" }, { "literal": "Jiaheng Yu" }, { "literal": "Lewei Lu" }, { "literal": "Ziwei Liu" } ], "citation-key": "arxiv_2506_08012", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ce3b7d2c25b5a99f110f00be7389d4230d625ac1f7f33d5ab81f3d6f441f3610", "submitted_at": "2025-06-09T17:59:57Z", "updated_at": "2025-06-09T17:59:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2506.08012v1" }, "canonical_source_url": "https://arxiv.org/abs/2506.08012", "catalog_id": "arxiv:2506.08012", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-09", "identifiers": { "arxiv": "2506.08012" }, "record_updated_at": "2025-06-09" }, "genre": "preprint", "id": "arxiv:2506.08012", "issued": { "date-parts": [ [ 2025, 6, 9 ] ] }, "note": "First published: 2025-06-09; Recorded arXiv version: v1; Recorded version updated: 2025-06-09T17:59:57Z.", "title": "GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2506.11127v3", "archive": "arXiv", "archive_location": "2506.11127", "author": [ { "literal": "Wenkang Han" }, { "literal": "Zhixiong Zeng" }, { "literal": "Jing Huang" }, { "literal": "Shu Jiang" }, { "literal": "Liming Zheng" }, { "literal": "Longrong Yang" }, { "literal": "Haibo Qiu" }, { "literal": "Chang Yao" }, { "literal": "Jingyuan Chen" }, { "literal": "Lin Ma" } ], "citation-key": "arxiv_2506_11127", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3cce7c2e1623ec841e8afed03c2e8e0c6f969f3dd05d53ddc4ef11e74310c21c", "submitted_at": "2025-06-10T12:16:27Z", "updated_at": "2025-11-26T07:48:14Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2506.11127v3" }, "canonical_source_url": "https://arxiv.org/abs/2506.11127", "catalog_id": "arxiv:2506.11127", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-10", "identifiers": { "arxiv": "2506.11127" }, "record_updated_at": "2025-11-26" }, "genre": "preprint", "id": "arxiv:2506.11127", "issued": { "date-parts": [ [ 2025, 6, 10 ] ] }, "note": "First published: 2025-06-10; Recorded arXiv version: v3; Recorded version updated: 2025-11-26T07:48:14Z.", "title": "UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2506.14205v2", "archive": "arXiv", "archive_location": "2506.14205", "author": [ { "literal": "Jingxu Xie" }, { "literal": "Dylan Xu" }, { "literal": "Xuandong Zhao" }, { "literal": "Dawn Song" } ], "citation-key": "arxiv_2506_14205", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ae36b271f9b4799093831cabee772845edfaeca97107414e424e170ccf89904d", "submitted_at": "2025-06-17T05:46:52Z", "updated_at": "2026-03-02T00:51:36Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2506.14205v2" }, "canonical_source_url": "https://arxiv.org/abs/2506.14205", "catalog_id": "arxiv:2506.14205", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-17", "identifiers": { "arxiv": "2506.14205" }, "record_updated_at": "2026-03-02" }, "genre": "preprint", "id": "arxiv:2506.14205", "issued": { "date-parts": [ [ 2025, 6, 17 ] ] }, "note": "First published: 2025-06-17; Recorded arXiv version: v2; Recorded version updated: 2026-03-02T00:51:36Z.", "title": "AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2506.14477v1", "archive": "arXiv", "archive_location": "2506.14477", "author": [ { "literal": "Jingqi Yang" }, { "literal": "Zhilong Song" }, { "literal": "Jiawei Chen" }, { "literal": "Mingli Song" }, { "literal": "Sheng Zhou" }, { "literal": "linjun sun" }, { "literal": "Xiaogang Ouyang" }, { "literal": "Chun Chen" }, { "literal": "Can Wang" } ], "citation-key": "arxiv_2506_14477", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f9e64118f03c2a9f3f55e35f79c38835f1eb823265c83c933fdceca2610b9904", "submitted_at": "2025-06-17T12:50:35Z", "updated_at": "2025-06-17T12:50:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2506.14477v1" }, "canonical_source_url": "https://arxiv.org/abs/2506.14477", "catalog_id": "arxiv:2506.14477", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-17", "identifiers": { "arxiv": "2506.14477" }, "record_updated_at": "2025-06-17" }, "genre": "preprint", "id": "arxiv:2506.14477", "issued": { "date-parts": [ [ 2025, 6, 17 ] ] }, "note": "First published: 2025-06-17; Recorded arXiv version: v1; Recorded version updated: 2025-06-17T12:50:35Z.", "title": "GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2506.18158v1", "archive": "arXiv", "archive_location": "2506.18158", "author": [ { "literal": "Xinzge Gao" }, { "literal": "Chuanrui Hu" }, { "literal": "Bin Chen" }, { "literal": "Teng Li" } ], "citation-key": "arxiv_2506_18158", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aaa62e24a7a269fea49471f17028a3d5d8068d934e450f53bc002ae80fb7cb03", "submitted_at": "2025-06-22T20:17:46Z", "updated_at": "2025-06-22T20:17:46Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2506.18158v1" }, "canonical_source_url": "https://arxiv.org/abs/2506.18158", "catalog_id": "arxiv:2506.18158", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-22", "identifiers": { "arxiv": "2506.18158" }, "record_updated_at": "2025-06-22" }, "genre": "preprint", "id": "arxiv:2506.18158", "issued": { "date-parts": [ [ 2025, 6, 22 ] ] }, "note": "First published: 2025-06-22; Recorded arXiv version: v1; Recorded version updated: 2025-06-22T20:17:46Z.", "title": "Chain-of-Memory: Enhancing GUI Agents for Cross-Application Navigation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2506.23491v3", "archive": "arXiv", "archive_location": "2506.23491", "author": [ { "literal": "ZongHan Hsieh" }, { "literal": "Tzer-Jen Wei" }, { "literal": "ShengJing Yang" } ], "citation-key": "arxiv_2506_23491", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bb3678b0d0e645a87ce9392b606c1d67dcbc40656880c57d1cbb8ddd8ede7ea1", "submitted_at": "2025-06-30T03:33:02Z", "updated_at": "2025-07-18T06:03:26Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2506.23491v3" }, "canonical_source_url": "https://arxiv.org/abs/2506.23491", "catalog_id": "arxiv:2506.23491", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-30", "identifiers": { "arxiv": "2506.23491" }, "record_updated_at": "2025-07-18" }, "genre": "preprint", "id": "arxiv:2506.23491", "issued": { "date-parts": [ [ 2025, 6, 30 ] ] }, "note": "First published: 2025-06-30; Recorded arXiv version: v3; Recorded version updated: 2025-07-18T06:03:26Z.", "title": "ZonUI-3B: A Lightweight Vision-Language Model for Cross-Resolution GUI Grounding", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2507.05720v1", "archive": "arXiv", "archive_location": "2507.05720", "author": [ { "literal": "Yucheng Shi" }, { "literal": "Wenhao Yu" }, { "literal": "Zaitang Li" }, { "literal": "Yonglin Wang" }, { "literal": "Hongming Zhang" }, { "literal": "Ninghao Liu" }, { "literal": "Haitao Mi" }, { "literal": "Dong Yu" } ], "citation-key": "arxiv_2507_05720", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "45d36dd32b30bf4faee6d9a72e3cdfe91edff465bbd886bdfc3c27c3da475b82", "submitted_at": "2025-07-08T07:07:53Z", "updated_at": "2025-07-08T07:07:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2507.05720v1" }, "canonical_source_url": "https://arxiv.org/abs/2507.05720", "catalog_id": "arxiv:2507.05720", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-07-08", "identifiers": { "arxiv": "2507.05720" }, "record_updated_at": "2025-07-08" }, "genre": "preprint", "id": "arxiv:2507.05720", "issued": { "date-parts": [ [ 2025, 7, 8 ] ] }, "note": "First published: 2025-07-08; Recorded arXiv version: v1; Recorded version updated: 2025-07-08T07:07:53Z.", "title": "MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2507.21071v2", "archive": "arXiv", "archive_location": "2507.21071", "author": [ { "literal": "Qinglong Yang" }, { "literal": "Haoming Li" }, { "literal": "Haotian Zhao" }, { "literal": "Xiaokai Yan" }, { "literal": "Jingtao Ding" }, { "literal": "Fengli Xu" }, { "literal": "Yong Li" } ], "citation-key": "arxiv_2507_21071", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "947c85efc189635a118b823b8ca0787ff6b1c922d1af8b21a8686b7df9a27cf8", "submitted_at": "2025-06-09T06:38:41Z", "updated_at": "2026-03-16T09:14:01Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2507.21071v2" }, "canonical_source_url": "https://arxiv.org/abs/2507.21071", "catalog_id": "arxiv:2507.21071", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-09", "identifiers": { "arxiv": "2507.21071" }, "record_updated_at": "2026-03-16" }, "genre": "preprint", "id": "arxiv:2507.21071", "issued": { "date-parts": [ [ 2025, 6, 9 ] ] }, "note": "First published: 2025-06-09; Recorded arXiv version: v2; Recorded version updated: 2026-03-16T09:14:01Z.", "title": "FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2508.01858v3", "archive": "arXiv", "archive_location": "2508.01858", "author": [ { "literal": "Yuhan Guo" }, { "literal": "Cong Guo" }, { "literal": "Aiwen Sun" }, { "literal": "Hongliang He" }, { "literal": "Xinyu Yang" }, { "literal": "Yue Lu" }, { "literal": "Yingji Zhang" }, { "literal": "Xuntao Guo" }, { "literal": "Dong Zhang" }, { "literal": "Jianzhuang Liu" }, { "literal": "Jiang Duan" }, { "literal": "Yijia Xiao" }, { "literal": "Liangjian Wen" }, { "literal": "Hai-Ming Xu" }, { "literal": "Yong Dai" } ], "citation-key": "arxiv_2508_01858", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7406b48ed9826d51215d955c31c3c67cd2ce9e08bf9a93a55ac4e85a546315f1", "submitted_at": "2025-08-03T17:17:52Z", "updated_at": "2026-07-05T06:17:25Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2508.01858v3" }, "canonical_source_url": "https://arxiv.org/abs/2508.01858", "catalog_id": "arxiv:2508.01858", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-03", "identifiers": { "arxiv": "2508.01858" }, "record_updated_at": "2026-07-05" }, "genre": "preprint", "id": "arxiv:2508.01858", "issued": { "date-parts": [ [ 2025, 8, 3 ] ] }, "note": "First published: 2025-08-03; Recorded arXiv version: v3; Recorded version updated: 2026-07-05T06:17:25Z.", "title": "Web-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web Agents", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2508.02046v4", "archive": "arXiv", "archive_location": "2508.02046", "author": [ { "literal": "Zhihao Luo" }, { "literal": "Wentao Yan" }, { "literal": "Jingyu Gong" }, { "literal": "Min Wang" }, { "literal": "Zhizhong Zhang" }, { "literal": "Xuhong Wang" }, { "literal": "Yuan Xie" }, { "literal": "Xin Tan" } ], "citation-key": "arxiv_2508_02046", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e892ab93511f4164f37ef79ac0473e3c1eed7d6ec11fb6c8ec82092f26c5ca68", "submitted_at": "2025-08-04T04:28:18Z", "updated_at": "2026-05-02T12:32:44Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2508.02046v4" }, "canonical_source_url": "https://arxiv.org/abs/2508.02046", "catalog_id": "arxiv:2508.02046", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-04", "identifiers": { "arxiv": "2508.02046" }, "record_updated_at": "2026-05-02" }, "genre": "preprint", "id": "arxiv:2508.02046", "issued": { "date-parts": [ [ 2025, 8, 4 ] ] }, "note": "First published: 2025-08-04; Recorded arXiv version: v4; Recorded version updated: 2026-05-02T12:32:44Z.", "title": "NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2508.03700v5", "archive": "arXiv", "archive_location": "2508.03700", "author": [ { "literal": "Liujian Tang" }, { "literal": "Shaokang Dong" }, { "literal": "Yijia Huang" }, { "literal": "Minqi Xiang" }, { "literal": "Hongtao Ruan" }, { "literal": "Bin Wang" }, { "literal": "Shuo Li" }, { "literal": "Zhiheng Xi" }, { "literal": "Zhihui Cao" }, { "literal": "Hailiang Pang" }, { "literal": "Heng Kong" }, { "literal": "He Yang" }, { "literal": "Mingxu Chai" }, { "literal": "Zhilin Gao" }, { "literal": "Xingyu Liu" }, { "literal": "Yingnan Fu" }, { "literal": "Jiaming Liu" }, { "literal": "Xuanjing Huang" }, { "literal": "Yu-Gang Jiang" }, { "literal": "Tao Gui" }, { "literal": "Qi Zhang" }, { "literal": "Kang Wang" }, { "literal": "Yunke Zhang" }, { "literal": "Yuran Wang" } ], "citation-key": "arxiv_2508_03700", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d5175e5ed0061660fa950512300daa878eb90e5c98bdac8f80d478414b0a2931", "submitted_at": "2025-07-19T12:33:43Z", "updated_at": "2025-09-11T14:28:11Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2508.03700v5" }, "canonical_source_url": "https://arxiv.org/abs/2508.03700", "catalog_id": "arxiv:2508.03700", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-07-19", "identifiers": { "arxiv": "2508.03700" }, "record_updated_at": "2025-09-11" }, "genre": "preprint", "id": "arxiv:2508.03700", "issued": { "date-parts": [ [ 2025, 7, 19 ] ] }, "note": "First published: 2025-07-19; Recorded arXiv version: v5; Recorded version updated: 2025-09-11T14:28:11Z.", "title": "MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning", "type": "article", "version": "5" }, { "URL": "https://arxiv.org/abs/2508.04037v2", "archive": "arXiv", "archive_location": "2508.04037", "author": [ { "literal": "Yuhao Cheng" }, { "literal": "Liang Tang" }, { "literal": "Shuxian Li" }, { "literal": "Yukang Huo" }, { "literal": "Tiaonan Duan" }, { "literal": "Kaer Huang" }, { "literal": "Yanzhe Jing" }, { "literal": "Yiqiang Yan" } ], "citation-key": "arxiv_2508_04037", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d54ad74695a60cb040d88fcb85549912d7d4ecf6ca2ed78e636d05f8f17d1795", "submitted_at": "2025-08-06T02:57:22Z", "updated_at": "2026-01-22T05:22:03Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.04037v2" }, "canonical_source_url": "https://arxiv.org/abs/2508.04037", "catalog_id": "arxiv:2508.04037", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-06", "identifiers": { "arxiv": "2508.04037" }, "record_updated_at": "2026-01-22" }, "genre": "preprint", "id": "arxiv:2508.04037", "issued": { "date-parts": [ [ 2025, 8, 6 ] ] }, "note": "First published: 2025-08-06; Recorded arXiv version: v2; Recorded version updated: 2026-01-22T05:22:03Z.", "title": "Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agent", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2508.04700v2", "archive": "arXiv", "archive_location": "2508.04700", "author": [ { "literal": "Zeyi Sun" }, { "literal": "Ziyu Liu" }, { "literal": "Yuhang Zang" }, { "literal": "Yuhang Cao" }, { "literal": "Xiaoyi Dong" }, { "literal": "Tong Wu" }, { "literal": "Dahua Lin" }, { "literal": "Jiaqi Wang" } ], "citation-key": "arxiv_2508_04700", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "268c38e6f11f11771a1251fc522112ff052557b5753dff6cadf2ba49c0ec04b2", "submitted_at": "2025-08-06T17:58:46Z", "updated_at": "2025-08-12T15:11:53Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.04700v2" }, "canonical_source_url": "https://arxiv.org/abs/2508.04700", "catalog_id": "arxiv:2508.04700", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-06", "identifiers": { "arxiv": "2508.04700" }, "record_updated_at": "2025-08-12" }, "genre": "preprint", "id": "arxiv:2508.04700", "issued": { "date-parts": [ [ 2025, 8, 6 ] ] }, "note": "First published: 2025-08-06; Recorded arXiv version: v2; Recorded version updated: 2025-08-12T15:11:53Z.", "title": "SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2508.09123v3", "archive": "arXiv", "archive_location": "2508.09123", "author": [ { "literal": "Xinyuan Wang" }, { "literal": "Bowen Wang" }, { "literal": "Dunjie Lu" }, { "literal": "Junlin Yang" }, { "literal": "Tianbao Xie" }, { "literal": "Junli Wang" }, { "literal": "Jiaqi Deng" }, { "literal": "Xiaole Guo" }, { "literal": "Yiheng Xu" }, { "literal": "Chen Henry Wu" }, { "literal": "Zhennan Shen" }, { "literal": "Zhuokai Li" }, { "literal": "Ryan Li" }, { "literal": "Xiaochuan Li" }, { "literal": "Junda Chen" }, { "literal": "Boyuan Zheng" }, { "literal": "Peihang Li" }, { "literal": "Fangyu Lei" }, { "literal": "Ruisheng Cao" }, { "literal": "Yeqiao Fu" }, { "literal": "Dongchan Shin" }, { "literal": "Martin Shin" }, { "literal": "Jiarui Hu" }, { "literal": "Yuyan Wang" }, { "literal": "Jixuan Chen" }, { "literal": "Yuxiao Ye" }, { "literal": "Danyang Zhang" }, { "literal": "Dikang Du" }, { "literal": "Hao Hu" }, { "literal": "Huarong Chen" }, { "literal": "Zaida Zhou" }, { "literal": "Haotian Yao" }, { "literal": "Ziwei Chen" }, { "literal": "Qizheng Gu" }, { "literal": "Yipu Wang" }, { "literal": "Heng Wang" }, { "literal": "Diyi Yang" }, { "literal": "Victor Zhong" }, { "literal": "Flood Sung" }, { "literal": "Y. Charles" }, { "literal": "Zhilin Yang" }, { "literal": "Tao Yu" } ], "citation-key": "arxiv_2508_09123", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "40e46f27128d066358fcee6279b26bb2b708dacaf1f7b5794b755520fe892243", "submitted_at": "2025-08-12T17:52:32Z", "updated_at": "2025-10-04T17:38:02Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2508.09123v3" }, "canonical_source_url": "https://arxiv.org/abs/2508.09123", "catalog_id": "arxiv:2508.09123", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-12", "identifiers": { "arxiv": "2508.09123" }, "record_updated_at": "2025-10-04" }, "genre": "preprint", "id": "arxiv:2508.09123", "issued": { "date-parts": [ [ 2025, 8, 12 ] ] }, "note": "First published: 2025-08-12; Recorded arXiv version: v3; Recorded version updated: 2025-10-04T17:38:02Z.", "title": "OpenCUA: Open Foundations for Computer-Use Agents", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2508.15144v2", "archive": "arXiv", "archive_location": "2508.15144", "author": [ { "literal": "Jiabo Ye" }, { "literal": "Xi Zhang" }, { "literal": "Haiyang Xu" }, { "literal": "Haowei Liu" }, { "literal": "Junyang Wang" }, { "literal": "Zhaoqing Zhu" }, { "literal": "Ziwei Zheng" }, { "literal": "Feiyu Gao" }, { "literal": "Junjie Cao" }, { "literal": "Zhengxi Lu" }, { "literal": "Jitong Liao" }, { "literal": "Qi Zheng" }, { "literal": "Fei Huang" }, { "literal": "Jingren Zhou" }, { "literal": "Ming Yan" } ], "citation-key": "arxiv_2508_15144", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "629421d60bb8beeba3f087854ebaddc5461f9af0e5fb0bc572d0c20394ba9dcd", "submitted_at": "2025-08-21T00:39:12Z", "updated_at": "2025-09-01T05:38:34Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.15144v2" }, "canonical_source_url": "https://arxiv.org/abs/2508.15144", "catalog_id": "arxiv:2508.15144", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-21", "identifiers": { "arxiv": "2508.15144" }, "record_updated_at": "2025-09-01" }, "genre": "preprint", "id": "arxiv:2508.15144", "issued": { "date-parts": [ [ 2025, 8, 21 ] ] }, "note": "First published: 2025-08-21; Recorded arXiv version: v2; Recorded version updated: 2025-09-01T05:38:34Z.", "title": "Mobile-Agent-v3: Fundamental Agents for GUI Automation", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2508.15832v2", "archive": "arXiv", "archive_location": "2508.15832", "author": [ { "literal": "Xianren Zhang" }, { "literal": "Shreyas Prasad" }, { "literal": "Di Wang" }, { "literal": "Qiuhai Zeng" }, { "literal": "Suhang Wang" }, { "literal": "Wenbo Yan" }, { "literal": "Mat Hans" } ], "citation-key": "arxiv_2508_15832", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6c8336a707723227a9d651a3e9347e45907f28ed7421b577761ed57f7d70593d", "submitted_at": "2025-08-18T21:58:43Z", "updated_at": "2026-04-21T00:38:54Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.15832v2" }, "canonical_source_url": "https://arxiv.org/abs/2508.15832", "catalog_id": "arxiv:2508.15832", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-18", "identifiers": { "arxiv": "2508.15832" }, "record_updated_at": "2026-04-21" }, "genre": "preprint", "id": "arxiv:2508.15832", "issued": { "date-parts": [ [ 2025, 8, 18 ] ] }, "note": "First published: 2025-08-18; Recorded arXiv version: v2; Recorded version updated: 2026-04-21T00:38:54Z.", "title": "A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2508.21767v1", "archive": "arXiv", "archive_location": "2508.21767", "author": [ { "literal": "Zhixiong Zeng" }, { "literal": "Jing Huang" }, { "literal": "Liming Zheng" }, { "literal": "Wenkang Han" }, { "literal": "Yufeng Zhong" }, { "literal": "Lei Chen" }, { "literal": "Longrong Yang" }, { "literal": "Yingjie Chu" }, { "literal": "Yuzhi He" }, { "literal": "Lin Ma" } ], "citation-key": "arxiv_2508_21767", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b2a14819c7d7e8258947c9db8cc89012f4d133eaced4e4b904c3bfd1761181e5", "submitted_at": "2025-08-29T16:40:57Z", "updated_at": "2025-08-29T16:40:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2508.21767v1" }, "canonical_source_url": "https://arxiv.org/abs/2508.21767", "catalog_id": "arxiv:2508.21767", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-29", "identifiers": { "arxiv": "2508.21767" }, "record_updated_at": "2025-08-29" }, "genre": "preprint", "id": "arxiv:2508.21767", "issued": { "date-parts": [ [ 2025, 8, 29 ] ] }, "note": "First published: 2025-08-29; Recorded arXiv version: v1; Recorded version updated: 2025-08-29T16:40:57Z.", "title": "UItron: Foundational GUI Agent with Advanced Perception and Planning", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.00531v1", "archive": "arXiv", "archive_location": "2509.00531", "author": [ { "literal": "Cheng Zhang" }, { "literal": "Erhu Feng" }, { "literal": "Xi Zhao" }, { "literal": "Yisheng Zhao" }, { "literal": "Wangbo Gong" }, { "literal": "Jiahui Sun" }, { "literal": "Dong Du" }, { "literal": "Zhichao Hua" }, { "literal": "Yubin Xia" }, { "literal": "Haibo Chen" } ], "citation-key": "arxiv_2509_00531", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dbf26f28382245db085fd48f15e905bfa31f1c289a9a7f0799d35440069b442a", "submitted_at": "2025-08-30T15:24:47Z", "updated_at": "2025-08-30T15:24:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.00531v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.00531", "catalog_id": "arxiv:2509.00531", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-30", "identifiers": { "arxiv": "2509.00531" }, "record_updated_at": "2025-08-30" }, "genre": "preprint", "id": "arxiv:2509.00531", "issued": { "date-parts": [ [ 2025, 8, 30 ] ] }, "note": "First published: 2025-08-30; Recorded arXiv version: v1; Recorded version updated: 2025-08-30T15:24:47Z.", "title": "MobiAgent: A Systematic Framework for Customizable Mobile Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.02322v1", "archive": "arXiv", "archive_location": "2509.02322", "author": [ { "literal": "Longrong Yang" }, { "literal": "Zhixiong Zeng" }, { "literal": "Yufeng Zhong" }, { "literal": "Jing Huang" }, { "literal": "Liming Zheng" }, { "literal": "Lei Chen" }, { "literal": "Haibo Qiu" }, { "literal": "Zequn Qin" }, { "literal": "Lin Ma" }, { "literal": "Xi Li" } ], "citation-key": "arxiv_2509_02322", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "227630b3a257557262ed25eb21906a129eb35c6c5d2de7c5754f919dd281c4bd", "submitted_at": "2025-09-02T13:47:54Z", "updated_at": "2025-09-02T13:47:54Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.02322v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.02322", "catalog_id": "arxiv:2509.02322", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-02", "identifiers": { "arxiv": "2509.02322" }, "record_updated_at": "2025-09-02" }, "genre": "preprint", "id": "arxiv:2509.02322", "issued": { "date-parts": [ [ 2025, 9, 2 ] ] }, "note": "First published: 2025-09-02; Recorded arXiv version: v1; Recorded version updated: 2025-09-02T13:47:54Z.", "title": "OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.02544v2", "archive": "arXiv", "archive_location": "2509.02544", "author": [ { "literal": "Haoming Wang" }, { "literal": "Haoyang Zou" }, { "literal": "Huatong Song" }, { "literal": "Jiazhan Feng" }, { "literal": "Junjie Fang" }, { "literal": "Junting Lu" }, { "literal": "Longxiang Liu" }, { "literal": "Qinyu Luo" }, { "literal": "Shihao Liang" }, { "literal": "Shijue Huang" }, { "literal": "Wanjun Zhong" }, { "literal": "Yining Ye" }, { "literal": "Yujia Qin" }, { "literal": "Yuwen Xiong" }, { "literal": "Yuxin Song" }, { "literal": "Zhiyong Wu" }, { "literal": "Aoyan Li" }, { "literal": "Bo Li" }, { "literal": "Chen Dun" }, { "literal": "Chong Liu" }, { "literal": "Daoguang Zan" }, { "literal": "Fuxing Leng" }, { "literal": "Hanbin Wang" }, { "literal": "Hao Yu" }, { "literal": "Haobin Chen" }, { "literal": "Hongyi Guo" }, { "literal": "Jing Su" }, { "literal": "Jingjia Huang" }, { "literal": "Kai Shen" }, { "literal": "Kaiyu Shi" }, { "literal": "Lin Yan" }, { "literal": "Peiyao Zhao" }, { "literal": "Pengfei Liu" }, { "literal": "Qinghao Ye" }, { "literal": "Renjie Zheng" }, { "literal": "Shulin Xin" }, { "literal": "Wayne Xin Zhao" }, { "literal": "Wen Heng" }, { "literal": "Wenhao Huang" }, { "literal": "Wenqian Wang" }, { "literal": "Xiaobo Qin" }, { "literal": "Yi Lin" }, { "literal": "Youbin Wu" }, { "literal": "Zehui Chen" }, { "literal": "Zihao Wang" }, { "literal": "Baoquan Zhong" }, { "literal": "Xinchun Zhang" }, { "literal": "Xujing Li" }, { "literal": "Yuanfan Li" }, { "literal": "Zhongkai Zhao" }, { "literal": "Chengquan Jiang" }, { "literal": "Faming Wu" }, { "literal": "Haotian Zhou" }, { "literal": "Jinlin Pang" }, { "literal": "Li Han" }, { "literal": "Qi Liu" }, { "literal": "Qianli Ma" }, { "literal": "Siyao Liu" }, { "literal": "Songhua Cai" }, { "literal": "Wenqi Fu" }, { "literal": "Xin Liu" }, { "literal": "Yaohui Wang" }, { "literal": "Zhi Zhang" }, { "literal": "Bo Zhou" }, { "literal": "Guoliang Li" }, { "literal": "Jiajun Shi" }, { "literal": "Jiale Yang" }, { "literal": "Jie Tang" }, { "literal": "Li Li" }, { "literal": "Qihua Han" }, { "literal": "Taoran Lu" }, { "literal": "Woyu Lin" }, { "literal": "Xiaokang Tong" }, { "literal": "Xinyao Li" }, { "literal": "Yichi Zhang" }, { "literal": "Yu Miao" }, { "literal": "Zhengxuan Jiang" }, { "literal": "Zili Li" }, { "literal": "Ziyuan Zhao" }, { "literal": "Chenxin Li" }, { "literal": "Dehua Ma" }, { "literal": "Feng Lin" }, { "literal": "Ge Zhang" }, { "literal": "Haihua Yang" }, { "literal": "Hangyu Guo" }, { "literal": "Hongda Zhu" }, { "literal": "Jiaheng Liu" }, { "literal": "Junda Du" }, { "literal": "Kai Cai" }, { "literal": "Kuanye Li" }, { "literal": "Lichen Yuan" }, { "literal": "Meilan Han" }, { "literal": "Minchao Wang" }, { "literal": "Shuyue Guo" }, { "literal": "Tianhao Cheng" }, { "literal": "Xiaobo Ma" }, { "literal": "Xiaojun Xiao" }, { "literal": "Xiaolong Huang" }, { "literal": "Xinjie Chen" }, { "literal": "Yidi Du" }, { "literal": "Yilin Chen" }, { "literal": "Yiwen Wang" }, { "literal": "Zhaojian Li" }, { "literal": "Zhenzhu Yang" }, { "literal": "Zhiyuan Zeng" }, { "literal": "Chaolin Jin" }, { "literal": "Chen Li" }, { "literal": "Hao Chen" }, { "literal": "Haoli Chen" }, { "literal": "Jian Chen" }, { "literal": "Qinghao Zhao" }, { "literal": "Guang Shi" } ], "citation-key": "arxiv_2509_02544", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "800e417f4a2f720beb436ddd2e7bc60f0dd2483b44ac007a72a5eab2c6001ff8", "submitted_at": "2025-09-02T17:44:45Z", "updated_at": "2025-09-05T14:59:27Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.02544v2" }, "canonical_source_url": "https://arxiv.org/abs/2509.02544", "catalog_id": "arxiv:2509.02544", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-02", "identifiers": { "arxiv": "2509.02544" }, "record_updated_at": "2025-09-05" }, "genre": "preprint", "id": "arxiv:2509.02544", "issued": { "date-parts": [ [ 2025, 9, 2 ] ] }, "note": "First published: 2025-09-02; Recorded arXiv version: v2; Recorded version updated: 2025-09-05T14:59:27Z.", "title": "UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2509.04243v1", "archive": "arXiv", "archive_location": "2509.04243", "author": [ { "literal": "Wanfu Wang" }, { "literal": "Qipeng Huang" }, { "literal": "Guangquan Xue" }, { "literal": "Xiaobo Liang" }, { "literal": "Juntao Li" } ], "citation-key": "arxiv_2509_04243", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "875e2452985bae9e67d7071121ab13f5205307ecc30bf33f237048a44e75b3bc", "submitted_at": "2025-09-04T14:17:01Z", "updated_at": "2025-09-04T14:17:01Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.04243v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.04243", "catalog_id": "arxiv:2509.04243", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-04", "identifiers": { "arxiv": "2509.04243" }, "record_updated_at": "2025-09-04" }, "genre": "preprint", "id": "arxiv:2509.04243", "issued": { "date-parts": [ [ 2025, 9, 4 ] ] }, "note": "First published: 2025-09-04; Recorded arXiv version: v1; Recorded version updated: 2025-09-04T14:17:01Z.", "title": "Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.15221v2", "archive": "arXiv", "archive_location": "2509.15221", "author": [ { "literal": "Zhaoyang Liu" }, { "literal": "Jingjing Xie" }, { "literal": "Zichen Ding" }, { "literal": "Zehao Li" }, { "literal": "Bowen Yang" }, { "literal": "Zhenyu Wu" }, { "literal": "Xuehui Wang" }, { "literal": "Qiushi Sun" }, { "literal": "Shi Liu" }, { "literal": "Weiyun Wang" }, { "literal": "Shenglong Ye" }, { "literal": "Qingyun Li" }, { "literal": "Xuan Dong" }, { "literal": "Yue Yu" }, { "literal": "Chenyu Lu" }, { "literal": "YunXiang Mo" }, { "literal": "Yao Yan" }, { "literal": "Zeyue Tian" }, { "literal": "Xiao Zhang" }, { "literal": "Yuan Huang" }, { "literal": "Yiqian Liu" }, { "literal": "Weijie Su" }, { "literal": "Gen Luo" }, { "literal": "Xiangyu Yue" }, { "literal": "Biqing Qi" }, { "literal": "Kai Chen" }, { "literal": "Bowen Zhou" }, { "literal": "Yu Qiao" }, { "literal": "Qifeng Chen" }, { "literal": "Wenhai Wang" } ], "citation-key": "arxiv_2509_15221", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2509.15221", "catalog_id": "arxiv:2509.15221", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-18", "identifiers": { "arxiv": "2509.15221" }, "record_updated_at": "2025-09-19" }, "genre": "preprint", "id": "arxiv:2509.15221", "issued": { "date-parts": [ [ 2025, 9, 18 ] ] }, "note": "First published: 2025-09-18; Recorded arXiv version: v2; Recorded version updated: 2025-09-19T05:29:03Z.", "title": "ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2509.15566v4", "archive": "arXiv", "archive_location": "2509.15566", "author": [ { "literal": "Shaojie Zhang" }, { "literal": "Ruoceng Zhang" }, { "literal": "Pei Fu" }, { "literal": "Shaokang Wang" }, { "literal": "Jiahui Yang" }, { "literal": "Xin Du" }, { "literal": "Shiqi Cui" }, { "literal": "Bin Qin" }, { "literal": "Ying Huang" }, { "literal": "Zhenbo Luo" }, { "literal": "Jian Luan" } ], "citation-key": "arxiv_2509_15566", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d190eefae9309d87f4ea4780d3483ae0ebd834e0bf70e7f2af204c3788d87e7e", "submitted_at": "2025-09-19T04:03:44Z", "updated_at": "2025-10-27T11:34:58Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2509.15566v4" }, "canonical_source_url": "https://arxiv.org/abs/2509.15566", "catalog_id": "arxiv:2509.15566", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-19", "identifiers": { "arxiv": "2509.15566" }, "record_updated_at": "2025-10-27" }, "genre": "preprint", "id": "arxiv:2509.15566", "issued": { "date-parts": [ [ 2025, 9, 19 ] ] }, "note": "First published: 2025-09-19; Recorded arXiv version: v4; Recorded version updated: 2025-10-27T11:34:58Z.", "title": "BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2509.15738v1", "archive": "arXiv", "archive_location": "2509.15738", "author": [ { "literal": "Musen Lin" }, { "literal": "Minghao Liu" }, { "literal": "Taoran Lu" }, { "literal": "Lichen Yuan" }, { "literal": "Yiwei Liu" }, { "literal": "Haonan Xu" }, { "literal": "Yu Miao" }, { "literal": "Yuhao Chao" }, { "literal": "Zhaojian Li" } ], "citation-key": "arxiv_2509_15738", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "035048459d2b303721ef0738212829d1fa3314ccd0736b6649cc786c6e975ad4", "submitted_at": "2025-09-19T08:09:18Z", "updated_at": "2025-09-19T08:09:18Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.15738v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.15738", "catalog_id": "arxiv:2509.15738", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-19", "identifiers": { "arxiv": "2509.15738" }, "record_updated_at": "2025-09-19" }, "genre": "preprint", "id": "arxiv:2509.15738", "issued": { "date-parts": [ [ 2025, 9, 19 ] ] }, "note": "First published: 2025-09-19; Recorded arXiv version: v1; Recorded version updated: 2025-09-19T08:09:18Z.", "title": "GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.17328v1", "archive": "arXiv", "archive_location": "2509.17328", "author": [ { "literal": "Hongxin Li" }, { "literal": "Jingran Su" }, { "literal": "Jingfan Chen" }, { "literal": "Zheng Ju" }, { "literal": "Yuntao Chen" }, { "literal": "Qing Li" }, { "literal": "Zhaoxiang Zhang" } ], "citation-key": "arxiv_2509_17328", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "97b7c0690ba7deb7dbbdac6ac94dd82e3864c440cb4325bf143ad735919bb08b", "submitted_at": "2025-09-22T03:04:53Z", "updated_at": "2025-09-22T03:04:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.17328v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.17328", "catalog_id": "arxiv:2509.17328", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-22", "identifiers": { "arxiv": "2509.17328" }, "record_updated_at": "2025-09-22" }, "genre": "preprint", "id": "arxiv:2509.17328", "issued": { "date-parts": [ [ 2025, 9, 22 ] ] }, "note": "First published: 2025-09-22; Recorded arXiv version: v1; Recorded version updated: 2025-09-22T03:04:53Z.", "title": "UIPro: Unleashing Superior Interaction Capability For GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.17917v1", "archive": "arXiv", "archive_location": "2509.17917", "author": [ { "literal": "Junyu Lu" }, { "literal": "Songxin Zhang" }, { "literal": "Zejian Xie" }, { "literal": "Zhuoyang Song" }, { "literal": "Jiaxing Zhang" } ], "citation-key": "arxiv_2509_17917", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7b85c9bae829bad343dd6f57c866ea100859fa0ad67f5c1a3ac9b3e53d617486", "submitted_at": "2025-09-22T15:40:31Z", "updated_at": "2025-09-22T15:40:31Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.17917v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.17917", "catalog_id": "arxiv:2509.17917", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-22", "identifiers": { "arxiv": "2509.17917" }, "record_updated_at": "2025-09-22" }, "genre": "preprint", "id": "arxiv:2509.17917", "issued": { "date-parts": [ [ 2025, 9, 22 ] ] }, "note": "First published: 2025-09-22; Recorded arXiv version: v1; Recorded version updated: 2025-09-22T15:40:31Z.", "title": "Orcust: Stepwise-Feedback Reinforcement Learning for GUI Agent", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.21982v2", "archive": "arXiv", "archive_location": "2509.21982", "author": [ { "literal": "Renqi Chen" }, { "literal": "Zeyin Tao" }, { "literal": "Jianming Guo" }, { "literal": "Jingzhe Zhu" }, { "literal": "Yiheng Peng" }, { "literal": "Qingqing Sun" }, { "literal": "Tianyi Zhang" }, { "literal": "Shuai Chen" } ], "citation-key": "arxiv_2509_21982", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d23b9f33282f77b9d4965078ca993bcf21163dc1d3210aaa4e554d4fc12b37c5", "submitted_at": "2025-09-26T07:05:01Z", "updated_at": "2026-04-13T03:14:30Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.21982v2" }, "canonical_source_url": "https://arxiv.org/abs/2509.21982", "catalog_id": "arxiv:2509.21982", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-26", "identifiers": { "arxiv": "2509.21982" }, "record_updated_at": "2026-04-13" }, "genre": "preprint", "id": "arxiv:2509.21982", "issued": { "date-parts": [ [ 2025, 9, 26 ] ] }, "note": "First published: 2025-09-26; Recorded arXiv version: v2; Recorded version updated: 2026-04-13T03:14:30Z.", "title": "RISK: A Framework for GUI Agents in E-commerce Risk Management", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2509.23866v1", "archive": "arXiv", "archive_location": "2509.23866", "author": [ { "literal": "Pengxiang Li" }, { "literal": "Zechen Hu" }, { "literal": "Zirui Shang" }, { "literal": "Jingrong Wu" }, { "literal": "Yang Liu" }, { "literal": "Hui Liu" }, { "literal": "Zhi Gao" }, { "literal": "Chenrui Shi" }, { "literal": "Bofei Zhang" }, { "literal": "Zihao Zhang" }, { "literal": "Xiaochuan Shi" }, { "literal": "Zedong YU" }, { "literal": "Yuwei Wu" }, { "literal": "Xinxiao Wu" }, { "literal": "Yunde Jia" }, { "literal": "Liuyu Xiang" }, { "literal": "Zhaofeng He" }, { "literal": "Qing Li" } ], "citation-key": "arxiv_2509_23866", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a96e774920489ef366ad462972a938863a3e714672e9c1f4b784d57eee34c4ca", "submitted_at": "2025-09-28T13:19:20Z", "updated_at": "2025-09-28T13:19:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.23866v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.23866", "catalog_id": "arxiv:2509.23866", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-28", "identifiers": { "arxiv": "2509.23866" }, "record_updated_at": "2025-09-28" }, "genre": "preprint", "id": "arxiv:2509.23866", "issued": { "date-parts": [ [ 2025, 9, 28 ] ] }, "note": "First published: 2025-09-28; Recorded arXiv version: v1; Recorded version updated: 2025-09-28T13:19:20Z.", "title": "Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.25047v1", "archive": "arXiv", "archive_location": "2509.25047", "author": [ { "literal": "Ram Ramrakhya" }, { "literal": "Andrew Szot" }, { "literal": "Omar Attia" }, { "literal": "Yuhao Yang" }, { "literal": "Anh Nguyen" }, { "literal": "Bogdan Mazoure" }, { "literal": "Zhe Gan" }, { "literal": "Harsh Agrawal" }, { "literal": "Alexander Toshev" } ], "citation-key": "arxiv_2509_25047", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d41da9264d664abbeacccae889f9f14f403fc4edbd7453ed4ff276689592fe68", "submitted_at": "2025-09-29T17:00:02Z", "updated_at": "2025-09-29T17:00:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.25047v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.25047", "catalog_id": "arxiv:2509.25047", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-29", "identifiers": { "arxiv": "2509.25047" }, "record_updated_at": "2025-09-29" }, "genre": "preprint", "id": "arxiv:2509.25047", "issued": { "date-parts": [ [ 2025, 9, 29 ] ] }, "note": "First published: 2025-09-29; Recorded arXiv version: v1; Recorded version updated: 2025-09-29T17:00:02Z.", "title": "Scaling Synthetic Task Generation for Agents via Exploration", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2510.16051v2", "archive": "arXiv", "archive_location": "2510.16051", "author": [ { "literal": "Sofiya Garkot" }, { "literal": "Maksym Shamrai" }, { "literal": "Ivan Synytsia" }, { "literal": "Mariya Hirna" } ], "citation-key": "arxiv_2510_16051", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6e4377fd6b510455afa1eb04c64e8e0b551e89d3b54ce31f241f283233985e1c", "submitted_at": "2025-10-16T19:03:45Z", "updated_at": "2026-03-24T14:39:38Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.16051v2" }, "canonical_source_url": "https://arxiv.org/abs/2510.16051", "catalog_id": "arxiv:2510.16051", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-16", "identifiers": { "arxiv": "2510.16051" }, "record_updated_at": "2026-03-24" }, "genre": "preprint", "id": "arxiv:2510.16051", "issued": { "date-parts": [ [ 2025, 10, 16 ] ] }, "note": "First published: 2025-10-16; Recorded arXiv version: v2; Recorded version updated: 2026-03-24T14:39:38Z.", "title": "GUIrilla: A Scalable Framework for Automated Desktop UI Exploration", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2510.17790v3", "archive": "arXiv", "archive_location": "2510.17790", "author": [ { "literal": "Yuhao Yang" }, { "literal": "Zhen Yang" }, { "literal": "Zi-Yi Dou" }, { "literal": "Anh Nguyen" }, { "literal": "Keen You" }, { "literal": "Omar Attia" }, { "literal": "Andrew Szot" }, { "literal": "Michael Feng" }, { "literal": "Ram Ramrakhya" }, { "literal": "Alexander Toshev" }, { "literal": "Chao Huang" }, { "literal": "Yinfei Yang" }, { "literal": "Zhe Gan" } ], "citation-key": "arxiv_2510_17790", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "33569f6ccca9c7e2675796191124424e76636828179c300d35da01ad9ccef1ce", "submitted_at": "2025-10-20T17:48:26Z", "updated_at": "2026-05-26T11:29:37Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2510.17790v3" }, "canonical_source_url": "https://arxiv.org/abs/2510.17790", "catalog_id": "arxiv:2510.17790", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-20", "identifiers": { "arxiv": "2510.17790" }, "record_updated_at": "2026-05-26" }, "genre": "preprint", "id": "arxiv:2510.17790", "issued": { "date-parts": [ [ 2025, 10, 20 ] ] }, "note": "First published: 2025-10-20; Recorded arXiv version: v3; Recorded version updated: 2026-05-26T11:29:37Z.", "title": "UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2510.18488v1", "archive": "arXiv", "archive_location": "2510.18488", "author": [ { "literal": "Ho Fai Leung" }, { "literal": "Xiaoyan Xi" }, { "literal": "Fei Zuo" } ], "citation-key": "arxiv_2510_18488", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "33b21a63d51148f2b5c30478c302e3df9b92e03e2e106a1c68224f2c835a8608", "submitted_at": "2025-10-21T10:11:33Z", "updated_at": "2025-10-21T10:11:33Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.18488v1" }, "canonical_source_url": "https://arxiv.org/abs/2510.18488", "catalog_id": "arxiv:2510.18488", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-21", "identifiers": { "arxiv": "2510.18488" }, "record_updated_at": "2025-10-21" }, "genre": "preprint", "id": "arxiv:2510.18488", "issued": { "date-parts": [ [ 2025, 10, 21 ] ] }, "note": "First published: 2025-10-21; Recorded arXiv version: v1; Recorded version updated: 2025-10-21T10:11:33Z.", "title": "AndroidControl-Curated: Revealing the True Potential of GUI Agents through Benchmark Purification", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2510.19488v1", "archive": "arXiv", "archive_location": "2510.19488", "author": [ { "literal": "Dunjie Lu" }, { "literal": "Yiheng Xu" }, { "literal": "Junli Wang" }, { "literal": "Haoyuan Wu" }, { "literal": "Xinyuan Wang" }, { "literal": "Zekun Wang" }, { "literal": "Junlin Yang" }, { "literal": "Hongjin Su" }, { "literal": "Jixuan Chen" }, { "literal": "Junda Chen" }, { "literal": "Yuchen Mao" }, { "literal": "Jingren Zhou" }, { "literal": "Junyang Lin" }, { "literal": "Binyuan Hui" }, { "literal": "Tao Yu" } ], "citation-key": "arxiv_2510_19488", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ebb064e1a9c3e2255677d9b4cd9ce33d2a97dd26a379c321721d576e7c5d6399", "submitted_at": "2025-10-22T11:25:48Z", "updated_at": "2025-10-22T11:25:48Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.19488v1" }, "canonical_source_url": "https://arxiv.org/abs/2510.19488", "catalog_id": "arxiv:2510.19488", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-22", "identifiers": { "arxiv": "2510.19488" }, "record_updated_at": "2025-10-22" }, "genre": "preprint", "id": "arxiv:2510.19488", "issued": { "date-parts": [ [ 2025, 10, 22 ] ] }, "note": "First published: 2025-10-22; Recorded arXiv version: v1; Recorded version updated: 2025-10-22T11:25:48Z.", "title": "VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2511.04137v1", "archive": "arXiv", "archive_location": "2511.04137", "author": [ { "literal": "Yujian Liu" }, { "literal": "Ze Wang" }, { "literal": "Hao Chen" }, { "literal": "Ximeng Sun" }, { "literal": "Xiaodong Yu" }, { "literal": "Jialian Wu" }, { "literal": "Jiang Liu" }, { "literal": "Emad Barsoum" }, { "literal": "Zicheng Liu" }, { "literal": "Shiyu Chang" } ], "citation-key": "arxiv_2511_04137", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a91413c1e80869860d411402ab49f6e5968787b3bca83f0a9066a0e9c2f75d40", "submitted_at": "2025-11-06T07:29:02Z", "updated_at": "2025-11-06T07:29:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.04137v1" }, "canonical_source_url": "https://arxiv.org/abs/2511.04137", "catalog_id": "arxiv:2511.04137", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-06", "identifiers": { "arxiv": "2511.04137" }, "record_updated_at": "2025-11-06" }, "genre": "preprint", "id": "arxiv:2511.04137", "issued": { "date-parts": [ [ 2025, 11, 6 ] ] }, "note": "First published: 2025-11-06; Recorded arXiv version: v1; Recorded version updated: 2025-11-06T07:29:02Z.", "title": "Learning from Online Videos at Inference Time for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2511.04307v2", "archive": "arXiv", "archive_location": "2511.04307", "author": [ { "literal": "Jian Mu" }, { "literal": "Chaoyun Zhang" }, { "literal": "Chiming Ni" }, { "literal": "Lu Wang" }, { "literal": "Bo Qiao" }, { "literal": "Kartik Mathur" }, { "literal": "Qianhui Wu" }, { "literal": "Yuhang Xie" }, { "literal": "Xiaojun Ma" }, { "literal": "Mengyu Zhou" }, { "literal": "Si Qin" }, { "literal": "Liqun Li" }, { "literal": "Yu Kang" }, { "literal": "Minghua Ma" }, { "literal": "Qingwei Lin" }, { "literal": "Saravan Rajmohan" }, { "literal": "Dongmei Zhang" } ], "citation-key": "arxiv_2511_04307", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6b063a4d2b3a552aa05a153745978473a7d165f2c6b4b97e4c91eff11b7b0f80", "submitted_at": "2025-11-06T12:19:02Z", "updated_at": "2025-11-10T12:27:15Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2511.04307v2" }, "canonical_source_url": "https://arxiv.org/abs/2511.04307", "catalog_id": "arxiv:2511.04307", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-06", "identifiers": { "arxiv": "2511.04307" }, "record_updated_at": "2025-11-10" }, "genre": "preprint", "id": "arxiv:2511.04307", "issued": { "date-parts": [ [ 2025, 11, 6 ] ] }, "note": "First published: 2025-11-06; Recorded arXiv version: v2; Recorded version updated: 2025-11-10T12:27:15Z.", "title": "GUI-360$^\\circ$: A Comprehensive Dataset and Benchmark for Computer-Using Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2511.06101v3", "archive": "arXiv", "archive_location": "2511.06101", "author": [ { "literal": "Zhaoyang Wang" }, { "literal": "Yiming Liang" }, { "literal": "Xuchao Zhang" }, { "literal": "Qianhui Wu" }, { "literal": "Siwei Han" }, { "literal": "Anson Bastos" }, { "literal": "Rujia Wang" }, { "literal": "Chetan Bansal" }, { "literal": "Baolin Peng" }, { "literal": "Jianfeng Gao" }, { "literal": "Saravan Rajmohan" }, { "literal": "Huaxiu Yao" } ], "citation-key": "arxiv_2511_06101", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7420d51203de06ed3afe6f2695b8612ec36dc072765a4f2394f366f9e6bf8838", "submitted_at": "2025-11-08T18:45:33Z", "updated_at": "2026-04-13T06:03:02Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2511.06101v3" }, "canonical_source_url": "https://arxiv.org/abs/2511.06101", "catalog_id": "arxiv:2511.06101", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-08", "identifiers": { "arxiv": "2511.06101" }, "record_updated_at": "2026-04-13" }, "genre": "preprint", "id": "arxiv:2511.06101", "issued": { "date-parts": [ [ 2025, 11, 8 ] ] }, "note": "First published: 2025-11-08; Recorded arXiv version: v3; Recorded version updated: 2026-04-13T06:03:02Z.", "title": "SynthAgent: Adapting Web Agents with Synthetic Supervision", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2511.06417v1", "archive": "arXiv", "archive_location": "2511.06417", "author": [ { "literal": "Xiangwu Guo" }, { "literal": "Difei Gao" }, { "literal": "Mike Zheng Shou" } ], "citation-key": "arxiv_2511_06417", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8a5f43873a47e5b47250cedd3d860abe2dc5ec9b85fe657444bf2b7378f3e8f7", "submitted_at": "2025-11-09T15:13:45Z", "updated_at": "2025-11-09T15:13:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.06417v1" }, "canonical_source_url": "https://arxiv.org/abs/2511.06417", "catalog_id": "arxiv:2511.06417", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-09", "identifiers": { "arxiv": "2511.06417" }, "record_updated_at": "2025-11-09" }, "genre": "preprint", "id": "arxiv:2511.06417", "issued": { "date-parts": [ [ 2025, 11, 9 ] ] }, "note": "First published: 2025-11-09; Recorded arXiv version: v1; Recorded version updated: 2025-11-09T15:13:45Z.", "title": "AUTO-Explorer: Automated Data Collection for GUI Agent", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2511.07332v2", "archive": "arXiv", "archive_location": "2511.07332", "author": [ { "literal": "Aarash Feizi" }, { "literal": "Shravan Nayak" }, { "literal": "Xiangru Jian" }, { "literal": "Kevin Qinghong Lin" }, { "literal": "Kaixin Li" }, { "literal": "Rabiul Awal" }, { "literal": "Xing Han Lù" }, { "literal": "Johan Obando-Ceron" }, { "literal": "Juan A. Rodriguez" }, { "literal": "Nicolas Chapados" }, { "literal": "David Vazquez" }, { "literal": "Adriana Romero-Soriano" }, { "literal": "Reihaneh Rabbany" }, { "literal": "Perouz Taslakian" }, { "literal": "Christopher Pal" }, { "literal": "Spandana Gella" }, { "literal": "Sai Rajeswar" } ], "citation-key": "arxiv_2511_07332", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0f2b80f294ddf5e3331dcb47a836864032f88f2fdbe35588bfef000cd9ceddc8", "submitted_at": "2025-11-10T17:35:21Z", "updated_at": "2026-06-09T21:30:32Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2511.07332v2" }, "canonical_source_url": "https://arxiv.org/abs/2511.07332", "catalog_id": "arxiv:2511.07332", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-10", "identifiers": { "arxiv": "2511.07332" }, "record_updated_at": "2026-06-09" }, "genre": "preprint", "id": "arxiv:2511.07332", "issued": { "date-parts": [ [ 2025, 11, 10 ] ] }, "note": "First published: 2025-11-10; Recorded arXiv version: v2; Recorded version updated: 2026-06-09T21:30:32Z.", "title": "Grounding Computer Use Agents on Human Demonstrations", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2511.10705v1", "archive": "arXiv", "archive_location": "2511.10705", "author": [ { "literal": "Yuan Zhao" }, { "literal": "Hualei Zhu" }, { "literal": "Tingyu Jiang" }, { "literal": "Shen Li" }, { "literal": "Xiaohang Xu" }, { "literal": "Hao Henry Wang" } ], "citation-key": "arxiv_2511_10705", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "101d38ed439c41ebfa826e990697b502b9126728956295d25b0ea9d539ff23e3", "submitted_at": "2025-11-13T03:41:02Z", "updated_at": "2025-11-13T03:41:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.10705v1" }, "canonical_source_url": "https://arxiv.org/abs/2511.10705", "catalog_id": "arxiv:2511.10705", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-13", "identifiers": { "arxiv": "2511.10705" }, "record_updated_at": "2025-11-13" }, "genre": "preprint", "id": "arxiv:2511.10705", "issued": { "date-parts": [ [ 2025, 11, 13 ] ] }, "note": "First published: 2025-11-13; Recorded arXiv version: v1; Recorded version updated: 2025-11-13T03:41:02Z.", "title": "Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2511.11672v5", "archive": "arXiv", "archive_location": "2511.11672", "author": [ { "literal": "Zengyi Qin" }, { "literal": "Jinyuan Chen" }, { "literal": "Yunze Man" }, { "literal": "Shengcao Cao" }, { "literal": "Ziqi Pang" }, { "literal": "Zhuoyuan Wang" }, { "literal": "Han Fang" }, { "literal": "Ling Zhu" }, { "literal": "Zixin Xie" }, { "literal": "Zibu Wei" }, { "literal": "Tianshu Ran" }, { "literal": "Haoran Geng" }, { "literal": "Ray Pan" }, { "literal": "Qizhen Sun" }, { "literal": "Zachary Bright" }, { "literal": "Yuyang Cai" }, { "literal": "Chongye Yang" }, { "literal": "Jiace Zhao" }, { "literal": "Tianrui Liu" }, { "literal": "Han Cao" }, { "literal": "Yeyang Zhou" }, { "literal": "Rui Wang" }, { "literal": "Song Wang" }, { "literal": "Xiang Ren" }, { "literal": "Bo Zhang" }, { "literal": "Yutong Ban" }, { "literal": "Pieter Abbeel" }, { "literal": "Brian Anthony" } ], "citation-key": "arxiv_2511_11672", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "755d41575ae8ee5d07be0022c8f078c742da4628f12ecd1cad984269441021cf", "submitted_at": "2025-11-11T20:03:38Z", "updated_at": "2026-04-02T02:42:36Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2511.11672v5" }, "canonical_source_url": "https://arxiv.org/abs/2511.11672", "catalog_id": "arxiv:2511.11672", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-11", "identifiers": { "arxiv": "2511.11672" }, "record_updated_at": "2026-04-02" }, "genre": "preprint", "id": "arxiv:2511.11672", "issued": { "date-parts": [ [ 2025, 11, 11 ] ] }, "note": "First published: 2025-11-11; Recorded arXiv version: v5; Recorded version updated: 2026-04-02T02:42:36Z.", "title": "OSGym: Scalable OS Infra for Computer Use Agents", "type": "article", "version": "5" }, { "URL": "https://arxiv.org/abs/2511.19663v1", "archive": "arXiv", "archive_location": "2511.19663", "author": [ { "literal": "Ahmed Awadallah" }, { "literal": "Yash Lara" }, { "literal": "Raghav Magazine" }, { "literal": "Hussein Mozannar" }, { "literal": "Akshay Nambi" }, { "literal": "Yash Pandya" }, { "literal": "Aravind Rajeswaran" }, { "literal": "Corby Rosset" }, { "literal": "Alexey Taymanov" }, { "literal": "Vibhav Vineet" }, { "literal": "Spencer Whitehead" }, { "literal": "Andrew Zhao" } ], "citation-key": "arxiv_2511_19663", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f0e23ba9b31a01956836e67329652882f84fe8ebef1075385a6af5e68cdae936", "submitted_at": "2025-11-24T19:56:28Z", "updated_at": "2025-11-24T19:56:28Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.19663v1" }, "canonical_source_url": "https://arxiv.org/abs/2511.19663", "catalog_id": "arxiv:2511.19663", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-24", "identifiers": { "arxiv": "2511.19663" }, "record_updated_at": "2025-11-24" }, "genre": "preprint", "id": "arxiv:2511.19663", "issued": { "date-parts": [ [ 2025, 11, 24 ] ] }, "note": "First published: 2025-11-24; Recorded arXiv version: v1; Recorded version updated: 2025-11-24T19:56:28Z.", "title": "Fara-7B: An Efficient Agentic Model for Computer Use", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2511.20766v1", "archive": "arXiv", "archive_location": "2511.20766", "author": [ { "literal": "Karen Ullrich" }, { "literal": "Jingtong Su" }, { "literal": "Claudia Shi" }, { "literal": "Arjun Subramonian" }, { "literal": "Amir Bar" }, { "literal": "Ivan Evtimov" }, { "literal": "Nikolaos Tsilivis" }, { "literal": "Randall Balestriero" }, { "literal": "Julia Kempe" }, { "literal": "Mark Ibrahim" } ], "citation-key": "arxiv_2511_20766", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2c288e7c42b5eedeea3f27a5622e87981f101f472db05ead6d6bede1371500f0", "submitted_at": "2025-11-25T19:00:22Z", "updated_at": "2025-11-25T19:00:22Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.20766v1" }, "canonical_source_url": "https://arxiv.org/abs/2511.20766", "catalog_id": "arxiv:2511.20766", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-25", "identifiers": { "arxiv": "2511.20766" }, "record_updated_at": "2025-11-25" }, "genre": "preprint", "id": "arxiv:2511.20766", "issued": { "date-parts": [ [ 2025, 11, 25 ] ] }, "note": "First published: 2025-11-25; Recorded arXiv version: v1; Recorded version updated: 2025-11-25T19:00:22Z.", "title": "OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.02423v1", "archive": "arXiv", "archive_location": "2512.02423", "author": [ { "literal": "Haolong Yan" }, { "literal": "Yeqing Shen" }, { "literal": "Xin Huang" }, { "literal": "Jia Wang" }, { "literal": "Kaijun Tan" }, { "literal": "Zhixuan Liang" }, { "literal": "Hongxin Li" }, { "literal": "Zheng Ge" }, { "literal": "Osamu Yoshie" }, { "literal": "Si Li" }, { "literal": "Xiangyu Zhang" }, { "literal": "Daxin Jiang" } ], "citation-key": "arxiv_2512_02423", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fda844ac6767e6d9dfd16919042469e2070ec7f092e0b01fb5a243ed6eb4c282", "submitted_at": "2025-12-02T05:11:23Z", "updated_at": "2025-12-02T05:11:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.02423v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.02423", "catalog_id": "arxiv:2512.02423", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-02", "identifiers": { "arxiv": "2512.02423" }, "record_updated_at": "2025-12-02" }, "genre": "preprint", "id": "arxiv:2512.02423", "issued": { "date-parts": [ [ 2025, 12, 2 ] ] }, "note": "First published: 2025-12-02; Recorded arXiv version: v1; Recorded version updated: 2025-12-02T05:11:23Z.", "title": "GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.10962v3", "archive": "arXiv", "archive_location": "2512.10962", "author": [ { "literal": "Yifei He" }, { "literal": "Pranit Chawla" }, { "literal": "Yaser Souri" }, { "literal": "Subhojit Som" }, { "literal": "Xia Song" } ], "citation-key": "arxiv_2512_10962", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a7ccc7923f4e6f2ea296b4a6bfc28ba4dc7a52ed256008f153f13fccac3f018f", "submitted_at": "2025-11-22T23:12:56Z", "updated_at": "2026-02-04T19:36:03Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2512.10962v3" }, "canonical_source_url": "https://arxiv.org/abs/2512.10962", "catalog_id": "arxiv:2512.10962", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-22", "identifiers": { "arxiv": "2512.10962" }, "record_updated_at": "2026-02-04" }, "genre": "preprint", "id": "arxiv:2512.10962", "issued": { "date-parts": [ [ 2025, 11, 22 ] ] }, "note": "First published: 2025-11-22; Recorded arXiv version: v3; Recorded version updated: 2026-02-04T19:36:03Z.", "title": "WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2512.11611v1", "archive": "arXiv", "archive_location": "2512.11611", "author": [ { "literal": "Chunyi Li" }, { "literal": "Longfei Li" }, { "literal": "Zicheng Zhang" }, { "literal": "Xiaohong Liu" }, { "literal": "Min Tang" }, { "literal": "Weisi Lin" }, { "literal": "Guangtao Zhai" } ], "citation-key": "arxiv_2512_11611", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "484a51656db4466d5e8630d64fa78d3cf10043568488f5a2e9bae679fa800cbe", "submitted_at": "2025-12-12T14:49:32Z", "updated_at": "2025-12-12T14:49:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.11611v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.11611", "catalog_id": "arxiv:2512.11611", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-12", "identifiers": { "arxiv": "2512.11611" }, "record_updated_at": "2025-12-12" }, "genre": "preprint", "id": "arxiv:2512.11611", "issued": { "date-parts": [ [ 2025, 12, 12 ] ] }, "note": "First published: 2025-12-12; Recorded arXiv version: v1; Recorded version updated: 2025-12-12T14:49:32Z.", "title": "Using GUI Agent for Electronic Design Automation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.15431v2", "archive": "arXiv", "archive_location": "2512.15431", "author": [ { "literal": "Haolong Yan" }, { "literal": "Jia Wang" }, { "literal": "Xin Huang" }, { "literal": "Yeqing Shen" }, { "literal": "Ziyang Meng" }, { "literal": "Zhimin Fan" }, { "literal": "Kaijun Tan" }, { "literal": "Jin Gao" }, { "literal": "Lieyu Shi" }, { "literal": "Mi Yang" }, { "literal": "Shiliang Yang" }, { "literal": "Zhirui Wang" }, { "literal": "Brian Li" }, { "literal": "Kang An" }, { "literal": "Chenyang Li" }, { "literal": "Lei Lei" }, { "literal": "Mengmeng Duan" }, { "literal": "Danxun Liang" }, { "literal": "Guodong Liu" }, { "literal": "Hang Cheng" }, { "literal": "Hao Wu" }, { "literal": "Jie Dong" }, { "literal": "Junhao Huang" }, { "literal": "Mei Chen" }, { "literal": "Renjie Yu" }, { "literal": "Shunshan Li" }, { "literal": "Xu Zhou" }, { "literal": "Yiting Dai" }, { "literal": "Yineng Deng" }, { "literal": "Yingdan Liang" }, { "literal": "Zelin Chen" }, { "literal": "Wen Sun" }, { "literal": "Chengxu Yan" }, { "literal": "Chunqin Xu" }, { "literal": "Dong Li" }, { "literal": "Fengqiong Xiao" }, { "literal": "Guanghao Fan" }, { "literal": "Guopeng Li" }, { "literal": "Guozhen Peng" }, { "literal": "Hongbing Li" }, { "literal": "Hang Li" }, { "literal": "Hongming Chen" }, { "literal": "Jingjing Xie" }, { "literal": "Jianyong Li" }, { "literal": "Jingyang Zhang" }, { "literal": "Jiaju Ren" }, { "literal": "Jiayu Yuan" }, { "literal": "Jianpeng Yin" }, { "literal": "Kai Cao" }, { "literal": "Liang Zhao" }, { "literal": "Liguo Tan" }, { "literal": "Liying Shi" }, { "literal": "Mengqiang Ren" }, { "literal": "Min Xu" }, { "literal": "Manjiao Liu" }, { "literal": "Mao Luo" }, { "literal": "Mingxin Wan" }, { "literal": "Na Wang" }, { "literal": "Nan Wu" }, { "literal": "Ning Wang" }, { "literal": "Peiyao Ma" }, { "literal": "Qingzhou Zhang" }, { "literal": "Qiao Wang" }, { "literal": "Qinlin Zeng" }, { "literal": "Qiong Gao" }, { "literal": "Qiongyao Li" }, { "literal": "Shangwu Zhong" }, { "literal": "Shuli Gao" }, { "literal": "Shaofan Liu" }, { "literal": "Shisi Gao" }, { "literal": "Shuang Luo" }, { "literal": "Xingbin Liu" }, { "literal": "Xiaojia Liu" }, { "literal": "Xiaojie Hou" }, { "literal": "Xin Liu" }, { "literal": "Xuanti Feng" }, { "literal": "Xuedan Cai" }, { "literal": "Xuan Wen" }, { "literal": "Xianwei Zhu" }, { "literal": "Xin Liang" }, { "literal": "Xin Liu" }, { "literal": "Xin Zhou" }, { "literal": "Yifan Sui" }, { "literal": "Yingxiu Zhao" }, { "literal": "Yukang Shi" }, { "literal": "Yunfang Xu" }, { "literal": "Yuqing Zeng" }, { "literal": "Yixun Zhang" }, { "literal": "Zejia Weng" }, { "literal": "Zhonghao Yan" }, { "literal": "Zhiguo Huang" }, { "literal": "Zhuoyu Wang" }, { "literal": "Zihan Yan" }, { "literal": "Zheng Ge" }, { "literal": "Jing Li" }, { "literal": "Yibo Zhu" }, { "literal": "Binxing Jiao" }, { "literal": "Xiangyu Zhang" }, { "literal": "Daxin Jiang" } ], "citation-key": "arxiv_2512_15431", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2fc824bdeabca3451fd895447a0321c507da1ac7bc7cc24184c7768992549daf", "submitted_at": "2025-12-17T13:26:30Z", "updated_at": "2025-12-19T17:36:21Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2512.15431v2" }, "canonical_source_url": "https://arxiv.org/abs/2512.15431", "catalog_id": "arxiv:2512.15431", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-17", "identifiers": { "arxiv": "2512.15431" }, "record_updated_at": "2025-12-19" }, "genre": "preprint", "id": "arxiv:2512.15431", "issued": { "date-parts": [ [ 2025, 12, 17 ] ] }, "note": "First published: 2025-12-17; Recorded arXiv version: v2; Recorded version updated: 2025-12-19T17:36:21Z.", "title": "Step-GUI Technical Report", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2512.16295v1", "archive": "arXiv", "archive_location": "2512.16295", "author": [ { "literal": "Zhenyu Wu" }, { "literal": "Jingjing Xie" }, { "literal": "Zehao Li" }, { "literal": "Bowen Yang" }, { "literal": "Qiushi Sun" }, { "literal": "Zhaoyang Liu" }, { "literal": "Zhoumianze Liu" }, { "literal": "Yu Qiao" }, { "literal": "Xiangyu Yue" }, { "literal": "Zun Wang" }, { "literal": "Zichen Ding" } ], "citation-key": "arxiv_2512_16295", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "67a1bd40b117b34e5fb994b1c2c93cd285714097d1bc9730baeeaba6c31a7b8a", "submitted_at": "2025-12-18T08:29:50Z", "updated_at": "2025-12-18T08:29:50Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.16295v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.16295", "catalog_id": "arxiv:2512.16295", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-18", "identifiers": { "arxiv": "2512.16295" }, "record_updated_at": "2025-12-18" }, "genre": "preprint", "id": "arxiv:2512.16295", "issued": { "date-parts": [ [ 2025, 12, 18 ] ] }, "note": "First published: 2025-12-18; Recorded arXiv version: v1; Recorded version updated: 2025-12-18T08:29:50Z.", "title": "OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.16501v1", "archive": "arXiv", "archive_location": "2512.16501", "author": [ { "literal": "Beitong Zhou" }, { "literal": "Zhexiao Huang" }, { "literal": "Yuan Guo" }, { "literal": "Zhangxuan Gu" }, { "literal": "Tianyu Xia" }, { "literal": "Zichen Luo" }, { "literal": "Fei Tang" }, { "literal": "Dehan Kong" }, { "literal": "Yanyi Shang" }, { "literal": "Suling Ou" }, { "literal": "Zhenlin Guo" }, { "literal": "Changhua Meng" }, { "literal": "Shuheng Shen" } ], "citation-key": "arxiv_2512_16501", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4bc8a1da3993ead9b36af47a9332fe9a1a2427101ad0d91da654b4a4b25141df", "submitted_at": "2025-12-18T13:09:09Z", "updated_at": "2025-12-18T13:09:09Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.16501v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.16501", "catalog_id": "arxiv:2512.16501", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-18", "identifiers": { "arxiv": "2512.16501" }, "record_updated_at": "2025-12-18" }, "genre": "preprint", "id": "arxiv:2512.16501", "issued": { "date-parts": [ [ 2025, 12, 18 ] ] }, "note": "First published: 2025-12-18; Recorded arXiv version: v1; Recorded version updated: 2025-12-18T13:09:09Z.", "title": "VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.19396v3", "archive": "arXiv", "archive_location": "2512.19396", "author": [ { "literal": "Runze Li" }, { "literal": "Yuwen Zhai" }, { "literal": "Bo Xu" }, { "literal": "LiWu Xu" }, { "literal": "Nian Shi" }, { "literal": "Wei Zhang" }, { "literal": "Ran Lin" }, { "literal": "Liang Wang" } ], "citation-key": "arxiv_2512_19396", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "03cdf8514fa9f036b4614a880d842d49bb9cb0a821858b7215784fba209faa62", "submitted_at": "2025-12-22T13:42:18Z", "updated_at": "2026-04-10T06:20:00Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2512.19396v3" }, "canonical_source_url": "https://arxiv.org/abs/2512.19396", "catalog_id": "arxiv:2512.19396", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-22", "identifiers": { "arxiv": "2512.19396" }, "record_updated_at": "2026-04-10" }, "genre": "preprint", "id": "arxiv:2512.19396", "issued": { "date-parts": [ [ 2025, 12, 22 ] ] }, "note": "First published: 2025-12-22; Recorded arXiv version: v3; Recorded version updated: 2026-04-10T06:20:00Z.", "title": "EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2512.22047v1", "archive": "arXiv", "archive_location": "2512.22047", "author": [ { "literal": "Hanzhang Zhou" }, { "literal": "Xu Zhang" }, { "literal": "Panrong Tong" }, { "literal": "Jianan Zhang" }, { "literal": "Liangyu Chen" }, { "literal": "Quyu Kong" }, { "literal": "Chenglin Cai" }, { "literal": "Chen Liu" }, { "literal": "Yue Wang" }, { "literal": "Jingren Zhou" }, { "literal": "Steven Hoi" } ], "citation-key": "arxiv_2512_22047", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a89eb3fd173680c127245933d252d4e245b7179d77bca4b463d50800c78f7238", "submitted_at": "2025-12-26T14:51:52Z", "updated_at": "2025-12-26T14:51:52Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.22047v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.22047", "catalog_id": "arxiv:2512.22047", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-26", "identifiers": { "arxiv": "2512.22047" }, "record_updated_at": "2025-12-26" }, "genre": "preprint", "id": "arxiv:2512.22047", "issued": { "date-parts": [ [ 2025, 12, 26 ] ] }, "note": "First published: 2025-12-26; Recorded arXiv version: v1; Recorded version updated: 2025-12-26T14:51:52Z.", "title": "MAI-UI Technical Report: Real-World Centric Foundation GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.24965v1", "archive": "arXiv", "archive_location": "2512.24965", "author": [ { "literal": "Siyuan Hu" }, { "literal": "Kevin Qinghong Lin" }, { "literal": "Mike Zheng Shou" } ], "citation-key": "arxiv_2512_24965", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b7d1f358b450f2a6c3deb00f1b16c54d443f48fda3a7dc70c77456bebf35ad7c", "submitted_at": "2025-12-31T16:51:14Z", "updated_at": "2025-12-31T16:51:14Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.24965v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.24965", "catalog_id": "arxiv:2512.24965", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-31", "identifiers": { "arxiv": "2512.24965" }, "record_updated_at": "2025-12-31" }, "genre": "preprint", "id": "arxiv:2512.24965", "issued": { "date-parts": [ [ 2025, 12, 31 ] ] }, "note": "First published: 2025-12-31; Recorded arXiv version: v1; Recorded version updated: 2025-12-31T16:51:14Z.", "title": "ShowUI-$π$: Flow-based Generative Models as GUI Dexterous Hands", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.02439v6", "archive": "arXiv", "archive_location": "2601.02439", "author": [ { "literal": "Hao Bai" }, { "literal": "Alexey Taymanov" }, { "literal": "Tong Zhang" }, { "literal": "Aviral Kumar" }, { "literal": "Spencer Whitehead" } ], "citation-key": "arxiv_2601_02439", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ae8751c4fae3b4f838eba59ffa8be37a1a5f4fa497dfd69fa3075f8581547f51", "submitted_at": "2026-01-05T09:35:11Z", "updated_at": "2026-05-02T18:45:09Z", "version": 6, "versioned_url": "https://arxiv.org/abs/2601.02439v6" }, "canonical_source_url": "https://arxiv.org/abs/2601.02439", "catalog_id": "arxiv:2601.02439", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-05", "identifiers": { "arxiv": "2601.02439" }, "record_updated_at": "2026-05-02" }, "genre": "preprint", "id": "arxiv:2601.02439", "issued": { "date-parts": [ [ 2026, 1, 5 ] ] }, "note": "First published: 2026-01-05; Recorded arXiv version: v6; Recorded version updated: 2026-05-02T18:45:09Z.", "title": "WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks", "type": "article", "version": "6" }, { "URL": "https://arxiv.org/abs/2601.04126v3", "archive": "arXiv", "archive_location": "2601.04126", "author": [ { "literal": "Ziyun Zhang" }, { "literal": "Zezhou Wang" }, { "literal": "Xiaoyi Zhang" }, { "literal": "Zongyu Guo" }, { "literal": "Jiahao Li" }, { "literal": "Bin Li" }, { "literal": "Yan Lu" } ], "citation-key": "arxiv_2601_04126", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d4d0a59f1eb8197b4d389f5f40957fb8aeb1e22d0739f9877b26d57ed70fe59b", "submitted_at": "2026-01-07T17:40:08Z", "updated_at": "2026-06-30T13:54:32Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2601.04126v3" }, "canonical_source_url": "https://arxiv.org/abs/2601.04126", "catalog_id": "arxiv:2601.04126", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-07", "identifiers": { "arxiv": "2601.04126" }, "record_updated_at": "2026-06-30" }, "genre": "preprint", "id": "arxiv:2601.04126", "issued": { "date-parts": [ [ 2026, 1, 7 ] ] }, "note": "First published: 2026-01-07; Recorded arXiv version: v3; Recorded version updated: 2026-06-30T13:54:32Z.", "title": "InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2601.05787v2", "archive": "arXiv", "archive_location": "2601.05787", "author": [ { "literal": "Zezhou Wang" }, { "literal": "Ziyun Zhang" }, { "literal": "Xiaoyi Zhang" }, { "literal": "Zhuzhong Qian" }, { "literal": "Yan Lu" } ], "citation-key": "arxiv_2601_05787", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e342723078b50e612df749df80eadfd16e0fe29f5875777c1b3189d8b5981512", "submitted_at": "2026-01-09T13:26:38Z", "updated_at": "2026-02-10T15:12:17Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.05787v2" }, "canonical_source_url": "https://arxiv.org/abs/2601.05787", "catalog_id": "arxiv:2601.05787", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-09", "identifiers": { "arxiv": "2601.05787" }, "record_updated_at": "2026-02-10" }, "genre": "preprint", "id": "arxiv:2601.05787", "issued": { "date-parts": [ [ 2026, 1, 9 ] ] }, "note": "First published: 2026-01-09; Recorded arXiv version: v2; Recorded version updated: 2026-02-10T15:12:17Z.", "title": "From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2601.07181v1", "archive": "arXiv", "archive_location": "2601.07181", "author": [ { "literal": "Yichun Zhang" }, { "literal": "Xiangwu Guo" }, { "literal": "Yauhong Goh" }, { "literal": "Jessica Hu" }, { "literal": "Zhiheng Chen" }, { "literal": "Xin Wang" }, { "literal": "Difei Gao" }, { "literal": "Mike Zheng Shou" } ], "citation-key": "arxiv_2601_07181", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "60c6a513f53c16ea6d989a7b2be56ad26b83e531bcea46b00f2e08476b686c97", "submitted_at": "2026-01-12T04:04:20Z", "updated_at": "2026-01-12T04:04:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.07181v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.07181", "catalog_id": "arxiv:2601.07181", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-12", "identifiers": { "arxiv": "2601.07181" }, "record_updated_at": "2026-01-12" }, "genre": "preprint", "id": "arxiv:2601.07181", "issued": { "date-parts": [ [ 2026, 1, 12 ] ] }, "note": "First published: 2026-01-12; Recorded arXiv version: v1; Recorded version updated: 2026-01-12T04:04:20Z.", "title": "ShowUI-Aloha: Human-Taught GUI Agent", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.12822v1", "archive": "arXiv", "archive_location": "2601.12822", "author": [ { "literal": "Wenqi Zhang" }, { "literal": "Yulin Shen" }, { "literal": "Changyue Jiang" }, { "literal": "Jiarun Dai" }, { "literal": "Geng Hong" }, { "literal": "Xudong Pan" } ], "citation-key": "arxiv_2601_12822", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b57586682d4675387dea2687e7c15d70cc10aecac883e35fe1812c39abcbc1dc", "submitted_at": "2026-01-19T08:32:09Z", "updated_at": "2026-01-19T08:32:09Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.12822v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.12822", "catalog_id": "arxiv:2601.12822", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-19", "identifiers": { "arxiv": "2601.12822" }, "record_updated_at": "2026-01-19" }, "genre": "preprint", "id": "arxiv:2601.12822", "issued": { "date-parts": [ [ 2026, 1, 19 ] ] }, "note": "First published: 2026-01-19; Recorded arXiv version: v1; Recorded version updated: 2026-01-19T08:32:09Z.", "title": "MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.13060v1", "archive": "arXiv", "archive_location": "2601.13060", "author": [ { "literal": "Zecheng Li" }, { "literal": "Zhihui Cao" }, { "literal": "Wenke Huang" }, { "literal": "Yudong Zhang" }, { "literal": "Keying Qi" }, { "literal": "Rui Wang" }, { "literal": "Zeyu Zheng" }, { "literal": "Jian Zhao" }, { "literal": "Hao Zhu" }, { "literal": "Hengxin Wu" }, { "literal": "Yuran Wang" }, { "literal": "Guitao Fan" }, { "literal": "Guokun Wu" }, { "literal": "Yicong Liu" }, { "literal": "Zhilin Gao" }, { "literal": "Haikun Xu" }, { "literal": "He Yang" }, { "literal": "Minqi Xiang" }, { "literal": "Xingyu Liu" }, { "literal": "Zuojian Wang" } ], "citation-key": "arxiv_2601_13060", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aa8cb4137e862bf8031a55bc8f81e1d6c903733f2cfac9cf758e5f2f92884481", "submitted_at": "2026-01-19T13:50:43Z", "updated_at": "2026-01-19T13:50:43Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.13060v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.13060", "catalog_id": "arxiv:2601.13060", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-19", "identifiers": { "arxiv": "2601.13060" }, "record_updated_at": "2026-01-19" }, "genre": "preprint", "id": "arxiv:2601.13060", "issued": { "date-parts": [ [ 2026, 1, 19 ] ] }, "note": "First published: 2026-01-19; Recorded arXiv version: v1; Recorded version updated: 2026-01-19T13:50:43Z.", "title": "MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.15876v2", "archive": "arXiv", "archive_location": "2601.15876", "author": [ { "literal": "Taofeng Xue" }, { "literal": "Chong Peng" }, { "literal": "Mianqiu Huang" }, { "literal": "Linsen Guo" }, { "literal": "Tiancheng Han" }, { "literal": "Haozhe Wang" }, { "literal": "Jianing Wang" }, { "literal": "Xiaocheng Zhang" }, { "literal": "Xin Yang" }, { "literal": "Dengchang Zhao" }, { "literal": "Jinrui Ding" }, { "literal": "Xiandi Ma" }, { "literal": "Yuchen Xie" }, { "literal": "Peng Pei" }, { "literal": "Xunliang Cai" }, { "literal": "Xipeng Qiu" } ], "citation-key": "arxiv_2601_15876", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "38b2798ce9ebd69a46202f0fa8ceca859394acda4f5173b5e30248914c8c35ac", "submitted_at": "2026-01-22T11:36:43Z", "updated_at": "2026-01-23T08:52:00Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.15876v2" }, "canonical_source_url": "https://arxiv.org/abs/2601.15876", "catalog_id": "arxiv:2601.15876", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-22", "identifiers": { "arxiv": "2601.15876" }, "record_updated_at": "2026-01-23" }, "genre": "preprint", "id": "arxiv:2601.15876", "issued": { "date-parts": [ [ 2026, 1, 22 ] ] }, "note": "First published: 2026-01-22; Recorded arXiv version: v2; Recorded version updated: 2026-01-23T08:52:00Z.", "title": "EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2601.18197v2", "archive": "arXiv", "archive_location": "2601.18197", "author": [ { "literal": "Shaokang Wang" }, { "literal": "Pei Fu" }, { "literal": "Ruoceng Zhang" }, { "literal": "Shaojie Zhang" }, { "literal": "Xiuwen Xi" }, { "literal": "Jiahui Yang" }, { "literal": "Bin Qin" }, { "literal": "Ying Huang" }, { "literal": "Zhenbo Luo" }, { "literal": "Jian Luan" } ], "citation-key": "arxiv_2601_18197", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ccb46b86b0c0b854ed2f1e17f9e12bf031c5ed1349f3d3c44d3276b2a3a195ee", "submitted_at": "2026-01-26T06:29:41Z", "updated_at": "2026-06-26T07:19:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.18197v2" }, "canonical_source_url": "https://arxiv.org/abs/2601.18197", "catalog_id": "arxiv:2601.18197", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-26", "identifiers": { "arxiv": "2601.18197" }, "record_updated_at": "2026-06-26" }, "genre": "preprint", "id": "arxiv:2601.18197", "issued": { "date-parts": [ [ 2026, 1, 26 ] ] }, "note": "First published: 2026-01-26; Recorded arXiv version: v2; Recorded version updated: 2026-06-26T07:19:55Z.", "title": "GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2601.18305v2", "archive": "arXiv", "archive_location": "2601.18305", "author": [ { "literal": "Xuan Wang" }, { "literal": "Siyuan Su" }, { "literal": "Quantong Fu" }, { "literal": "Yongxiang Hu" }, { "literal": "Yangfan Zhou" } ], "citation-key": "arxiv_2601_18305", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cb90eed33e989d38cd4058d54ba7d073f1b8e5c1453a9106dfe5e533da7b08a1", "submitted_at": "2026-01-26T09:35:10Z", "updated_at": "2026-08-20T07:50:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.18305v2" }, "canonical_source_url": "https://arxiv.org/abs/2601.18305", "catalog_id": "arxiv:2601.18305", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-26", "identifiers": { "arxiv": "2601.18305" }, "record_updated_at": "2026-08-20" }, "genre": "preprint", "id": "arxiv:2601.18305", "issued": { "date-parts": [ [ 2026, 1, 26 ] ] }, "note": "First published: 2026-01-26; Recorded arXiv version: v2; Recorded version updated: 2026-08-20T07:50:44Z.", "title": "SwipeGen: Bridging the Execution Gap in GUI Agents via Human-like Swipe Synthesis", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2601.20380v1", "archive": "arXiv", "archive_location": "2601.20380", "author": [ { "literal": "Le Zhang" }, { "literal": "Yixiong Xiao" }, { "literal": "Xinjiang Lu" }, { "literal": "Jingjia Cao" }, { "literal": "Yusai Zhao" }, { "literal": "Jingbo Zhou" }, { "literal": "Lang An" }, { "literal": "Zikan Feng" }, { "literal": "Wanxiang Sha" }, { "literal": "Yu Shi" }, { "literal": "Congxi Xiao" }, { "literal": "Jian Xiong" }, { "literal": "Yankai Zhang" }, { "literal": "Hua Wu" }, { "literal": "Haifeng Wang" } ], "citation-key": "arxiv_2601_20380", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ad764cf86a2ecab81f3f730d6d26ea582544a355a90a8be55be220c98aabd7bf", "submitted_at": "2026-01-28T08:45:17Z", "updated_at": "2026-01-28T08:45:17Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.20380v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.20380", "catalog_id": "arxiv:2601.20380", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-28", "identifiers": { "arxiv": "2601.20380" }, "record_updated_at": "2026-01-28" }, "genre": "preprint", "id": "arxiv:2601.20380", "issued": { "date-parts": [ [ 2026, 1, 28 ] ] }, "note": "First published: 2026-01-28; Recorded arXiv version: v1; Recorded version updated: 2026-01-28T08:45:17Z.", "title": "OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.22149v2", "archive": "arXiv", "archive_location": "2601.22149", "author": [ { "literal": "Hang Ding" }, { "literal": "Peidong Liu" }, { "literal": "Junqiao Wang" }, { "literal": "Ziwei Ji" }, { "literal": "Meng Cao" }, { "literal": "Rongzhao Zhang" }, { "literal": "Lynn Ai" }, { "literal": "Eric Yang" }, { "literal": "Tianyu Shi" }, { "literal": "Lei Yu" } ], "citation-key": "arxiv_2601_22149", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aedb5ed90c91d72f62f5ab60be5374b6f431f887425bc760883ce3fb85a46d43", "submitted_at": "2026-01-29T18:59:07Z", "updated_at": "2026-04-17T18:27:53Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.22149v2" }, "canonical_source_url": "https://arxiv.org/abs/2601.22149", "catalog_id": "arxiv:2601.22149", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-29", "identifiers": { "arxiv": "2601.22149" }, "record_updated_at": "2026-04-17" }, "genre": "preprint", "id": "arxiv:2601.22149", "issued": { "date-parts": [ [ 2026, 1, 29 ] ] }, "note": "First published: 2026-01-29; Recorded arXiv version: v2; Recorded version updated: 2026-04-17T18:27:53Z.", "title": "DynaWeb: Model-Based Reinforcement Learning of Web Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2601.22781v1", "archive": "arXiv", "archive_location": "2601.22781", "author": [ { "literal": "Linjia Kang" }, { "literal": "Zhimin Wang" }, { "literal": "Yongkang Zhang" }, { "literal": "Duo Wu" }, { "literal": "Jinghe Wang" }, { "literal": "Ming Ma" }, { "literal": "Haopeng Yan" }, { "literal": "Zhi Wang" } ], "citation-key": "arxiv_2601_22781", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0d66365682d0ea4cee744c6c59d3a585c9272a31da5f8ff7c27983d719f070a7", "submitted_at": "2026-01-30T10:03:20Z", "updated_at": "2026-01-30T10:03:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.22781v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.22781", "catalog_id": "arxiv:2601.22781", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-30", "identifiers": { "arxiv": "2601.22781" }, "record_updated_at": "2026-01-30" }, "genre": "preprint", "id": "arxiv:2601.22781", "issued": { "date-parts": [ [ 2026, 1, 30 ] ] }, "note": "First published: 2026-01-30; Recorded arXiv version: v1; Recorded version updated: 2026-01-30T10:03:20Z.", "title": "Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent Training", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.01576v2", "archive": "arXiv", "archive_location": "2602.01576", "author": [ { "literal": "Woosung Koh" }, { "literal": "Sungjun Han" }, { "literal": "Segyu Lee" }, { "literal": "Se-Young Yun" }, { "literal": "Jamin Shin" } ], "citation-key": "arxiv_2602_01576", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7c29d1404b02c4f5ef2cdaf78bdb0f9062b1b85ec1a154408bc8f49446c28d08", "submitted_at": "2026-02-02T03:12:16Z", "updated_at": "2026-05-23T02:41:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.01576v2" }, "canonical_source_url": "https://arxiv.org/abs/2602.01576", "catalog_id": "arxiv:2602.01576", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-02", "identifiers": { "arxiv": "2602.01576" }, "record_updated_at": "2026-05-23" }, "genre": "preprint", "id": "arxiv:2602.01576", "issued": { "date-parts": [ [ 2026, 2, 2 ] ] }, "note": "First published: 2026-02-02; Recorded arXiv version: v2; Recorded version updated: 2026-05-23T02:41:44Z.", "title": "Generative Visual Code Mobile World Models", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.02548v1", "archive": "arXiv", "archive_location": "2602.02548", "author": [ { "literal": "Xiaoce Wang" }, { "literal": "Guibin Zhang" }, { "literal": "Junzhe Li" }, { "literal": "Jinzhe Tu" }, { "literal": "Chun Li" }, { "literal": "Ming Li" } ], "citation-key": "arxiv_2602_02548", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "49b0dbff31dcf8c966bebd367ae05984e46a7fd13b2cfb1ad5ef061332b43f00", "submitted_at": "2026-01-30T08:38:05Z", "updated_at": "2026-01-30T08:38:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.02548v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.02548", "catalog_id": "arxiv:2602.02548", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-30", "identifiers": { "arxiv": "2602.02548" }, "record_updated_at": "2026-01-30" }, "genre": "preprint", "id": "arxiv:2602.02548", "issued": { "date-parts": [ [ 2026, 1, 30 ] ] }, "note": "First published: 2026-01-30; Recorded arXiv version: v1; Recorded version updated: 2026-01-30T08:38:05Z.", "title": "ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.05429v1", "archive": "arXiv", "archive_location": "2602.05429", "author": [ { "literal": "Rui Lv" }, { "literal": "Juncheng Mo" }, { "literal": "Tianyi Chu" }, { "literal": "Chen Rao" }, { "literal": "Hongyi Jing" }, { "literal": "Jiajie Teng" }, { "literal": "Jiafu Chen" }, { "literal": "Shiqi Zhang" }, { "literal": "Liangzi Ding" }, { "literal": "Shuo Fang" }, { "literal": "Huaizhong Lin" }, { "literal": "Ziqiang Dang" }, { "literal": "Chenguang Ma" }, { "literal": "Lei Zhao" } ], "citation-key": "arxiv_2602_05429", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "84d822655c810958cff6035584542d7e151d765734ec7030f841c15561ee5677", "submitted_at": "2026-02-05T08:19:39Z", "updated_at": "2026-02-05T08:19:39Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.05429v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.05429", "catalog_id": "arxiv:2602.05429", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-05", "identifiers": { "arxiv": "2602.05429" }, "record_updated_at": "2026-02-05" }, "genre": "preprint", "id": "arxiv:2602.05429", "issued": { "date-parts": [ [ 2026, 2, 5 ] ] }, "note": "First published: 2026-02-05; Recorded arXiv version: v1; Recorded version updated: 2026-02-05T08:19:39Z.", "title": "M$^2$-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.07153v2", "archive": "arXiv", "archive_location": "2602.07153", "author": [ { "literal": "Jinbiao Wei" }, { "literal": "Yilun Zhao" }, { "literal": "Kangqi Ni" }, { "literal": "Arman Cohan" } ], "citation-key": "arxiv_2602_07153", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ce896d4d846bf07fedc68b7f952532c4fefe24dcb49b51556e0d6c2bc648bb91", "submitted_at": "2026-02-06T19:55:26Z", "updated_at": "2026-04-12T06:09:23Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.07153v2" }, "canonical_source_url": "https://arxiv.org/abs/2602.07153", "catalog_id": "arxiv:2602.07153", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-06", "identifiers": { "arxiv": "2602.07153" }, "record_updated_at": "2026-04-12" }, "genre": "preprint", "id": "arxiv:2602.07153", "issued": { "date-parts": [ [ 2026, 2, 6 ] ] }, "note": "First published: 2026-02-06; Recorded arXiv version: v2; Recorded version updated: 2026-04-12T06:09:23Z.", "title": "ANCHOR: Branch-Point Data Generation for GUI Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.09012v2", "archive": "arXiv", "archive_location": "2602.09012", "author": [ { "literal": "Jiacheng Liu" }, { "literal": "Yaxin Luo" }, { "literal": "Jiacheng Cui" }, { "literal": "Xinyi Shang" }, { "literal": "Xiaohan Zhao" }, { "literal": "Zhiqiang Shen" } ], "citation-key": "arxiv_2602_09012", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3178684a322fcf07f847473139efdddf0b02213af468f1afbd285549d15bde56", "submitted_at": "2026-02-09T18:55:33Z", "updated_at": "2026-06-21T08:25:39Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.09012v2" }, "canonical_source_url": "https://arxiv.org/abs/2602.09012", "catalog_id": "arxiv:2602.09012", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-09", "identifiers": { "arxiv": "2602.09012" }, "record_updated_at": "2026-06-21" }, "genre": "preprint", "id": "arxiv:2602.09012", "issued": { "date-parts": [ [ 2026, 2, 9 ] ] }, "note": "First published: 2026-02-09; Recorded arXiv version: v2; Recorded version updated: 2026-06-21T08:25:39Z.", "title": "Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.09310v1", "archive": "arXiv", "archive_location": "2602.09310", "author": [ { "literal": "Ananya Gubbi Mohanbabu" }, { "literal": "Rosiana Natalie" }, { "literal": "Brandon Kim" }, { "literal": "Anhong Guo" }, { "literal": "Amy Pavel" } ], "citation-key": "arxiv_2602_09310", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c3606d090749737d4223a9f826400c2b2aebde245c623391f2a8c6702b2468f8", "submitted_at": "2026-02-10T01:00:55Z", "updated_at": "2026-02-10T01:00:55Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.09310v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.09310", "catalog_id": "arxiv:2602.09310", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-10", "identifiers": { "arxiv": "2602.09310" }, "record_updated_at": "2026-02-10" }, "genre": "preprint", "id": "arxiv:2602.09310", "issued": { "date-parts": [ [ 2026, 2, 10 ] ] }, "note": "First published: 2026-02-10; Recorded arXiv version: v1; Recorded version updated: 2026-02-10T01:00:55Z.", "title": "A11y-CUA Dataset: Characterizing the Accessibility Gap in Computer Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.09662v1", "archive": "arXiv", "archive_location": "2602.09662", "author": [ { "literal": "Deyang Jiang" }, { "literal": "Jing Huang" }, { "literal": "Xuanle Zhao" }, { "literal": "Lei Chen" }, { "literal": "Liming Zheng" }, { "literal": "Fanfan Liu" }, { "literal": "Haibo Qiu" }, { "literal": "Peng Shi" }, { "literal": "Zhixiong Zeng" } ], "citation-key": "arxiv_2602_09662", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b5080050b85e38c8c03078c96c206e92d4ed63d106d55983563d51fcbc9f66c5", "submitted_at": "2026-02-10T11:16:57Z", "updated_at": "2026-02-10T11:16:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.09662v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.09662", "catalog_id": "arxiv:2602.09662", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-10", "identifiers": { "arxiv": "2602.09662" }, "record_updated_at": "2026-02-10" }, "genre": "preprint", "id": "arxiv:2602.09662", "issued": { "date-parts": [ [ 2026, 2, 10 ] ] }, "note": "First published: 2026-02-10; Recorded arXiv version: v1; Recorded version updated: 2026-02-10T11:16:57Z.", "title": "TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.09856v1", "archive": "arXiv", "archive_location": "2602.09856", "author": [ { "literal": "Yuhao Zheng" }, { "literal": "Li'an Zhong" }, { "literal": "Yi Wang" }, { "literal": "Rui Dai" }, { "literal": "Kaikui Liu" }, { "literal": "Xiangxiang Chu" }, { "literal": "Linyuan Lv" }, { "literal": "Philip Torr" }, { "literal": "Kevin Qinghong Lin" } ], "citation-key": "arxiv_2602_09856", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "55287e2fe8a5e94671e4aab8e9d4a907ba9b6c83306d9b3f61b74adccd5c5059", "submitted_at": "2026-02-10T14:56:19Z", "updated_at": "2026-02-10T14:56:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.09856v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.09856", "catalog_id": "arxiv:2602.09856", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-10", "identifiers": { "arxiv": "2602.09856" }, "record_updated_at": "2026-02-10" }, "genre": "preprint", "id": "arxiv:2602.09856", "issued": { "date-parts": [ [ 2026, 2, 10 ] ] }, "note": "First published: 2026-02-10; Recorded arXiv version: v1; Recorded version updated: 2026-02-10T14:56:19Z.", "title": "Code2World: A GUI World Model via Renderable Code Generation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.10356v2", "archive": "arXiv", "archive_location": "2602.10356", "author": [ { "literal": "Tianci Xue" }, { "literal": "Zeyi Liao" }, { "literal": "Tianneng Shi" }, { "literal": "Zilu Wang" }, { "literal": "Kai Zhang" }, { "literal": "Dawn Song" }, { "literal": "Yu Su" }, { "literal": "Huan Sun" } ], "citation-key": "arxiv_2602_10356", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d3385966e7b483b33738b3c8e6c9a4d9cf17afa671e1f2e49de4f946cbc5f251", "submitted_at": "2026-02-10T23:06:02Z", "updated_at": "2026-05-11T00:11:46Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.10356v2" }, "canonical_source_url": "https://arxiv.org/abs/2602.10356", "catalog_id": "arxiv:2602.10356", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-10", "identifiers": { "arxiv": "2602.10356" }, "record_updated_at": "2026-05-11" }, "genre": "preprint", "id": "arxiv:2602.10356", "issued": { "date-parts": [ [ 2026, 2, 10 ] ] }, "note": "First published: 2026-02-10; Recorded arXiv version: v2; Recorded version updated: 2026-05-11T00:11:46Z.", "title": "Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.12544v1", "archive": "arXiv", "archive_location": "2602.12544", "author": [ { "literal": "Lajanugen Logeswaran" }, { "literal": "Jaekyeom Kim" }, { "literal": "Sungryull Sohn" }, { "literal": "Creighton Glasscock" }, { "literal": "Honglak Lee" } ], "citation-key": "arxiv_2602_12544", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "555285a1ab51e02661067bdf8bcc3fa7f6ee0fdd63f52f786a03eb2483bd1a31", "submitted_at": "2026-02-13T02:52:18Z", "updated_at": "2026-02-13T02:52:18Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.12544v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.12544", "catalog_id": "arxiv:2602.12544", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-13", "identifiers": { "arxiv": "2602.12544" }, "record_updated_at": "2026-02-13" }, "genre": "preprint", "id": "arxiv:2602.12544", "issued": { "date-parts": [ [ 2026, 2, 13 ] ] }, "note": "First published: 2026-02-13; Recorded arXiv version: v1; Recorded version updated: 2026-02-13T02:52:18Z.", "title": "Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.14093v1", "archive": "arXiv", "archive_location": "2602.14093", "author": [ { "literal": "Yuan Cao" }, { "literal": "Dezhi Ran" }, { "literal": "Mengzhou Wu" }, { "literal": "Yuzhe Guo" }, { "literal": "Xin Chen" }, { "literal": "Ang Li" }, { "literal": "Gang Cao" }, { "literal": "Gong Zhi" }, { "literal": "Hao Yu" }, { "literal": "Linyi Li" }, { "literal": "Wei Yang" }, { "literal": "Tao Xie" } ], "citation-key": "arxiv_2602_14093", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "29b4c8a5bda1df237fad33ce483018b3476684f904841ed0598ec4286234b858", "submitted_at": "2026-02-15T10:58:01Z", "updated_at": "2026-02-15T10:58:01Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.14093v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.14093", "catalog_id": "arxiv:2602.14093", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-15", "identifiers": { "arxiv": "2602.14093" }, "record_updated_at": "2026-02-15" }, "genre": "preprint", "id": "arxiv:2602.14093", "issued": { "date-parts": [ [ 2026, 2, 15 ] ] }, "note": "First published: 2026-02-15; Recorded arXiv version: v1; Recorded version updated: 2026-02-15T10:58:01Z.", "title": "GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.14276v2", "archive": "arXiv", "archive_location": "2602.14276", "author": [ { "literal": "A. Said Gurbuz" }, { "literal": "Sunghwan Hong" }, { "literal": "Ahmed Nassar" }, { "literal": "Marc Pollefeys" }, { "literal": "Peter Staar" } ], "citation-key": "arxiv_2602_14276", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d7c6e23f704562c4ae4db9e0b4f8f2a8dde1318efc08876ee57f5967b178257e", "submitted_at": "2026-02-15T19:00:02Z", "updated_at": "2026-05-01T17:32:06Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.14276v2" }, "canonical_source_url": "https://arxiv.org/abs/2602.14276", "catalog_id": "arxiv:2602.14276", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-15", "identifiers": { "arxiv": "2602.14276" }, "record_updated_at": "2026-05-01" }, "genre": "preprint", "id": "arxiv:2602.14276", "issued": { "date-parts": [ [ 2026, 2, 15 ] ] }, "note": "First published: 2026-02-15; Recorded arXiv version: v2; Recorded version updated: 2026-05-01T17:32:06Z.", "title": "ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.14296v1", "archive": "arXiv", "archive_location": "2602.14296", "author": [ { "literal": "Yifan Wu" }, { "literal": "Yiran Peng" }, { "literal": "Yiyu Chen" }, { "literal": "Jianhao Ruan" }, { "literal": "Zijie Zhuang" }, { "literal": "Cheng Yang" }, { "literal": "Jiayi Zhang" }, { "literal": "Man Chen" }, { "literal": "Yenchi Tseng" }, { "literal": "Zhaoyang Yu" }, { "literal": "Liang Chen" }, { "literal": "Yuyao Zhai" }, { "literal": "Bang Liu" }, { "literal": "Chenglin Wu" }, { "literal": "Yuyu Luo" } ], "citation-key": "arxiv_2602_14296", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3773ec51f5316b9006f93aeafd7b654bf0e7418253c0af16ef7b7c00fddea102", "submitted_at": "2026-02-15T20:03:19Z", "updated_at": "2026-02-15T20:03:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.14296v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.14296", "catalog_id": "arxiv:2602.14296", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-15", "identifiers": { "arxiv": "2602.14296" }, "record_updated_at": "2026-02-15" }, "genre": "preprint", "id": "arxiv:2602.14296", "issued": { "date-parts": [ [ 2026, 2, 15 ] ] }, "note": "First published: 2026-02-15; Recorded arXiv version: v1; Recorded version updated: 2026-02-15T20:03:19Z.", "title": "AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.14721v1", "archive": "arXiv", "archive_location": "2602.14721", "author": [ { "literal": "Zikai Xiao" }, { "literal": "Jianhong Tu" }, { "literal": "Chuhang Zou" }, { "literal": "Yuxin Zuo" }, { "literal": "Zhi Li" }, { "literal": "Peng Wang" }, { "literal": "Bowen Yu" }, { "literal": "Fei Huang" }, { "literal": "Junyang Lin" }, { "literal": "Zuozhu Liu" } ], "citation-key": "arxiv_2602_14721", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2dca0e4219a788205bbb060911d0f004d1db4cf2ff8a4962c04fd5777ea194d7", "submitted_at": "2026-02-16T13:06:49Z", "updated_at": "2026-02-16T13:06:49Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.14721v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.14721", "catalog_id": "arxiv:2602.14721", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-16", "identifiers": { "arxiv": "2602.14721" }, "record_updated_at": "2026-02-16" }, "genre": "preprint", "id": "arxiv:2602.14721", "issued": { "date-parts": [ [ 2026, 2, 16 ] ] }, "note": "First published: 2026-02-16; Recorded arXiv version: v1; Recorded version updated: 2026-02-16T13:06:49Z.", "title": "WebWorld: A Large-Scale World Model for Web Agent Training", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.17588v4", "archive": "arXiv", "archive_location": "2602.17588", "author": [ { "literal": "Faria Huq" }, { "literal": "Zora Zhiruo Wang" }, { "literal": "Zhanqiu Guo" }, { "literal": "Venu Arvind Arangarajan" }, { "literal": "Tianyue Ou" }, { "literal": "Frank Xu" }, { "literal": "Shuyan Zhou" }, { "literal": "Graham Neubig" }, { "literal": "Jeffrey P. Bigham" } ], "citation-key": "arxiv_2602_17588", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fe83d38ece7cd8f39d932611abaf7a170e7cb9b7c9744bd1176eb42e73be85b5", "submitted_at": "2026-02-19T18:11:28Z", "updated_at": "2026-07-07T23:37:46Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2602.17588v4" }, "canonical_source_url": "https://arxiv.org/abs/2602.17588", "catalog_id": "arxiv:2602.17588", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-19", "identifiers": { "arxiv": "2602.17588" }, "record_updated_at": "2026-07-07" }, "genre": "preprint", "id": "arxiv:2602.17588", "issued": { "date-parts": [ [ 2026, 2, 19 ] ] }, "note": "First published: 2026-02-19; Recorded arXiv version: v4; Recorded version updated: 2026-07-07T23:37:46Z.", "title": "Modeling Distinct Human Interaction in Web Agents", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2603.04949v4", "archive": "arXiv", "archive_location": "2603.04949", "author": [ { "literal": "Md Farhan Ishmam" }, { "literal": "Kenneth Marino" } ], "citation-key": "arxiv_2603_04949", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1901125b21431e41eacb5d5f0fc7a439d9a637c43762d441ece46a90e135051b", "submitted_at": "2026-03-05T08:43:06Z", "updated_at": "2026-10-14T10:16:21Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2603.04949v4" }, "canonical_source_url": "https://arxiv.org/abs/2603.04949", "catalog_id": "arxiv:2603.04949", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-05", "identifiers": { "arxiv": "2603.04949" }, "record_updated_at": "2026-10-14" }, "genre": "preprint", "id": "arxiv:2603.04949", "issued": { "date-parts": [ [ 2026, 3, 5 ] ] }, "note": "First published: 2026-03-05; Recorded arXiv version: v4; Recorded version updated: 2026-10-14T10:16:21Z.", "title": "TimeWarp: Evaluating Web Agents by Revisiting the Past", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2603.05044v2", "archive": "arXiv", "archive_location": "2603.05044", "author": [ { "literal": "Sicheng Fan" }, { "literal": "Qingyun Shi" }, { "literal": "Shengze Xu" }, { "literal": "Shengbo Cai" }, { "literal": "Tieyong Zeng" }, { "literal": "Li Ling" }, { "literal": "Yanyi Shang" }, { "literal": "Dehan Kong" } ], "citation-key": "arxiv_2603_05044", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fcca36d9a28ace835ede3fa5a93cb9c54608f164240c18bfe007bc945273b460", "submitted_at": "2026-03-05T10:51:34Z", "updated_at": "2026-04-14T08:14:14Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2603.05044v2" }, "canonical_source_url": "https://arxiv.org/abs/2603.05044", "catalog_id": "arxiv:2603.05044", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-05", "identifiers": { "arxiv": "2603.05044" }, "record_updated_at": "2026-04-14" }, "genre": "preprint", "id": "arxiv:2603.05044", "issued": { "date-parts": [ [ 2026, 3, 5 ] ] }, "note": "First published: 2026-03-05; Recorded arXiv version: v2; Recorded version updated: 2026-04-14T08:14:14Z.", "title": "WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2603.05295v3", "archive": "arXiv", "archive_location": "2603.05295", "author": [ { "literal": "Sicheng Fan" }, { "literal": "Rui Wan" }, { "literal": "Yifei Leng" }, { "literal": "Gaoning Liang" }, { "literal": "Li Ling" }, { "literal": "Yanyi Shang" }, { "literal": "Dehan Kong" } ], "citation-key": "arxiv_2603_05295", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "db52246d9f5f305046e6dd14f2ef15440c371678e1db0d05282c84a3667c6f10", "submitted_at": "2026-03-05T15:37:34Z", "updated_at": "2026-04-14T08:41:56Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2603.05295v3" }, "canonical_source_url": "https://arxiv.org/abs/2603.05295", "catalog_id": "arxiv:2603.05295", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-05", "identifiers": { "arxiv": "2603.05295" }, "record_updated_at": "2026-04-14" }, "genre": "preprint", "id": "arxiv:2603.05295", "issued": { "date-parts": [ [ 2026, 3, 5 ] ] }, "note": "First published: 2026-03-05; Recorded arXiv version: v3; Recorded version updated: 2026-04-14T08:41:56Z.", "title": "WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2603.07978v1", "archive": "arXiv", "archive_location": "2603.07978", "author": [ { "literal": "Jiateng Liu" }, { "literal": "Zhenhailong Wang" }, { "literal": "Rushi Wang" }, { "literal": "Bingxuan Li" }, { "literal": "Jeonghwan Kim" }, { "literal": "Aditi Tiwari" }, { "literal": "Pengfei Yu" }, { "literal": "Denghui Zhang" }, { "literal": "Heng Ji" } ], "citation-key": "arxiv_2603_07978", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "77eb68f31d616b8e542dbb41ada67f28bdc21f29f7da3f04a0077c0fa2d10196", "submitted_at": "2026-03-09T05:27:56Z", "updated_at": "2026-03-09T05:27:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.07978v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.07978", "catalog_id": "arxiv:2603.07978", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-09", "identifiers": { "arxiv": "2603.07978" }, "record_updated_at": "2026-03-09" }, "genre": "preprint", "id": "arxiv:2603.07978", "issued": { "date-parts": [ [ 2026, 3, 9 ] ] }, "note": "First published: 2026-03-09; Recorded arXiv version: v1; Recorded version updated: 2026-03-09T05:27:56Z.", "title": "OSExpert: Computer-Use Agents Learning Professional Skills via Exploration", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.10505v1", "archive": "arXiv", "archive_location": "2603.10505", "author": [ { "literal": "Hyungjoo Chae" }, { "literal": "Jungsoo Park" }, { "literal": "Alan Ritter" } ], "citation-key": "arxiv_2603_10505", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "178b2140d0c70ded39fede20bc91d1459d0a4bf65c5cb6a63c09c9db73828513", "submitted_at": "2026-03-11T07:58:53Z", "updated_at": "2026-03-11T07:58:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.10505v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.10505", "catalog_id": "arxiv:2603.10505", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-11", "identifiers": { "arxiv": "2603.10505" }, "record_updated_at": "2026-03-11" }, "genre": "preprint", "id": "arxiv:2603.10505", "issued": { "date-parts": [ [ 2026, 3, 11 ] ] }, "note": "First published: 2026-03-11; Recorded arXiv version: v1; Recorded version updated: 2026-03-11T07:58:53Z.", "title": "Safe and Scalable Web Agent Learning via Recreated Websites", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.12138v1", "archive": "arXiv", "archive_location": "2603.12138", "author": [ { "literal": "Rui Shao" }, { "literal": "Ruize Gao" }, { "literal": "Bin Xie" }, { "literal": "Yixing Li" }, { "literal": "Kaiwen Zhou" }, { "literal": "Shuai Wang" }, { "literal": "Weili Guan" }, { "literal": "Gongwei Chen" } ], "citation-key": "arxiv_2603_12138", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6421a7928b502cd431964e6f84a1a58d4cd16dbbf1d9b3d1ecc1c2b3dae863bf", "submitted_at": "2026-03-12T16:40:59Z", "updated_at": "2026-03-12T16:40:59Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.12138v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.12138", "catalog_id": "arxiv:2603.12138", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-12", "identifiers": { "arxiv": "2603.12138" }, "record_updated_at": "2026-03-12" }, "genre": "preprint", "id": "arxiv:2603.12138", "issued": { "date-parts": [ [ 2026, 3, 12 ] ] }, "note": "First published: 2026-03-12; Recorded arXiv version: v1; Recorded version updated: 2026-03-12T16:40:59Z.", "title": "HATS: Hardness-Aware Trajectory Synthesis for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.17357v1", "archive": "arXiv", "archive_location": "2603.17357", "author": [ { "literal": "Nathan Zhao" } ], "citation-key": "arxiv_2603_17357", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e3b429d277ec776af18977a72aaeb95000a4fedf66aa89c0366ab02120d4cdbe", "submitted_at": "2026-03-18T04:41:16Z", "updated_at": "2026-03-18T04:41:16Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.17357v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.17357", "catalog_id": "arxiv:2603.17357", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-18", "identifiers": { "arxiv": "2603.17357" }, "record_updated_at": "2026-03-18" }, "genre": "preprint", "id": "arxiv:2603.17357", "issued": { "date-parts": [ [ 2026, 3, 18 ] ] }, "note": "First published: 2026-03-18; Recorded arXiv version: v1; Recorded version updated: 2026-03-18T04:41:16Z.", "title": "WebPII: Benchmarking Visual PII Detection for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.24440v1", "archive": "arXiv", "archive_location": "2603.24440", "author": [ { "literal": "Xiangru Jian" }, { "literal": "Shravan Nayak" }, { "literal": "Kevin Qinghong Lin" }, { "literal": "Aarash Feizi" }, { "literal": "Kaixin Li" }, { "literal": "Patrice Bechard" }, { "literal": "Spandana Gella" }, { "literal": "Sai Rajeswar" } ], "citation-key": "arxiv_2603_24440", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "15237fda2f3799314009635017487749dbedc9b1a0ffdd6b56a8d28eaf01481d", "submitted_at": "2026-03-25T15:52:56Z", "updated_at": "2026-03-25T15:52:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.24440v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.24440", "catalog_id": "arxiv:2603.24440", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-25", "identifiers": { "arxiv": "2603.24440" }, "record_updated_at": "2026-03-25" }, "genre": "preprint", "id": "arxiv:2603.24440", "issued": { "date-parts": [ [ 2026, 3, 25 ] ] }, "note": "First published: 2026-03-25; Recorded arXiv version: v1; Recorded version updated: 2026-03-25T15:52:56Z.", "title": "CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.24533v1", "archive": "arXiv", "archive_location": "2603.24533", "author": [ { "literal": "Zichuan Lin" }, { "literal": "Feiyu Liu" }, { "literal": "Yijun Yang" }, { "literal": "Jiafei Lyu" }, { "literal": "Yiming Gao" }, { "literal": "Yicheng Liu" }, { "literal": "Zhicong Lu" }, { "literal": "Yangbin Yu" }, { "literal": "Mingyu Yang" }, { "literal": "Junyou Li" }, { "literal": "Deheng Ye" }, { "literal": "Jie Jiang" } ], "citation-key": "arxiv_2603_24533", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aa03c8716edf782ce1a86e404107aa2569be63484dfedb472d3710dc82f405d0", "submitted_at": "2026-03-25T17:10:29Z", "updated_at": "2026-03-25T17:10:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.24533v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.24533", "catalog_id": "arxiv:2603.24533", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-25", "identifiers": { "arxiv": "2603.24533" }, "record_updated_at": "2026-03-25" }, "genre": "preprint", "id": "arxiv:2603.24533", "issued": { "date-parts": [ [ 2026, 3, 25 ] ] }, "note": "First published: 2026-03-25; Recorded arXiv version: v1; Recorded version updated: 2026-03-25T17:10:29Z.", "title": "UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.02345v1", "archive": "arXiv", "archive_location": "2604.02345", "author": [ { "literal": "Mengzhou Wu" }, { "literal": "Yuzhe Guo" }, { "literal": "Yuan Cao" }, { "literal": "Haochuan Lu" }, { "literal": "Songhe Zhu" }, { "literal": "Pingzhe Qu" }, { "literal": "Xin Chen" }, { "literal": "Kang Qin" }, { "literal": "Zhongpu Wang" }, { "literal": "Xiaode Zhang" }, { "literal": "Xinyi Wang" }, { "literal": "Wei Dai" }, { "literal": "Gang Cao" }, { "literal": "Yuetang Deng" }, { "literal": "Zhi Gong" }, { "literal": "Dezhi Ran" }, { "literal": "Linyi Li" }, { "literal": "Wei Yang" }, { "literal": "Tao Xie" } ], "citation-key": "arxiv_2604_02345", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bac86c2ff2bf18feb3edfbe76285d33718d0c6d9564aff5a9d62f8778cdc5147", "submitted_at": "2026-02-11T17:02:38Z", "updated_at": "2026-02-11T17:02:38Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.02345v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.02345", "catalog_id": "arxiv:2604.02345", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-11", "identifiers": { "arxiv": "2604.02345" }, "record_updated_at": "2026-02-11" }, "genre": "preprint", "id": "arxiv:2604.02345", "issued": { "date-parts": [ [ 2026, 2, 11 ] ] }, "note": "First published: 2026-02-11; Recorded arXiv version: v1; Recorded version updated: 2026-02-11T17:02:38Z.", "title": "UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.06126v1", "archive": "arXiv", "archive_location": "2604.06126", "author": [ { "literal": "Pranjal Aggarwal" }, { "literal": "Graham Neubig" }, { "literal": "Sean Welleck" } ], "citation-key": "arxiv_2604_06126", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fdd9cb6daad8832261ebe861fc1cb74429b819305e14ecfeb9698616013e6ac8", "submitted_at": "2026-04-07T17:38:15Z", "updated_at": "2026-04-07T17:38:15Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.06126v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.06126", "catalog_id": "arxiv:2604.06126", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-07", "identifiers": { "arxiv": "2604.06126" }, "record_updated_at": "2026-04-07" }, "genre": "preprint", "id": "arxiv:2604.06126", "issued": { "date-parts": [ [ 2026, 4, 7 ] ] }, "note": "First published: 2026-04-07; Recorded arXiv version: v1; Recorded version updated: 2026-04-07T17:38:15Z.", "title": "Gym-Anything: Turn any Software into an Agent Environment", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.08516v1", "archive": "arXiv", "archive_location": "2604.08516", "author": [ { "literal": "Tanmay Gupta" }, { "literal": "Piper Wolters" }, { "literal": "Zixian Ma" }, { "literal": "Peter Sushko" }, { "literal": "Rock Yuren Pang" }, { "literal": "Diego Llanes" }, { "literal": "Yue Yang" }, { "literal": "Taira Anderson" }, { "literal": "Boyuan Zheng" }, { "literal": "Zhongzheng Ren" }, { "literal": "Harsh Trivedi" }, { "literal": "Taylor Blanton" }, { "literal": "Caleb Ouellette" }, { "literal": "Winson Han" }, { "literal": "Ali Farhadi" }, { "literal": "Ranjay Krishna" } ], "citation-key": "arxiv_2604_08516", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dbc0d512a11b88a9036d06d0fcc26a8ab0d0bc54fad986d4b6225c8073897bc2", "submitted_at": "2026-04-09T17:54:02Z", "updated_at": "2026-04-09T17:54:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.08516v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.08516", "catalog_id": "arxiv:2604.08516", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-09", "identifiers": { "arxiv": "2604.08516" }, "record_updated_at": "2026-04-09" }, "genre": "preprint", "id": "arxiv:2604.08516", "issued": { "date-parts": [ [ 2026, 4, 9 ] ] }, "note": "First published: 2026-04-09; Recorded arXiv version: v1; Recorded version updated: 2026-04-09T17:54:02Z.", "title": "MolmoWeb: Open Visual Web Agent and Open Data for the Open Web", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.09815v1", "archive": "arXiv", "archive_location": "2604.09815", "author": [ { "literal": "Tiantian He" }, { "literal": "Yihang Chen" }, { "literal": "Keyue Jiang" }, { "literal": "Ka Yiu Lee" }, { "literal": "Kaiwen Zhou" }, { "literal": "Kun Shao" }, { "literal": "Shuai Wang" } ], "citation-key": "arxiv_2604_09815", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dd2bc0ee1955dbc8e98a9306a3d6260251cbab89d36ac117e4dc49b6fa99766e", "submitted_at": "2026-04-10T18:46:05Z", "updated_at": "2026-04-10T18:46:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.09815v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.09815", "catalog_id": "arxiv:2604.09815", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-10", "identifiers": { "arxiv": "2604.09815" }, "record_updated_at": "2026-04-10" }, "genre": "preprint", "id": "arxiv:2604.09815", "issued": { "date-parts": [ [ 2026, 4, 10 ] ] }, "note": "First published: 2026-04-10; Recorded arXiv version: v1; Recorded version updated: 2026-04-10T18:46:05Z.", "title": "EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.10988v1", "archive": "arXiv", "archive_location": "2604.10988", "author": [ { "literal": "Peng Yuan" }, { "literal": "Yuyang Yin" }, { "literal": "Yuxuan Cai" }, { "literal": "Zheng Wei" } ], "citation-key": "arxiv_2604_10988", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1db8d789fb8ba2d5e61ca24536670fd83491c305f532adfecf7193821f7eea52", "submitted_at": "2026-04-13T04:45:27Z", "updated_at": "2026-04-13T04:45:27Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.10988v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.10988", "catalog_id": "arxiv:2604.10988", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-13", "identifiers": { "arxiv": "2604.10988" }, "record_updated_at": "2026-04-13" }, "genre": "preprint", "id": "arxiv:2604.10988", "issued": { "date-parts": [ [ 2026, 4, 13 ] ] }, "note": "First published: 2026-04-13; Recorded arXiv version: v1; Recorded version updated: 2026-04-13T04:45:27Z.", "title": "WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.12284v1", "archive": "arXiv", "archive_location": "2604.12284", "author": [ { "literal": "Yulin Chen" }, { "literal": "Tri Cao" }, { "literal": "Haoran Li" }, { "literal": "Yue Liu" }, { "literal": "Yibo Li" }, { "literal": "Yufei He" }, { "literal": "Le Minh Khoi" }, { "literal": "Yangqiu Song" }, { "literal": "Shuicheng Yan" }, { "literal": "Bryan Hooi" } ], "citation-key": "arxiv_2604_12284", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "64d4323050a5ad0f7265231337eb22a4c0823cee41587099c8bdc5db6b320dea", "submitted_at": "2026-04-14T04:50:35Z", "updated_at": "2026-04-14T04:50:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.12284v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.12284", "catalog_id": "arxiv:2604.12284", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-14", "identifiers": { "arxiv": "2604.12284" }, "record_updated_at": "2026-04-14" }, "genre": "preprint", "id": "arxiv:2604.12284", "issued": { "date-parts": [ [ 2026, 4, 14 ] ] }, "note": "First published: 2026-04-14; Recorded arXiv version: v1; Recorded version updated: 2026-04-14T04:50:35Z.", "title": "WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.15093v1", "archive": "arXiv", "archive_location": "2604.15093", "author": [ { "literal": "Kanzhi Cheng" }, { "literal": "Zehao Li" }, { "literal": "Zheng Ma" }, { "literal": "Nuo Chen" }, { "literal": "Jialin Cao" }, { "literal": "Qiushi Sun" }, { "literal": "Zichen Ding" }, { "literal": "Fangzhi Xu" }, { "literal": "Hang Yan" }, { "literal": "Jiajun Chen" }, { "literal": "Anh Tuan Luu" }, { "literal": "Jianbing Zhang" }, { "literal": "Lewei Lu" }, { "literal": "Dahua Lin" } ], "citation-key": "arxiv_2604_15093", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "12c2e5e2ae9bdc871bb63d195194c5387129accf5e8b26d12b21650b92fe82b6", "submitted_at": "2026-04-16T14:53:08Z", "updated_at": "2026-04-16T14:53:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.15093v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.15093", "catalog_id": "arxiv:2604.15093", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-16", "identifiers": { "arxiv": "2604.15093" }, "record_updated_at": "2026-04-16" }, "genre": "preprint", "id": "arxiv:2604.15093", "issued": { "date-parts": [ [ 2026, 4, 16 ] ] }, "note": "First published: 2026-04-16; Recorded arXiv version: v1; Recorded version updated: 2026-04-16T14:53:08Z.", "title": "OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.24441v1", "archive": "arXiv", "archive_location": "2604.24441", "author": [ { "literal": "Hongxin Li" }, { "literal": "Xiping Wang" }, { "literal": "Jingran Su" }, { "literal": "Zheng Ju" }, { "literal": "Yuntao Chen" }, { "literal": "Qing Li" }, { "literal": "Zhaoxiang Zhang" } ], "citation-key": "arxiv_2604_24441", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "65325912365effe8adbc39301a378d7526c60d1185691f3a89cb8acd4aa53c3f", "submitted_at": "2026-04-27T13:06:27Z", "updated_at": "2026-04-27T13:06:27Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.24441v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.24441", "catalog_id": "arxiv:2604.24441", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-27", "identifiers": { "arxiv": "2604.24441" }, "record_updated_at": "2026-04-27" }, "genre": "preprint", "id": "arxiv:2604.24441", "issued": { "date-parts": [ [ 2026, 4, 27 ] ] }, "note": "First published: 2026-04-27; Recorded arXiv version: v1; Recorded version updated: 2026-04-27T13:06:27Z.", "title": "AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.27253v1", "archive": "arXiv", "archive_location": "2604.27253", "author": [ { "literal": "Fazle Elahi Faisal" }, { "literal": "Qianhui Wu" }, { "literal": "Baolin Peng" }, { "literal": "Jianfeng Gao" } ], "citation-key": "arxiv_2604_27253", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "276d8a62192c0ad576a1d986bb27d3978963b93466a822858e3313957dd83a81", "submitted_at": "2026-04-29T22:57:35Z", "updated_at": "2026-04-29T22:57:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.27253v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.27253", "catalog_id": "arxiv:2604.27253", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-29", "identifiers": { "arxiv": "2604.27253" }, "record_updated_at": "2026-04-29" }, "genre": "preprint", "id": "arxiv:2604.27253", "issued": { "date-parts": [ [ 2026, 4, 29 ] ] }, "note": "First published: 2026-04-29; Recorded arXiv version: v1; Recorded version updated: 2026-04-29T22:57:35Z.", "title": "AutoSurfer -- Teaching Web Agents through Comprehensive Surfing, Learning, and Modeling", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.06761v1", "archive": "arXiv", "archive_location": "2605.06761", "author": [ { "literal": "Oğuzhan Fatih Kar" }, { "literal": "Roman Bachmann" }, { "literal": "Yuanzheng Gong" }, { "literal": "Anders Boesen Lindbo Larsen" }, { "literal": "Afshin Dehghan" } ], "citation-key": "arxiv_2605_06761", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2e1fb158dad88d32f8754ac27f12346ba8fbe5f9a5e736fba3e81390071895a3", "submitted_at": "2026-05-07T17:17:10Z", "updated_at": "2026-05-07T17:17:10Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.06761v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.06761", "catalog_id": "arxiv:2605.06761", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-07", "identifiers": { "arxiv": "2605.06761" }, "record_updated_at": "2026-05-07" }, "genre": "preprint", "id": "arxiv:2605.06761", "issued": { "date-parts": [ [ 2026, 5, 7 ] ] }, "note": "First published: 2026-05-07; Recorded arXiv version: v1; Recorded version updated: 2026-05-07T17:17:10Z.", "title": "Weblica: Scalable and Reproducible Training Environments for Visual Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.10347v2", "archive": "arXiv", "archive_location": "2605.10347", "author": [ { "literal": "Weikai Xu" }, { "literal": "Kun Huang" }, { "literal": "Yunren Feng" }, { "literal": "Jiaxing Li" }, { "literal": "Yuhan Chen" }, { "literal": "Yuxuan Liu" }, { "literal": "Zhizheng Jiang" }, { "literal": "Heng Qu" }, { "literal": "Pengzhi Gao" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Xiaolin Hu" }, { "literal": "Bo An" } ], "citation-key": "arxiv_2605_10347", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4374ec1b7c44804bb78ea56bd0aa3214083419f37780d79c5fcfb68468727bbf", "submitted_at": "2026-05-11T10:49:31Z", "updated_at": "2026-05-22T05:43:30Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.10347v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.10347", "catalog_id": "arxiv:2605.10347", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-11", "identifiers": { "arxiv": "2605.10347" }, "record_updated_at": "2026-05-22" }, "genre": "preprint", "id": "arxiv:2605.10347", "issued": { "date-parts": [ [ 2026, 5, 11 ] ] }, "note": "First published: 2026-05-11; Recorded arXiv version: v2; Recorded version updated: 2026-05-22T05:43:30Z.", "title": "How Mobile World Model Guides GUI Agents?", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2605.12481v2", "archive": "arXiv", "archive_location": "2605.12481", "author": [ { "literal": "Xuhao Hu" }, { "literal": "Xi Zhang" }, { "literal": "Haiyang Xu" }, { "literal": "Kyle Qiao" }, { "literal": "Jingyi Yang" }, { "literal": "Xuanjing Huang" }, { "literal": "Jing Shao" }, { "literal": "Ming Yan" }, { "literal": "Jieping Ye" } ], "citation-key": "arxiv_2605_12481", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "09128e90b925ac0cd2cf6e967853180bbef1e97a0960c22065f1b0b50c30d58b", "submitted_at": "2026-05-12T17:57:04Z", "updated_at": "2026-09-19T14:53:46Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.12481v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.12481", "catalog_id": "arxiv:2605.12481", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-12", "identifiers": { "arxiv": "2605.12481" }, "record_updated_at": "2026-09-19" }, "genre": "preprint", "id": "arxiv:2605.12481", "issued": { "date-parts": [ [ 2026, 5, 12 ] ] }, "note": "First published: 2026-05-12; Recorded arXiv version: v2; Recorded version updated: 2026-09-19T14:53:46Z.", "title": "ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2605.12501v1", "archive": "arXiv", "archive_location": "2605.12501", "author": [ { "literal": "Miaosen Zhang" }, { "literal": "Xiaohan Zhao" }, { "literal": "Zhihong Tan" }, { "literal": "Zhou Huoshen" }, { "literal": "Yijia Fan" }, { "literal": "Yifan Yang" }, { "literal": "Kai Qiu" }, { "literal": "Bei Liu" }, { "literal": "Justin Wagle" }, { "literal": "Chenzhong Yin" }, { "literal": "Mingxi Cheng" }, { "literal": "Ji Li" }, { "literal": "Qi Dai" }, { "literal": "Chong Luo" }, { "literal": "Xu Yang" }, { "literal": "Xin Geng" }, { "literal": "Baining Guo" } ], "citation-key": "arxiv_2605_12501", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1fb57ba3cd858513d1da58d64a7c85388f12e331c9ea9f89204be5f43e6fec38", "submitted_at": "2026-05-12T17:59:58Z", "updated_at": "2026-05-12T17:59:58Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.12501v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.12501", "catalog_id": "arxiv:2605.12501", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-12", "identifiers": { "arxiv": "2605.12501" }, "record_updated_at": "2026-05-12" }, "genre": "preprint", "id": "arxiv:2605.12501", "issued": { "date-parts": [ [ 2026, 5, 12 ] ] }, "note": "First published: 2026-05-12; Recorded arXiv version: v1; Recorded version updated: 2026-05-12T17:59:58Z.", "title": "Covering Human Action Space for Computer Use: Data Synthesis and Benchmark", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.16402v1", "archive": "arXiv", "archive_location": "2605.16402", "author": [ { "literal": "Haoren Zhao" }, { "literal": "Tianyi Chen" }, { "literal": "Zhen Wang" } ], "citation-key": "arxiv_2605_16402", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "671f33dd87a7ebf9233494ef6fa0efd9c9772a3951f3c218bf4de822825f7af2", "submitted_at": "2026-05-13T02:48:52Z", "updated_at": "2026-05-13T02:48:52Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.16402v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.16402", "catalog_id": "arxiv:2605.16402", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-13", "identifiers": { "arxiv": "2605.16402" }, "record_updated_at": "2026-05-13" }, "genre": "preprint", "id": "arxiv:2605.16402", "issued": { "date-parts": [ [ 2026, 5, 13 ] ] }, "note": "First published: 2026-05-13; Recorded arXiv version: v1; Recorded version updated: 2026-05-13T02:48:52Z.", "title": "WinDeskGround: A Benchmark for Robust GUI Grounding in Complex Multi-Window Desktop Environments", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.17656v1", "archive": "arXiv", "archive_location": "2605.17656", "author": [ { "literal": "Athar Parvez" }, { "literal": "Muhammad Jawad Mufti" }, { "literal": "Muqaddas Gull" }, { "literal": "Omar Hammad" } ], "citation-key": "arxiv_2605_17656", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ff95e0b071508592190ba236741c1c01200dd38fdc74c31b2cc4d1bf8143ae9c", "submitted_at": "2026-05-17T21:14:32Z", "updated_at": "2026-05-17T21:14:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.17656v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.17656", "catalog_id": "arxiv:2605.17656", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-17", "identifiers": { "arxiv": "2605.17656" }, "record_updated_at": "2026-05-17" }, "genre": "preprint", "id": "arxiv:2605.17656", "issued": { "date-parts": [ [ 2026, 5, 17 ] ] }, "note": "First published: 2026-05-17; Recorded arXiv version: v1; Recorded version updated: 2026-05-17T21:14:32Z.", "title": "MUIAnno: An Expert-Annotated Dataset and Evaluation Benchmark for Mobile UI Understanding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.18652v1", "archive": "arXiv", "archive_location": "2605.18652", "author": [ { "literal": "Ziyun Zeng" }, { "literal": "Hang Hua" }, { "literal": "Bocheng Zou" }, { "literal": "Mu Cai" }, { "literal": "Rogerio Feris" }, { "literal": "Jiebo Luo" } ], "citation-key": "arxiv_2605_18652", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d96c8844274f79adea167169a0853e3a7cd82fee4a8a666913f97898a0836e7c", "submitted_at": "2026-05-18T16:57:36Z", "updated_at": "2026-05-18T16:57:36Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.18652v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.18652", "catalog_id": "arxiv:2605.18652", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-18", "identifiers": { "arxiv": "2605.18652" }, "record_updated_at": "2026-05-18" }, "genre": "preprint", "id": "arxiv:2605.18652", "issued": { "date-parts": [ [ 2026, 5, 18 ] ] }, "note": "First published: 2026-05-18; Recorded arXiv version: v1; Recorded version updated: 2026-05-18T16:57:36Z.", "title": "MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.19769v1", "archive": "arXiv", "archive_location": "2605.19769", "author": [ { "literal": "Jinbiao Wei" }, { "literal": "Qianran Ma" }, { "literal": "Yilun Zhao" }, { "literal": "Xiao Zhou" }, { "literal": "Kangqi Ni" }, { "literal": "Guo Gan" }, { "literal": "Arman Cohan" } ], "citation-key": "arxiv_2605_19769", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0a93d880793018d1b47a39e0487e3be76550fd2b49de9535b2913e9f08159074", "submitted_at": "2026-05-19T12:40:29Z", "updated_at": "2026-05-19T12:40:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.19769v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.19769", "catalog_id": "arxiv:2605.19769", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-19", "identifiers": { "arxiv": "2605.19769" }, "record_updated_at": "2026-05-19" }, "genre": "preprint", "id": "arxiv:2605.19769", "issued": { "date-parts": [ [ 2026, 5, 19 ] ] }, "note": "First published: 2026-05-19; Recorded arXiv version: v1; Recorded version updated: 2026-05-19T12:40:29Z.", "title": "OpenComputer: Verifiable Software Worlds for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.20291v2", "archive": "arXiv", "archive_location": "2605.20291", "author": [ { "literal": "Fatemeh Pesaran Zadeh" }, { "literal": "Seyeon Choi" }, { "literal": "Xing Han Lù" }, { "literal": "Siva Reddy" }, { "literal": "Gunhee Kim" } ], "citation-key": "arxiv_2605_20291", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aa6e11bae4d952d79276543ced6f81193b36868a6222fe51ee7b0816aa72fbab", "submitted_at": "2026-05-19T09:19:01Z", "updated_at": "2026-05-26T02:53:26Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.20291v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.20291", "catalog_id": "arxiv:2605.20291", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-19", "identifiers": { "arxiv": "2605.20291" }, "record_updated_at": "2026-05-26" }, "genre": "preprint", "id": "arxiv:2605.20291", "issued": { "date-parts": [ [ 2026, 5, 19 ] ] }, "note": "First published: 2026-05-19; Recorded arXiv version: v2; Recorded version updated: 2026-05-26T02:53:26Z.", "title": "Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2605.25160v2", "archive": "arXiv", "archive_location": "2605.25160", "author": [ { "literal": "Guohong Liu" }, { "literal": "Jialei Ye" }, { "literal": "Pengzhi Gao" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Yunxin Liu" }, { "literal": "Yuanchun Li" } ], "citation-key": "arxiv_2605_25160", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "eb40c8bf005d56139d263e1b5dc4553ddcd68522124686b7f0865e6d8d1725ad", "submitted_at": "2026-05-24T16:33:14Z", "updated_at": "2026-06-18T02:24:07Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.25160v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.25160", "catalog_id": "arxiv:2605.25160", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-24", "identifiers": { "arxiv": "2605.25160" }, "record_updated_at": "2026-06-18" }, "genre": "preprint", "id": "arxiv:2605.25160", "issued": { "date-parts": [ [ 2026, 5, 24 ] ] }, "note": "First published: 2026-05-24; Recorded arXiv version: v2; Recorded version updated: 2026-06-18T02:24:07Z.", "title": "ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2605.25624v2", "archive": "arXiv", "archive_location": "2605.25624", "author": [ { "literal": "Bowen Wang" }, { "literal": "Dunjie Lu" }, { "literal": "Junli Wang" }, { "literal": "Tianyi Bai" }, { "literal": "Shixuan Liu" }, { "literal": "Zhipeng Zhang" }, { "literal": "Haiquan Wang" }, { "literal": "Hao Hu" }, { "literal": "Tianbao Xie" }, { "literal": "Shuai Bai" }, { "literal": "Dayiheng Liu" }, { "literal": "Que Shen" }, { "literal": "Junyang Lin" }, { "literal": "Tao Yu" } ], "citation-key": "arxiv_2605_25624", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ecc0712f55ee90c237f9a48e013e396b1082f932a485c22d8249d1da7acbf307", "submitted_at": "2026-05-25T09:28:03Z", "updated_at": "2026-06-08T08:32:35Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.25624v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.25624", "catalog_id": "arxiv:2605.25624", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-25", "identifiers": { "arxiv": "2605.25624" }, "record_updated_at": "2026-06-08" }, "genre": "preprint", "id": "arxiv:2605.25624", "issued": { "date-parts": [ [ 2026, 5, 25 ] ] }, "note": "First published: 2026-05-25; Recorded arXiv version: v2; Recorded version updated: 2026-06-08T08:32:35Z.", "title": "CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2605.26086v1", "archive": "arXiv", "archive_location": "2605.26086", "author": [ { "literal": "Yusong Lin" }, { "literal": "Xinyuan Liang" }, { "literal": "Haiyang Wang" }, { "literal": "Qipeng Gu" }, { "literal": "Siqi Cheng" }, { "literal": "Jiangui Chen" }, { "literal": "Shuzhe Wu" }, { "literal": "Feiyang Pan" }, { "literal": "Lue Fan" }, { "literal": "Sanyuan Zhao" }, { "literal": "Dandan Tu" } ], "citation-key": "arxiv_2605_26086", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "27999553928305cfa4223011feb3f9c2decda8a861e5800865537a81c7c08832", "submitted_at": "2026-05-25T17:50:04Z", "updated_at": "2026-05-25T17:50:04Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.26086v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.26086", "catalog_id": "arxiv:2605.26086", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-25", "identifiers": { "arxiv": "2605.26086" }, "record_updated_at": "2026-05-25" }, "genre": "preprint", "id": "arxiv:2605.26086", "issued": { "date-parts": [ [ 2026, 5, 25 ] ] }, "note": "First published: 2026-05-25; Recorded arXiv version: v1; Recorded version updated: 2026-05-25T17:50:04Z.", "title": "Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.28116v1", "archive": "arXiv", "archive_location": "2605.28116", "author": [ { "literal": "Ruoqi Guo" }, { "literal": "Yi Liu" }, { "literal": "Gelei Deng" }, { "literal": "Yiheng Xiong" }, { "literal": "Yuekang Li" }, { "literal": "Ying Zhang" }, { "literal": "Leo Yu Zhang" }, { "literal": "Lida Zhao" }, { "literal": "Ji Jie" }, { "literal": "Yuxiao Lu" } ], "citation-key": "arxiv_2605_28116", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4f39433695b9574b275fc844ca6b10a43baf66aed57048bf841f41bf08d4ac9a", "submitted_at": "2026-05-27T08:09:53Z", "updated_at": "2026-05-27T08:09:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.28116v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.28116", "catalog_id": "arxiv:2605.28116", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-27", "identifiers": { "arxiv": "2605.28116" }, "record_updated_at": "2026-05-27" }, "genre": "preprint", "id": "arxiv:2605.28116", "issued": { "date-parts": [ [ 2026, 5, 27 ] ] }, "note": "First published: 2026-05-27; Recorded arXiv version: v1; Recorded version updated: 2026-05-27T08:09:53Z.", "title": "MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.28534v1", "archive": "arXiv", "archive_location": "2605.28534", "author": [ { "literal": "Zheng Wu" }, { "literal": "Chengcheng Han" }, { "literal": "Zhengxi Lu" }, { "literal": "Tianjie Ju" }, { "literal": "Yanyu Chen" }, { "literal": "Qi Gu" }, { "literal": "Xunliang Cai" }, { "literal": "Zhuosheng Zhang" } ], "citation-key": "arxiv_2605_28534", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "78a5f5d7df9a8b6f1dbdb5693849c728a4b97e1f25c6e2e24d0c2418628c64e7", "submitted_at": "2026-05-27T14:29:41Z", "updated_at": "2026-05-27T14:29:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.28534v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.28534", "catalog_id": "arxiv:2605.28534", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-27", "identifiers": { "arxiv": "2605.28534" }, "record_updated_at": "2026-05-27" }, "genre": "preprint", "id": "arxiv:2605.28534", "issued": { "date-parts": [ [ 2026, 5, 27 ] ] }, "note": "First published: 2026-05-27; Recorded arXiv version: v1; Recorded version updated: 2026-05-27T14:29:41Z.", "title": "GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.29486v3", "archive": "arXiv", "archive_location": "2605.29486", "author": [ { "literal": "Yuxuan Liu" }, { "literal": "Xin Lai" }, { "literal": "Junyi Li" }, { "literal": "Pengyuan Lyu" }, { "literal": "Jason" }, { "literal": "Yiduo Guo" }, { "literal": "Zhengyao Fang" }, { "literal": "Yang Ding" }, { "literal": "Yi Zhang" }, { "literal": "Weinong Wang" }, { "literal": "Huawen Shen" }, { "literal": "Xingran Zhou" }, { "literal": "Liang Wu" }, { "literal": "Fei Tang" }, { "literal": "Sunqi Fan" }, { "literal": "Shangpin Peng" }, { "literal": "Zheng Ruan" }, { "literal": "Anran Zhang" }, { "literal": "Chengquan Zhang" }, { "literal": "Han Hu" }, { "literal": "Benyou Wang" }, { "literal": "Ji-Rong Wen" }, { "literal": "Rui Yan" }, { "literal": "Zhengyang Tang" } ], "citation-key": "arxiv_2605_29486", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a41cb1a93e6aa6ba8fbc7dca55415577ab5880a6592e9b0bee5b12b5a7732cbf", "submitted_at": "2026-05-28T07:14:15Z", "updated_at": "2026-09-28T15:27:12Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2605.29486v3" }, "canonical_source_url": "https://arxiv.org/abs/2605.29486", "catalog_id": "arxiv:2605.29486", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-28", "identifiers": { "arxiv": "2605.29486" }, "record_updated_at": "2026-09-28" }, "genre": "preprint", "id": "arxiv:2605.29486", "issued": { "date-parts": [ [ 2026, 5, 28 ] ] }, "note": "First published: 2026-05-28; Recorded arXiv version: v3; Recorded version updated: 2026-09-28T15:27:12Z.", "title": "PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2606.06322v1", "archive": "arXiv", "archive_location": "2606.06322", "author": [ { "literal": "Nathan Bout" }, { "literal": "Maxime Langevin" }, { "literal": "Ronan Riochet" } ], "citation-key": "arxiv_2606_06322", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "27ffcb10d966946de9fa2353c4b96798e5f090bdfdc5610f5e8a5c6233cf70ea", "submitted_at": "2026-06-04T15:57:29Z", "updated_at": "2026-06-04T15:57:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.06322v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.06322", "catalog_id": "arxiv:2606.06322", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-04", "identifiers": { "arxiv": "2606.06322" }, "record_updated_at": "2026-06-04" }, "genre": "preprint", "id": "arxiv:2606.06322", "issued": { "date-parts": [ [ 2026, 6, 4 ] ] }, "note": "First published: 2026-06-04; Recorded arXiv version: v1; Recorded version updated: 2026-06-04T15:57:29Z.", "title": "DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.12485v2", "archive": "arXiv", "archive_location": "2606.12485", "author": [ { "literal": "Longkun Hao" }, { "literal": "Hongyu Lin" }, { "literal": "Hao Li" }, { "literal": "Zhuowen Liu" }, { "literal": "Zhichao Yang" }, { "literal": "Haojie Hao" }, { "literal": "Dongshuo Huang" }, { "literal": "Haitao Yang" }, { "literal": "Hongyu Ge" }, { "literal": "Ming jie Xie" }, { "literal": "Yanjun Wu" }, { "literal": "Zi Hao Yin" }, { "literal": "Yan Bai" }, { "literal": "Yihang Lou" } ], "citation-key": "arxiv_2606_12485", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "408c8e4bc46072641819f7ab1d97ba98604c06ba7e91049b8d0e29e1a8ff2db1", "submitted_at": "2026-06-10T08:56:27Z", "updated_at": "2026-08-17T02:54:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.12485v2" }, "canonical_source_url": "https://arxiv.org/abs/2606.12485", "catalog_id": "arxiv:2606.12485", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-10", "identifiers": { "arxiv": "2606.12485" }, "record_updated_at": "2026-08-17" }, "genre": "preprint", "id": "arxiv:2606.12485", "issued": { "date-parts": [ [ 2026, 6, 10 ] ] }, "note": "First published: 2026-06-10; Recorded arXiv version: v2; Recorded version updated: 2026-08-17T02:54:44Z.", "title": "Speculative Rollback Correction for Quality-Diverse Web Agent Imitation", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2606.14579v1", "archive": "arXiv", "archive_location": "2606.14579", "author": [ { "literal": "Xinyu Qiu" }, { "literal": "Yunzhu Zhang" }, { "literal": "Heng Jia" }, { "literal": "Shuheng Shen" }, { "literal": "Changhua Meng" }, { "literal": "Linchao Zhu" } ], "citation-key": "arxiv_2606_14579", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1a5e949a760f236c08ae3cebc32d8a52220b1101f5324770d40bd7d054351f6a", "submitted_at": "2026-06-12T15:58:18Z", "updated_at": "2026-06-12T15:58:18Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.14579v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.14579", "catalog_id": "arxiv:2606.14579", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-12", "identifiers": { "arxiv": "2606.14579" }, "record_updated_at": "2026-06-12" }, "genre": "preprint", "id": "arxiv:2606.14579", "issued": { "date-parts": [ [ 2026, 6, 12 ] ] }, "note": "First published: 2026-06-12; Recorded arXiv version: v1; Recorded version updated: 2026-06-12T15:58:18Z.", "title": "VISTA: View-Consistent Self-Verified Training for GUI Grounding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.17321v1", "archive": "arXiv", "archive_location": "2606.17321", "author": [ { "literal": "Jaehun Jung" }, { "literal": "Ximing Lu" }, { "literal": "Brandon Cui" }, { "literal": "Muhammad Khalifa" }, { "literal": "Shaokun Zhang" }, { "literal": "Hao Zhang" }, { "literal": "Jin Xu" }, { "literal": "Amala Sanjay Deshmukh" }, { "literal": "Karan Sapra" }, { "literal": "Andrew Tao" }, { "literal": "Yejin Choi" }, { "literal": "Jan Kautz" }, { "literal": "Mingjie Liu" }, { "literal": "Yi Dong" } ], "citation-key": "arxiv_2606_17321", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d7e6e0b66f2923cb66ab7aa404bedf9f4e1c73ae00df2e9fbfa7a5c3795cac4c", "submitted_at": "2026-06-15T22:04:11Z", "updated_at": "2026-06-15T22:04:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.17321v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.17321", "catalog_id": "arxiv:2606.17321", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-15", "identifiers": { "arxiv": "2606.17321" }, "record_updated_at": "2026-06-15" }, "genre": "preprint", "id": "arxiv:2606.17321", "issued": { "date-parts": [ [ 2026, 6, 15 ] ] }, "note": "First published: 2026-06-15; Recorded arXiv version: v1; Recorded version updated: 2026-06-15T22:04:11Z.", "title": "ProCUA-SFT Technical Report", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.18890v1", "archive": "arXiv", "archive_location": "2606.18890", "author": [ { "literal": "Zhimin Fan" }, { "literal": "Hongwei Yu" }, { "literal": "Yeqing Shen" }, { "literal": "Haolong Yan" }, { "literal": "Guozhen Peng" }, { "literal": "Tianhao Peng" }, { "literal": "Yudong Zhang" }, { "literal": "Xiaowen Zhang" }, { "literal": "Kaijun Tan" }, { "literal": "Zheng Ge" }, { "literal": "Xiangyu Zhang" }, { "literal": "Daxin Jiang" } ], "citation-key": "arxiv_2606_18890", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1929dfb5074e159d83006c7bbb470237a0c557e0723ac631116aa5e0369f9247", "submitted_at": "2026-06-17T10:07:51Z", "updated_at": "2026-06-17T10:07:51Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.18890v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.18890", "catalog_id": "arxiv:2606.18890", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-17", "identifiers": { "arxiv": "2606.18890" }, "record_updated_at": "2026-06-17" }, "genre": "preprint", "id": "arxiv:2606.18890", "issued": { "date-parts": [ [ 2026, 6, 17 ] ] }, "note": "First published: 2026-06-17; Recorded arXiv version: v1; Recorded version updated: 2026-06-17T10:07:51Z.", "title": "Skill-Guided Continuation Distillation for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.19926v1", "archive": "arXiv", "archive_location": "2606.19926", "author": [ { "literal": "Guangyi Liu" }, { "literal": "Gao Wu" }, { "literal": "Congxiao Liu" }, { "literal": "Pengxiang Zhao" }, { "literal": "Liang Liu" }, { "literal": "Mading Li" }, { "literal": "Qi Zhang" }, { "literal": "Mengyan Wang" }, { "literal": "Liang Guo" }, { "literal": "Yong Liu" } ], "citation-key": "arxiv_2606_19926", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cbbb1bd57057e465ce9d991d3f6e2bb52112fc133a5846fc8cb6ce51eddc2121", "submitted_at": "2026-06-18T08:26:09Z", "updated_at": "2026-06-18T08:26:09Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.19926v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.19926", "catalog_id": "arxiv:2606.19926", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-18", "identifiers": { "arxiv": "2606.19926" }, "record_updated_at": "2026-06-18" }, "genre": "preprint", "id": "arxiv:2606.19926", "issued": { "date-parts": [ [ 2026, 6, 18 ] ] }, "note": "First published: 2026-06-18; Recorded arXiv version: v1; Recorded version updated: 2026-06-18T08:26:09Z.", "title": "MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.19930v2", "archive": "arXiv", "archive_location": "2606.19930", "author": [ { "literal": "Guangyi Liu" }, { "literal": "Pengxiang Zhao" }, { "literal": "Gao Wu" }, { "literal": "Yiwen Yin" }, { "literal": "Mading Li" }, { "literal": "Liang Liu" }, { "literal": "Congxiao Liu" }, { "literal": "Zhang Qi" }, { "literal": "Mengyan Wang" }, { "literal": "Liang Guo" }, { "literal": "Jiangning Zhang" }, { "literal": "Yong Liu" } ], "citation-key": "arxiv_2606_19930", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cab809618ea4e218da26b4ae11bf937859c3a4bc240c91dd27b3a0d333737069", "submitted_at": "2026-06-18T08:29:33Z", "updated_at": "2026-08-07T03:54:59Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.19930v2" }, "canonical_source_url": "https://arxiv.org/abs/2606.19930", "catalog_id": "arxiv:2606.19930", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-18", "identifiers": { "arxiv": "2606.19930" }, "record_updated_at": "2026-08-07" }, "genre": "preprint", "id": "arxiv:2606.19930", "issued": { "date-parts": [ [ 2026, 6, 18 ] ] }, "note": "First published: 2026-06-18; Recorded arXiv version: v2; Recorded version updated: 2026-08-07T03:54:59Z.", "title": "MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2606.20363v1", "archive": "arXiv", "archive_location": "2606.20363", "author": [ { "literal": "Yuexing Hao" }, { "literal": "Xiaomin Li" } ], "citation-key": "arxiv_2606_20363", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b370491b37d5bf25c624f2bac654e438459c8084b5da292fb18a0bf9142adaa2", "submitted_at": "2026-06-18T15:25:42Z", "updated_at": "2026-06-18T15:25:42Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.20363v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.20363", "catalog_id": "arxiv:2606.20363", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-18", "identifiers": { "arxiv": "2606.20363" }, "record_updated_at": "2026-06-18" }, "genre": "preprint", "id": "arxiv:2606.20363", "issued": { "date-parts": [ [ 2026, 6, 18 ] ] }, "note": "First published: 2026-06-18; Recorded arXiv version: v1; Recorded version updated: 2026-06-18T15:25:42Z.", "title": "Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.20785v2", "archive": "arXiv", "archive_location": "2606.20785", "author": [ { "literal": "Ahmed Awadallah" }, { "literal": "Sahil Gupta" }, { "literal": "Yash Lara" }, { "literal": "Yadong Lu" }, { "literal": "Hussein Mozannar" }, { "literal": "Akshay Nambi" }, { "literal": "Zach Nussbaum" }, { "literal": "Yash Pandya" }, { "literal": "Aravind Rajeswaran" }, { "literal": "Corby Rosset" }, { "literal": "Alexey Taymanov" }, { "literal": "Luiz do Valle" }, { "literal": "Vibhav Vineet" }, { "literal": "Spencer Whitehead" }, { "literal": "Andrew Zhao" } ], "citation-key": "arxiv_2606_20785", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "414eced85da9f76828e4398b977f9b8dac77236c97d1594108c8f5dfc3be7cbb", "submitted_at": "2026-06-18T17:53:03Z", "updated_at": "2026-07-22T17:47:01Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.20785v2" }, "canonical_source_url": "https://arxiv.org/abs/2606.20785", "catalog_id": "arxiv:2606.20785", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-18", "identifiers": { "arxiv": "2606.20785" }, "record_updated_at": "2026-07-22" }, "genre": "preprint", "id": "arxiv:2606.20785", "issued": { "date-parts": [ [ 2026, 6, 18 ] ] }, "note": "First published: 2026-06-18; Recorded arXiv version: v2; Recorded version updated: 2026-07-22T17:47:01Z.", "title": "Fara-1.5: Scalable Learning Environments for Computer Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2606.22948v1", "archive": "arXiv", "archive_location": "2606.22948", "author": [ { "literal": "Yincheng Zhou" }, { "literal": "Athena Zhuoming Zhong" }, { "literal": "Shijie Zhang" }, { "literal": "Kevin Zhang" }, { "literal": "Teresa Xiaotao Shang" }, { "literal": "Shanghang Zhang" } ], "citation-key": "arxiv_2606_22948", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fbd8892e06a5e847c16aa3101b98b3d669a783b84ee8e3d4d4d810754914028b", "submitted_at": "2026-06-22T07:28:55Z", "updated_at": "2026-06-22T07:28:55Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.22948v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.22948", "catalog_id": "arxiv:2606.22948", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-22", "identifiers": { "arxiv": "2606.22948" }, "record_updated_at": "2026-06-22" }, "genre": "preprint", "id": "arxiv:2606.22948", "issued": { "date-parts": [ [ 2026, 6, 22 ] ] }, "note": "First published: 2026-06-22; Recorded arXiv version: v1; Recorded version updated: 2026-06-22T07:28:55Z.", "title": "ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.24525v1", "archive": "arXiv", "archive_location": "2606.24525", "author": [ { "literal": "Jiachen Qian" } ], "citation-key": "arxiv_2606_24525", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a3d0341f41a8ecba57fb7ed9e4b266bb4a176639c742be2b4fc98555754f5744", "submitted_at": "2026-06-23T12:57:02Z", "updated_at": "2026-06-23T12:57:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.24525v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.24525", "catalog_id": "arxiv:2606.24525", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-23", "identifiers": { "arxiv": "2606.24525" }, "record_updated_at": "2026-06-23" }, "genre": "preprint", "id": "arxiv:2606.24525", "issued": { "date-parts": [ [ 2026, 6, 23 ] ] }, "note": "First published: 2026-06-23; Recorded arXiv version: v1; Recorded version updated: 2026-06-23T12:57:02Z.", "title": "VisCritic: Visual State Comparison as Process Reward for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.25705v1", "archive": "arXiv", "archive_location": "2606.25705", "author": [ { "literal": "Aradhana Nayak" }, { "literal": "Mussadiq Nazeer" }, { "literal": "Wang Peng" }, { "literal": "Feng Liu" } ], "citation-key": "arxiv_2606_25705", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3c5a2d0e461b011e2d5b9dbd73012d007261d8df37bd1d687fa3bd86dc6f2246", "submitted_at": "2026-06-24T11:18:01Z", "updated_at": "2026-06-24T11:18:01Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.25705v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.25705", "catalog_id": "arxiv:2606.25705", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-24", "identifiers": { "arxiv": "2606.25705" }, "record_updated_at": "2026-06-24" }, "genre": "preprint", "id": "arxiv:2606.25705", "issued": { "date-parts": [ [ 2026, 6, 24 ] ] }, "note": "First published: 2026-06-24; Recorded arXiv version: v1; Recorded version updated: 2026-06-24T11:18:01Z.", "title": "GUI agent: Guided Exploration of User-Sensitive Screens", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.25964v1", "archive": "arXiv", "archive_location": "2606.25964", "author": [ { "literal": "Chengheng Li-Chen" }, { "literal": "Zhiqian Zhou" }, { "literal": "Hao Chen" }, { "literal": "Nicolas Chauvin" } ], "citation-key": "arxiv_2606_25964", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7a8efe4b9476d7f55ca4da17621ece653be2e33bf02be0183a339a12f5fac3ca", "submitted_at": "2026-06-24T15:35:29Z", "updated_at": "2026-06-24T15:35:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.25964v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.25964", "catalog_id": "arxiv:2606.25964", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-24", "identifiers": { "arxiv": "2606.25964" }, "record_updated_at": "2026-06-24" }, "genre": "preprint", "id": "arxiv:2606.25964", "issued": { "date-parts": [ [ 2026, 6, 24 ] ] }, "note": "First published: 2026-06-24; Recorded arXiv version: v1; Recorded version updated: 2026-06-24T15:35:29Z.", "title": "WinDOM: Self-Family Distillation for Small-Model GUI Grounding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.27330v1", "archive": "arXiv", "archive_location": "2606.27330", "author": [ { "literal": "Tianyi Men" }, { "literal": "Zhuoran Jin" }, { "literal": "Pengfei Cao" }, { "literal": "Yubo Chen" }, { "literal": "Kang Liu" }, { "literal": "Jun Zhao" } ], "citation-key": "arxiv_2606_27330", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "42166ac3980296a53b56bc4a076634beec36ba885b3260b5d36115b5a5261cd0", "submitted_at": "2026-06-25T17:44:48Z", "updated_at": "2026-06-25T17:44:48Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.27330v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.27330", "catalog_id": "arxiv:2606.27330", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-25", "identifiers": { "arxiv": "2606.27330" }, "record_updated_at": "2026-06-25" }, "genre": "preprint", "id": "arxiv:2606.27330", "issued": { "date-parts": [ [ 2026, 6, 25 ] ] }, "note": "First published: 2026-06-25; Recorded arXiv version: v1; Recorded version updated: 2026-06-25T17:44:48Z.", "title": "Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.29705v1", "archive": "arXiv", "archive_location": "2606.29705", "author": [ { "literal": "Sunqi Fan" }, { "literal": "Lingshan Chen" }, { "literal": "Runqi Yin" }, { "literal": "Qingle Liu" }, { "literal": "Yongming Rao" }, { "literal": "Meng-Hao Guo" }, { "literal": "Shi-Min Hu" } ], "citation-key": "arxiv_2606_29705", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7beb70ac91463b77a8babaf2b077c46c5072e8f86d22f4d9afc9c1e77680f309", "submitted_at": "2026-06-29T02:16:21Z", "updated_at": "2026-06-29T02:16:21Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.29705v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.29705", "catalog_id": "arxiv:2606.29705", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-29", "identifiers": { "arxiv": "2606.29705" }, "record_updated_at": "2026-06-29" }, "genre": "preprint", "id": "arxiv:2606.29705", "issued": { "date-parts": [ [ 2026, 6, 29 ] ] }, "note": "First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T02:16:21Z.", "title": "GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.04425v2", "archive": "arXiv", "archive_location": "2607.04425", "author": [ { "literal": "Niu Lian" }, { "literal": "Tongbo Chen" }, { "literal": "Zhehao Yu" }, { "literal": "Chengzhen Duan" }, { "literal": "Fazhan Liu" }, { "literal": "Hui Liu" }, { "literal": "Pei Fu" }, { "literal": "Jian Luan" }, { "literal": "Heng Qu" }, { "literal": "Shu-Tao Xia" }, { "literal": "Jinpeng Wang" } ], "citation-key": "arxiv_2607_04425", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "32cb3020ccf25c31b805dc44218f5f9496cbc310e1df2906d8b15e5b60c31278", "submitted_at": "2026-07-05T17:37:12Z", "updated_at": "2026-08-10T13:11:37Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.04425v2" }, "canonical_source_url": "https://arxiv.org/abs/2607.04425", "catalog_id": "arxiv:2607.04425", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-05", "identifiers": { "arxiv": "2607.04425" }, "record_updated_at": "2026-08-10" }, "genre": "preprint", "id": "arxiv:2607.04425", "issued": { "date-parts": [ [ 2026, 7, 5 ] ] }, "note": "First published: 2026-07-05; Recorded arXiv version: v2; Recorded version updated: 2026-08-10T13:11:37Z.", "title": "UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2607.09773v2", "archive": "arXiv", "archive_location": "2607.09773", "author": [ { "literal": "Mianqiu Huang" }, { "literal": "Taofeng Xue" }, { "literal": "Chong Peng" }, { "literal": "Jinrui Ding" }, { "literal": "Jie Yang" }, { "literal": "Sicheng Fan" }, { "literal": "Jiale Hong" }, { "literal": "Yufei Gao" }, { "literal": "Xiaocheng Zhang" }, { "literal": "Linsen Guo" }, { "literal": "Xin Yang" }, { "literal": "Dengchang Zhao" }, { "literal": "Yuchen Xie" }, { "literal": "Peng Pei" }, { "literal": "Xunliang Xie" }, { "literal": "Xipeng Qiu" } ], "citation-key": "arxiv_2607_09773", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "53c254c53a834d4f28bb4b65317121f5c46f5dd6985d03a30f1cc1f0fa78707d", "submitted_at": "2026-07-07T16:36:25Z", "updated_at": "2026-09-04T15:47:10Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.09773v2" }, "canonical_source_url": "https://arxiv.org/abs/2607.09773", "catalog_id": "arxiv:2607.09773", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-07", "identifiers": { "arxiv": "2607.09773" }, "record_updated_at": "2026-09-04" }, "genre": "preprint", "id": "arxiv:2607.09773", "issued": { "date-parts": [ [ 2026, 7, 7 ] ] }, "note": "First published: 2026-07-07; Recorded arXiv version: v2; Recorded version updated: 2026-09-04T15:47:10Z.", "title": "EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2607.11185v1", "archive": "arXiv", "archive_location": "2607.11185", "author": [ { "literal": "Bowen Lv" }, { "literal": "Xiao Liu" }, { "literal": "Yanyu Ren" }, { "literal": "Hanyu Lai" }, { "literal": "Bohao Jing" }, { "literal": "Hanchen Zhang" }, { "literal": "Yanxiao Zhao" }, { "literal": "Shuntian Yao" }, { "literal": "Jie Tang" }, { "literal": "Yuxiao Dong" } ], "citation-key": "arxiv_2607_11185", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "554844f23cddbdaadc3c52e93d07d06c756faadbd0136ffef0984b25423f84f8", "submitted_at": "2026-07-13T07:32:35Z", "updated_at": "2026-07-13T07:32:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.11185v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.11185", "catalog_id": "arxiv:2607.11185", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-13", "identifiers": { "arxiv": "2607.11185" }, "record_updated_at": "2026-07-13" }, "genre": "preprint", "id": "arxiv:2607.11185", "issued": { "date-parts": [ [ 2026, 7, 13 ] ] }, "note": "First published: 2026-07-13; Recorded arXiv version: v1; Recorded version updated: 2026-07-13T07:32:35Z.", "title": "SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.14548v1", "archive": "arXiv", "archive_location": "2607.14548", "author": [ { "literal": "Hy Vision Team" }, { "literal": "Huawen Shen" }, { "literal": "Zhengyang Tang" }, { "literal": "Shangpin Peng" }, { "literal": "Liang Wu" }, { "literal": "Anran Zhang" }, { "literal": "Weinong Wang" }, { "literal": "Yiduo Guo" }, { "literal": "Chenxin Li" }, { "literal": "Zhengyao Fang" }, { "literal": "Yang Ding" }, { "literal": "Junyi Li" }, { "literal": "Fei Tang" }, { "literal": "Zheng Ruan" }, { "literal": "Yi Zhang" }, { "literal": "Xingran Zhou" }, { "literal": "Dingchen Yang" }, { "literal": "Sunqi Fan" }, { "literal": "Zhiyi Wan" }, { "literal": "Han Hu" }, { "literal": "Xin Lai" }, { "literal": "Pengyuan Lyu" }, { "literal": "Chengquan Zhang" } ], "citation-key": "arxiv_2607_14548", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "151d4882fecc835dfffb9651bd860ebe8c85919a63ff5730e191f9146fbba272", "submitted_at": "2026-07-16T04:12:42Z", "updated_at": "2026-07-16T04:12:42Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.14548v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.14548", "catalog_id": "arxiv:2607.14548", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-16", "identifiers": { "arxiv": "2607.14548" }, "record_updated_at": "2026-07-16" }, "genre": "preprint", "id": "arxiv:2607.14548", "issued": { "date-parts": [ [ 2026, 7, 16 ] ] }, "note": "First published: 2026-07-16; Recorded arXiv version: v1; Recorded version updated: 2026-07-16T04:12:42Z.", "title": "HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.18046v2", "archive": "arXiv", "archive_location": "2607.18046", "author": [ { "literal": "Zhuohang Fan" }, { "literal": "Beichen Zhang" }, { "literal": "Yuanfa Li" }, { "literal": "Changqiao Wu" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Weigang Zhang" } ], "citation-key": "arxiv_2607_18046", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b85b453a688543477d31a940f9d1da2857b2cb7a8cb9eea91a39a3a2b8a1e1c7", "submitted_at": "2026-07-20T15:16:59Z", "updated_at": "2026-08-18T02:32:56Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.18046v2" }, "canonical_source_url": "https://arxiv.org/abs/2607.18046", "catalog_id": "arxiv:2607.18046", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-20", "identifiers": { "arxiv": "2607.18046" }, "record_updated_at": "2026-08-18" }, "genre": "preprint", "id": "arxiv:2607.18046", "issued": { "date-parts": [ [ 2026, 7, 20 ] ] }, "note": "First published: 2026-07-20; Recorded arXiv version: v2; Recorded version updated: 2026-08-18T02:32:56Z.", "title": "SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2607.23263v2", "archive": "arXiv", "archive_location": "2607.23263", "author": [ { "literal": "Yang Wan" }, { "literal": "Zhenhao Zhang" }, { "literal": "Jierui Wang" }, { "literal": "Xiangxin Zhou" }, { "literal": "Linchao Zhu" } ], "citation-key": "arxiv_2607_23263", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2de35aa3c7f4457d43d485eb136d8b380ea61870cc7253e807880ae731c51316", "submitted_at": "2026-07-25T16:00:45Z", "updated_at": "2026-09-26T12:15:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.23263v2" }, "canonical_source_url": "https://arxiv.org/abs/2607.23263", "catalog_id": "arxiv:2607.23263", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-25", "identifiers": { "arxiv": "2607.23263" }, "record_updated_at": "2026-09-26" }, "genre": "preprint", "id": "arxiv:2607.23263", "issued": { "date-parts": [ [ 2026, 7, 25 ] ] }, "note": "First published: 2026-07-25; Recorded arXiv version: v2; Recorded version updated: 2026-09-26T12:15:44Z.", "title": "SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2607.24112v1", "archive": "arXiv", "archive_location": "2607.24112", "author": [ { "literal": "Xiangyan Liu" }, { "literal": "Kaixin Li" }, { "literal": "Haonan Wang" }, { "literal": "Biao Wu" }, { "literal": "Meng Fang" }, { "literal": "Longxu Dou" }, { "literal": "Chao Du" }, { "literal": "Michael Qizhe Shieh" }, { "literal": "Tianyu Pang" } ], "citation-key": "arxiv_2607_24112", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4651964cbe45e4d740ed8f789753f82ae808e442d82c6598e7b3c997c09453c3", "submitted_at": "2026-07-27T07:54:08Z", "updated_at": "2026-07-27T07:54:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.24112v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.24112", "catalog_id": "arxiv:2607.24112", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-27", "identifiers": { "arxiv": "2607.24112" }, "record_updated_at": "2026-07-27" }, "genre": "preprint", "id": "arxiv:2607.24112", "issued": { "date-parts": [ [ 2026, 7, 27 ] ] }, "note": "First published: 2026-07-27; Recorded arXiv version: v1; Recorded version updated: 2026-07-27T07:54:08Z.", "title": "Scaling GUI Agents with Visual State Transitions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.28074v1", "archive": "arXiv", "archive_location": "2607.28074", "author": [ { "literal": "Yash Pandya" }, { "literal": "Sahil Gupta" }, { "literal": "Sarthak Harne" }, { "literal": "Archana Yadav" }, { "literal": "Kavyansh Chourasia" }, { "literal": "Hussein Mozannar" }, { "literal": "Vibhav Vineet" }, { "literal": "Sara Abdali" }, { "literal": "Corby Rosset" }, { "literal": "Yash Lara" }, { "literal": "Ahmed Awadallah" }, { "literal": "Ece Kamar" }, { "literal": "Akshay Nambi" } ], "citation-key": "arxiv_2607_28074", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f28e1ee8e101000f3cfe9215555251656fcb40b921b5c41c895fbc958f867e3", "submitted_at": "2026-07-30T11:48:22Z", "updated_at": "2026-07-30T11:48:22Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.28074v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.28074", "catalog_id": "arxiv:2607.28074", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-30", "identifiers": { "arxiv": "2607.28074" }, "record_updated_at": "2026-07-30" }, "genre": "preprint", "id": "arxiv:2607.28074", "issued": { "date-parts": [ [ 2026, 7, 30 ] ] }, "note": "First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T11:48:22Z.", "title": "Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.28609v2", "archive": "arXiv", "archive_location": "2607.28609", "author": [ { "literal": "Qiushi Sun" }, { "literal": "Kanzhi Cheng" }, { "literal": "Yian Wang" }, { "literal": "Bowen Yang" }, { "literal": "Hang Yan" }, { "literal": "Liheng Chen" }, { "literal": "Fangzhi Xu" }, { "literal": "Zichen Ding" }, { "literal": "Nuo Chen" }, { "literal": "Jialin Cao" }, { "literal": "Xingdong Gong" }, { "literal": "Zehao Li" }, { "literal": "Kaiming Jin" }, { "literal": "Xinfeng Yuan" }, { "literal": "Zhoumianze Liu" }, { "literal": "Jingyang Gong" }, { "literal": "Zhangyue Yin" }, { "literal": "Jiahui Gao" }, { "literal": "Zhiyong Wu" }, { "literal": "Tianbao Xie" }, { "literal": "Jianbing Zhang" }, { "literal": "Ben Kao" }, { "literal": "Lingpeng Kong" } ], "citation-key": "arxiv_2607_28609", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e3e82df7abffbd0c8f7e969ed8edb77423263a2b1d826a3e72529b0a51903d58", "submitted_at": "2026-07-30T17:57:41Z", "updated_at": "2026-08-06T17:55:59Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.28609v2" }, "canonical_source_url": "https://arxiv.org/abs/2607.28609", "catalog_id": "arxiv:2607.28609", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-30", "identifiers": { "arxiv": "2607.28609" }, "record_updated_at": "2026-08-06" }, "genre": "preprint", "id": "arxiv:2607.28609", "issued": { "date-parts": [ [ 2026, 7, 30 ] ] }, "note": "First published: 2026-07-30; Recorded arXiv version: v2; Recorded version updated: 2026-08-06T17:55:59Z.", "title": "OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2608.02352v1", "archive": "arXiv", "archive_location": "2608.02352", "author": [ { "literal": "Dunjie Lu" }, { "literal": "Shuai Bai" }, { "literal": "Tianyi Bai" }, { "literal": "Sicheng Fan" }, { "literal": "Chang Gao" }, { "literal": "Jian Guan" }, { "literal": "Feng Hu" }, { "literal": "Mianqiu Huang" }, { "literal": "Xingyang Huang" }, { "literal": "Yizhen Jiang" }, { "literal": "Yuheng Jing" }, { "literal": "Dehui Kong" }, { "literal": "Ning Li" }, { "literal": "Dayiheng Liu" }, { "literal": "Shixuan Liu" }, { "literal": "Zheng Liu" }, { "literal": "Que Shen" }, { "literal": "Bowen Wang" }, { "literal": "Junli Wang" }, { "literal": "Chencan Wu" }, { "literal": "Rui Xie" }, { "literal": "Tianbao Xie" }, { "literal": "Zhihui Xie" }, { "literal": "Haiyang Xu" }, { "literal": "An Yang" }, { "literal": "Tao Yu" }, { "literal": "Wenzhen Yuan" }, { "literal": "Xi Zhang" }, { "literal": "Zhenru Zhang" }, { "literal": "Mingkang Zhu" }, { "literal": "Zhaoqing Zhu" }, { "literal": "Yizhong Cao" }, { "literal": "Kai Dang" }, { "literal": "Binyuan Hui" }, { "literal": "Kaixin Li" }, { "literal": "Junyang Lin" }, { "literal": "Haiquan Wang" }, { "literal": "Zekun Wang" }, { "literal": "Yiheng Xu" }, { "literal": "Fan Yan" }, { "literal": "Mengqi Yuan" }, { "literal": "Danyang Zhang" }, { "literal": "Jiajun Zhang" }, { "literal": "Zhipeng Zhang" }, { "literal": "Fan Zhou" }, { "literal": "Fan Zhou" } ], "citation-key": "arxiv_2608_02352", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "26a61ccfdddb5cdc2da2b14d29ae8d4098544fea4e9458126f2a49c28418c4f0", "submitted_at": "2026-08-03T15:04:20Z", "updated_at": "2026-08-03T15:04:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.02352v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.02352", "catalog_id": "arxiv:2608.02352", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-03", "identifiers": { "arxiv": "2608.02352" }, "record_updated_at": "2026-08-03" }, "genre": "preprint", "id": "arxiv:2608.02352", "issued": { "date-parts": [ [ 2026, 8, 3 ] ] }, "note": "First published: 2026-08-03; Recorded arXiv version: v1; Recorded version updated: 2026-08-03T15:04:20Z.", "title": "Qwen-CUA: Native Computer Use for (almost) Everything", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.05891v1", "archive": "arXiv", "archive_location": "2608.05891", "author": [ { "literal": "Weikai Xu" }, { "literal": "Yunren Feng" }, { "literal": "Haoxiang Lei" }, { "literal": "Kun Huang" }, { "literal": "Yuxuan Liu" }, { "literal": "Kang Zhao" }, { "literal": "Xiaolin Hu" }, { "literal": "Shuo Shang" }, { "literal": "Bo An" } ], "citation-key": "arxiv_2608_05891", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ce37dd8217afbaa07ddea25c0daf78cdbfb449851ca6ab17b7f3ecacd451eb2f", "submitted_at": "2026-08-06T11:15:41Z", "updated_at": "2026-08-06T11:15:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.05891v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.05891", "catalog_id": "arxiv:2608.05891", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-06", "identifiers": { "arxiv": "2608.05891" }, "record_updated_at": "2026-08-06" }, "genre": "preprint", "id": "arxiv:2608.05891", "issued": { "date-parts": [ [ 2026, 8, 6 ] ] }, "note": "First published: 2026-08-06; Recorded arXiv version: v1; Recorded version updated: 2026-08-06T11:15:41Z.", "title": "AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.12429v1", "archive": "arXiv", "archive_location": "2608.12429", "author": [ { "literal": "Ruitao Wang" }, { "literal": "Yuwen Hao" }, { "literal": "Menglin Yang" } ], "citation-key": "arxiv_2608_12429", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bf543ef0b77eb6fe430c8cef5382932f13e4e4136aaba9c14c44b5a591d6612a", "submitted_at": "2026-08-12T12:03:20Z", "updated_at": "2026-08-12T12:03:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.12429v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.12429", "catalog_id": "arxiv:2608.12429", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-12", "identifiers": { "arxiv": "2608.12429" }, "record_updated_at": "2026-08-12" }, "genre": "preprint", "id": "arxiv:2608.12429", "issued": { "date-parts": [ [ 2026, 8, 12 ] ] }, "note": "First published: 2026-08-12; Recorded arXiv version: v1; Recorded version updated: 2026-08-12T12:03:20Z.", "title": "SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.15930v1", "archive": "arXiv", "archive_location": "2608.15930", "author": [ { "literal": "Zihan Ding" }, { "literal": "Longxu Dou" }, { "literal": "Qi Gao" }, { "literal": "Xiangwu Guo" }, { "literal": "Shengchao Hu" }, { "literal": "Zilong Huang" }, { "literal": "Zihang Jiang" }, { "literal": "Lei Ke" }, { "literal": "Mengcheng Lan" }, { "literal": "Weixian Lei" }, { "literal": "Hanxuan Li" }, { "literal": "Honglin Li" }, { "literal": "Xiyun Li" }, { "literal": "Zaitang Li" }, { "literal": "Leowei Liang" }, { "literal": "Xin Luo" }, { "literal": "Haozhe Ma" }, { "literal": "Jiayi Mao" }, { "literal": "Zhoujie Pan" }, { "literal": "Can Qin" }, { "literal": "Tianyuan Qu" }, { "literal": "Weiqi Wang" }, { "literal": "Wenkai Wang" }, { "literal": "Yonglin Wang" }, { "literal": "Yuxin Wang" }, { "literal": "Chenxu Wu" }, { "literal": "Yingchen Yu" }, { "literal": "Chenyu Zhang" }, { "literal": "Yuhao Zheng" } ], "citation-key": "arxiv_2608_15930", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "efe635792c696bca73c9a436be67d8528582fb239d4d4f8d3de531219b1f4f8e", "submitted_at": "2026-08-16T20:59:59Z", "updated_at": "2026-08-16T20:59:59Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.15930v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.15930", "catalog_id": "arxiv:2608.15930", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-16", "identifiers": { "arxiv": "2608.15930" }, "record_updated_at": "2026-08-16" }, "genre": "preprint", "id": "arxiv:2608.15930", "issued": { "date-parts": [ [ 2026, 8, 16 ] ] }, "note": "First published: 2026-08-16; Recorded arXiv version: v1; Recorded version updated: 2026-08-16T20:59:59Z.", "title": "UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.21898v2", "archive": "arXiv", "archive_location": "2608.21898", "author": [ { "literal": "Chenghao Zhang" }, { "literal": "Yuxi Cheng" }, { "literal": "Saisai Hu" }, { "literal": "Canran Xiao" }, { "literal": "Yikai Mao" }, { "literal": "Dan Roth" } ], "citation-key": "arxiv_2608_21898", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7d862afa969c0b4d1c6edc8d126017749844158f786b29c3b0710afecdec2008", "submitted_at": "2026-08-22T10:18:45Z", "updated_at": "2026-09-28T15:54:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2608.21898v2" }, "canonical_source_url": "https://arxiv.org/abs/2608.21898", "catalog_id": "arxiv:2608.21898", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-22", "identifiers": { "arxiv": "2608.21898" }, "record_updated_at": "2026-09-28" }, "genre": "preprint", "id": "arxiv:2608.21898", "issued": { "date-parts": [ [ 2026, 8, 22 ] ] }, "note": "First published: 2026-08-22; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T15:54:31Z.", "title": "Training Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2608.22847v1", "archive": "arXiv", "archive_location": "2608.22847", "author": [ { "literal": "Long Zhang" }, { "literal": "Yuhan Chen" }, { "literal": "Chaoran Zhang" }, { "literal": "Wanxia Cao" }, { "literal": "Kun Huang" }, { "literal": "Pengzhi Gao" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Chenliang Li" }, { "literal": "Lixin Zou" } ], "citation-key": "arxiv_2608_22847", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4c1198ce65d5a2fcffc51b37bc4553b35b9e0d809757dc4181747c57c7ae443d", "submitted_at": "2026-08-24T06:27:47Z", "updated_at": "2026-08-24T06:27:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.22847v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.22847", "catalog_id": "arxiv:2608.22847", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-24", "identifiers": { "arxiv": "2608.22847" }, "record_updated_at": "2026-08-24" }, "genre": "preprint", "id": "arxiv:2608.22847", "issued": { "date-parts": [ [ 2026, 8, 24 ] ] }, "note": "First published: 2026-08-24; Recorded arXiv version: v1; Recorded version updated: 2026-08-24T06:27:47Z.", "title": "GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.24848v1", "archive": "arXiv", "archive_location": "2608.24848", "author": [ { "literal": "Fei Tang" }, { "literal": "Huawen Shen" }, { "literal": "Zhiqiong Lu" }, { "literal": "Zhengxi Lu" }, { "literal": "Pengyuan Lyu" }, { "literal": "Chengquan Zhang" }, { "literal": "Weiming Lu" }, { "literal": "Jun Xiao" }, { "literal": "Yueting Zhuang" }, { "literal": "Yongliang Shen" } ], "citation-key": "arxiv_2608_24848", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0d2180e9b1b0c3ae20e32b0b597dc209e363551aaa5031c98504ef08314979a6", "submitted_at": "2026-08-25T17:35:42Z", "updated_at": "2026-08-25T17:35:42Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.24848v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.24848", "catalog_id": "arxiv:2608.24848", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-25", "identifiers": { "arxiv": "2608.24848" }, "record_updated_at": "2026-08-25" }, "genre": "preprint", "id": "arxiv:2608.24848", "issued": { "date-parts": [ [ 2026, 8, 25 ] ] }, "note": "First published: 2026-08-25; Recorded arXiv version: v1; Recorded version updated: 2026-08-25T17:35:42Z.", "title": "BrowserForge: Scaling Web Episode via Parallel Browser Sandboxes", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.27866v1", "archive": "arXiv", "archive_location": "2608.27866", "author": [ { "literal": "Jiahe Ying" }, { "literal": "Wendong Bu" }, { "literal": "Kaihang Pan" }, { "literal": "Bingchen Miao" }, { "literal": "Siyu Chen" }, { "literal": "Wen Wang" }, { "literal": "Xueming Jiang" }, { "literal": "Juncheng Li" }, { "literal": "Siliang Tang" } ], "citation-key": "arxiv_2608_27866", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "352699b04f3a9406d7cab95ce9b5fb000e3e98a28996777e75b7399a6290357a", "submitted_at": "2026-08-28T03:15:11Z", "updated_at": "2026-08-28T03:15:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.27866v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.27866", "catalog_id": "arxiv:2608.27866", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-28", "identifiers": { "arxiv": "2608.27866" }, "record_updated_at": "2026-08-28" }, "genre": "preprint", "id": "arxiv:2608.27866", "issued": { "date-parts": [ [ 2026, 8, 28 ] ] }, "note": "First published: 2026-08-28; Recorded arXiv version: v1; Recorded version updated: 2026-08-28T03:15:11Z.", "title": "Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.30207v2", "archive": "arXiv", "archive_location": "2608.30207", "author": [ { "literal": "Chen Xiong" }, { "literal": "Zhiyuan He" }, { "literal": "Pin-Yu Chen" }, { "literal": "Stjepan Picek" }, { "literal": "Tsung-Yi Ho" } ], "citation-key": "arxiv_2608_30207", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "87c3f58eebe2db437b1166ff8e83b336db4cde37684a7cd86f61c4b34fca7237", "submitted_at": "2026-08-31T03:39:43Z", "updated_at": "2026-10-03T10:41:41Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2608.30207v2" }, "canonical_source_url": "https://arxiv.org/abs/2608.30207", "catalog_id": "arxiv:2608.30207", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-31", "identifiers": { "arxiv": "2608.30207" }, "record_updated_at": "2026-10-03" }, "genre": "preprint", "id": "arxiv:2608.30207", "issued": { "date-parts": [ [ 2026, 8, 31 ] ] }, "note": "First published: 2026-08-31; Recorded arXiv version: v2; Recorded version updated: 2026-10-03T10:41:41Z.", "title": "SIR: Self-improving Red-teaming for Compute Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2609.02885v1", "archive": "arXiv", "archive_location": "2609.02885", "author": [ { "literal": "Kelvin Li" }, { "literal": "Dhruv Pendharkar" }, { "literal": "Anish Pahilajani" }, { "literal": "Chuyi Shang" }, { "literal": "Leon Oks" }, { "literal": "Leonid Karlinsky" }, { "literal": "Rogerio Feris" }, { "literal": "Trevor Darrell" }, { "literal": "Roei Herzig" } ], "citation-key": "arxiv_2609_02885", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8703474cb4f577b307731cf1a986f76f800470fde625b6ca4b3569d30e74f903", "submitted_at": "2026-09-02T17:59:40Z", "updated_at": "2026-09-02T17:59:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.02885v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.02885", "catalog_id": "arxiv:2609.02885", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-02", "identifiers": { "arxiv": "2609.02885" }, "record_updated_at": "2026-09-02" }, "genre": "preprint", "id": "arxiv:2609.02885", "issued": { "date-parts": [ [ 2026, 9, 2 ] ] }, "note": "First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T17:59:40Z.", "title": "Discriminative World Models for Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.05374v1", "archive": "arXiv", "archive_location": "2609.05374", "author": [ { "literal": "Haoting Shi" }, { "literal": "Wenhao Wang" }, { "literal": "Weicheng Fang" }, { "literal": "Yaozhong Liang" }, { "literal": "Tian Jin" }, { "literal": "Pengxiang Zhao" }, { "literal": "Guangyi Liu" }, { "literal": "Siheng Chen" }, { "literal": "Yanfeng Wang" } ], "citation-key": "arxiv_2609_05374", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "69eab19b6e45e1b2ddf9f29f6f0937d51e06a5bb7dea34dadb761361c82f08d4", "submitted_at": "2026-09-04T17:26:18Z", "updated_at": "2026-09-04T17:26:18Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.05374v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.05374", "catalog_id": "arxiv:2609.05374", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-04", "identifiers": { "arxiv": "2609.05374" }, "record_updated_at": "2026-09-04" }, "genre": "preprint", "id": "arxiv:2609.05374", "issued": { "date-parts": [ [ 2026, 9, 4 ] ] }, "note": "First published: 2026-09-04; Recorded arXiv version: v1; Recorded version updated: 2026-09-04T17:26:18Z.", "title": "CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.05513v1", "archive": "arXiv", "archive_location": "2609.05513", "author": [ { "literal": "Jianwei Zhang" }, { "literal": "Sihan Cao" }, { "literal": "Pengcheng Zheng" }, { "literal": "Ya Wen" }, { "literal": "Pei Ke" }, { "literal": "Kuien Liu" }, { "literal": "Shen Gao" }, { "literal": "Wei Dong" }, { "literal": "Yang Yang" }, { "literal": "Chaoning Zhang" } ], "citation-key": "arxiv_2609_05513", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aaeb2a57b2bb92ed926c9b65fb40b6bbf272e0ad9bb7415716d24eab0aeb4402", "submitted_at": "2026-08-31T08:40:34Z", "updated_at": "2026-08-31T08:40:34Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.05513v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.05513", "catalog_id": "arxiv:2609.05513", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-31", "identifiers": { "arxiv": "2609.05513" }, "record_updated_at": "2026-08-31" }, "genre": "preprint", "id": "arxiv:2609.05513", "issued": { "date-parts": [ [ 2026, 8, 31 ] ] }, "note": "First published: 2026-08-31; Recorded arXiv version: v1; Recorded version updated: 2026-08-31T08:40:34Z.", "title": "When and What to Teach: Budget-Aware Online Adaptation for Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.12394v3", "archive": "arXiv", "archive_location": "2609.12394", "author": [ { "literal": "Tong Ye" }, { "literal": "Kunyang Han" }, { "literal": "Guozhi Wang" }, { "literal": "Longqiang Luo" }, { "literal": "Zhifeng Ding" }, { "literal": "Yongxiang Zhang" }, { "literal": "Xiaolei Shen" }, { "literal": "Yuxuan Zhang" }, { "literal": "Zhuping Zhang" }, { "literal": "Tao Xu" }, { "literal": "Yue Pan" }, { "literal": "Yucheng Zhao" }, { "literal": "Yupei Hu" }, { "literal": "Yuanjiang Ouyang" }, { "literal": "Danfeng Shen" }, { "literal": "Runqi Lin" }, { "literal": "Hongda Cai" }, { "literal": "Zhaoxiong Wang" }, { "literal": "Mengjia Yan" }, { "literal": "Yingjie Zhong" }, { "literal": "Chen Zhou" }, { "literal": "Zeyu Zhang" }, { "literal": "Xuwen Zhu" }, { "literal": "Penggang Shi" }, { "literal": "Mingcheng Luo" }, { "literal": "Ziyang Wu" }, { "literal": "Min Jin" }, { "literal": "Mingfu Shen" }, { "literal": "Zairong Xu" }, { "literal": "Fan Zhang" }, { "literal": "Hao Wang" }, { "literal": "Liang Liu" }, { "literal": "Zhulin Xie" }, { "literal": "Lijun Yao" }, { "literal": "Xiao Liang" }, { "literal": "Liangmin Wen" }, { "literal": "Liqiang Feng" }, { "literal": "Feilong Wu" }, { "literal": "Min Hu" }, { "literal": "Min Chen" }, { "literal": "Guanjing Xiong" }, { "literal": "Xiaohu Ruan" }, { "literal": "Xiaoxin Chen" } ], "citation-key": "arxiv_2609_12394", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cc15573bca49d453001ec22061f190e429704a5318751b041550e3610c469f4e", "submitted_at": "2026-09-11T03:36:35Z", "updated_at": "2026-09-15T06:36:04Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2609.12394v3" }, "canonical_source_url": "https://arxiv.org/abs/2609.12394", "catalog_id": "arxiv:2609.12394", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-11", "identifiers": { "arxiv": "2609.12394" }, "record_updated_at": "2026-09-15" }, "genre": "preprint", "id": "arxiv:2609.12394", "issued": { "date-parts": [ [ 2026, 9, 11 ] ] }, "note": "First published: 2026-09-11; Recorded arXiv version: v3; Recorded version updated: 2026-09-15T06:36:04Z.", "title": "BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2609.18690v1", "archive": "arXiv", "archive_location": "2609.18690", "author": [ { "literal": "Liyang Fan" }, { "literal": "Xinping Bi" }, { "literal": "Yitai Li" }, { "literal": "Shuaimin Li" }, { "literal": "Hui Li" }, { "literal": "Min Yang" } ], "citation-key": "arxiv_2609_18690", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ccbc85f4d2598b4cb1e6e1a96b3b9184ddeba838cb610658070fd2d1ac9c8d06", "submitted_at": "2026-09-16T14:06:38Z", "updated_at": "2026-09-16T14:06:38Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.18690v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.18690", "catalog_id": "arxiv:2609.18690", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-16", "identifiers": { "arxiv": "2609.18690" }, "record_updated_at": "2026-09-16" }, "genre": "preprint", "id": "arxiv:2609.18690", "issued": { "date-parts": [ [ 2026, 9, 16 ] ] }, "note": "First published: 2026-09-16; Recorded arXiv version: v1; Recorded version updated: 2026-09-16T14:06:38Z.", "title": "RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.22000v2", "archive": "arXiv", "archive_location": "2609.22000", "author": [ { "literal": "Shuai Bai" }, { "literal": "Jiayong Deng" }, { "literal": "Sicheng Fan" }, { "literal": "Yikun Fu" }, { "literal": "Chang Gao" }, { "literal": "Xuhao Hu" }, { "literal": "Mianqiu Huang" }, { "literal": "Yizhen Jiang" }, { "literal": "Yuheng Jing" }, { "literal": "Dehui Kong" }, { "literal": "Keliang Li" }, { "literal": "Ning Li" }, { "literal": "Wanli Li" }, { "literal": "Dayiheng Liu" }, { "literal": "Dunjie Lu" }, { "literal": "Changwei Luo" }, { "literal": "Que Shen" }, { "literal": "Zheyuan Wang" }, { "literal": "Zijian Wang" }, { "literal": "Jie Wu" }, { "literal": "Gao Wu" }, { "literal": "Zhihui Xie" }, { "literal": "Rui Xie" }, { "literal": "Haiyang Xu" }, { "literal": "An Yang" }, { "literal": "Jiakang Yuan" }, { "literal": "Yanming Zhang" }, { "literal": "Jiajun Zhang" }, { "literal": "Xi Zhang" }, { "literal": "Zhenru Zhang" }, { "literal": "Zhuo Zhen" }, { "literal": "Mingkang Zhu" }, { "literal": "Bowen Zhou" } ], "citation-key": "arxiv_2609_22000", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3b312c5a4d638ec9f9a7408fd9ce2d8cbf74fa462d48c8aa37f59e4ad3bd8edc", "submitted_at": "2026-09-18T17:00:56Z", "updated_at": "2026-09-21T07:09:10Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2609.22000v2" }, "canonical_source_url": "https://arxiv.org/abs/2609.22000", "catalog_id": "arxiv:2609.22000", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-18", "identifiers": { "arxiv": "2609.22000" }, "record_updated_at": "2026-09-21" }, "genre": "preprint", "id": "arxiv:2609.22000", "issued": { "date-parts": [ [ 2026, 9, 18 ] ] }, "note": "First published: 2026-09-18; Recorded arXiv version: v2; Recorded version updated: 2026-09-21T07:09:10Z.", "title": "RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2609.22083v1", "archive": "arXiv", "archive_location": "2609.22083", "author": [ { "literal": "Mingfei Gao" }, { "literal": "Rui Tian" }, { "literal": "Haiming Gang" }, { "literal": "Bohan Zhai" }, { "literal": "Le Zhang" }, { "literal": "Yuanzheng Gong" }, { "literal": "Di Feng" }, { "literal": "Ege Özsoy" }, { "literal": "Kaixin Ma" }, { "literal": "Vishwesh Kirthivasan" }, { "literal": "Oğuzhan Fatih Kar" }, { "literal": "Roman Bachmann" }, { "literal": "Anders Boesen Lindbo Larsen" }, { "literal": "Afshin Dehghan" } ], "citation-key": "arxiv_2609_22083", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4dfb0703133032426ff8f40ed6a2c8131025b07658c0b643603f8d50ba163d16", "submitted_at": "2026-09-18T17:59:34Z", "updated_at": "2026-09-18T17:59:34Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.22083v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.22083", "catalog_id": "arxiv:2609.22083", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-18", "identifiers": { "arxiv": "2609.22083" }, "record_updated_at": "2026-09-18" }, "genre": "preprint", "id": "arxiv:2609.22083", "issued": { "date-parts": [ [ 2026, 9, 18 ] ] }, "note": "First published: 2026-09-18; Recorded arXiv version: v1; Recorded version updated: 2026-09-18T17:59:34Z.", "title": "MintAct: A Unified Visual Agent for Digital Environments", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.22178v2", "archive": "arXiv", "archive_location": "2609.22178", "author": [ { "literal": "Zeyu Kang" }, { "literal": "Zhenyun Yin" }, { "literal": "Yang Zhang" }, { "literal": "Shan He" }, { "literal": "Shanzhe Lei" }, { "literal": "Yanjiu Zhong" }, { "literal": "Xinquan Chen" }, { "literal": "Xuhong Wang" } ], "citation-key": "arxiv_2609_22178", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a88d287d5433009962a905dbdbf03359e1183e66e4a6015441ec28405f64a6ee", "submitted_at": "2026-08-27T05:43:50Z", "updated_at": "2026-09-22T06:39:18Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2609.22178v2" }, "canonical_source_url": "https://arxiv.org/abs/2609.22178", "catalog_id": "arxiv:2609.22178", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-27", "identifiers": { "arxiv": "2609.22178" }, "record_updated_at": "2026-09-22" }, "genre": "preprint", "id": "arxiv:2609.22178", "issued": { "date-parts": [ [ 2026, 8, 27 ] ] }, "note": "First published: 2026-08-27; Recorded arXiv version: v2; Recorded version updated: 2026-09-22T06:39:18Z.", "title": "Beyond Task Completion: Training Capable and Safe Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2609.29892v1", "archive": "arXiv", "archive_location": "2609.29892", "author": [ { "literal": "Tingyu Qu" }, { "literal": "Weigao Sun" }, { "literal": "Yuecheng Liu" }, { "literal": "Yucheng Zhao" }, { "literal": "Yi Zhu" }, { "literal": "Yifeng Ding" }, { "literal": "Qiyi Wang" }, { "literal": "Sihan Cao" }, { "literal": "Pengkun Jiao" }, { "literal": "Hanlei Xie" }, { "literal": "Xiongwei Wu" }, { "literal": "Qichao Wang" }, { "literal": "Haodong Zhang" }, { "literal": "Jiajun Liu" }, { "literal": "Yuhao Wang" }, { "literal": "Yuqing Xie" }, { "literal": "Junpeng Zhao" }, { "literal": "Long Chen" }, { "literal": "Ming Ma" }, { "literal": "Sihan Yang" }, { "literal": "Ziwang Zhao" }, { "literal": "Yanhao Jia" }, { "literal": "Liangquan Gong" }, { "literal": "Feida Zhu" }, { "literal": "Yiran Zhong" }, { "literal": "Steven Hoi" } ], "citation-key": "arxiv_2609_29892", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "572ba5397fc1e4bb138febc3e7004e6e4f244e0ba8b628fb91debef4a854561f", "submitted_at": "2026-09-24T14:38:08Z", "updated_at": "2026-09-24T14:38:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.29892v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.29892", "catalog_id": "arxiv:2609.29892", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-24", "identifiers": { "arxiv": "2609.29892" }, "record_updated_at": "2026-09-24" }, "genre": "preprint", "id": "arxiv:2609.29892", "issued": { "date-parts": [ [ 2026, 9, 24 ] ] }, "note": "First published: 2026-09-24; Recorded arXiv version: v1; Recorded version updated: 2026-09-24T14:38:08Z.", "title": "Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.30887v1", "archive": "arXiv", "archive_location": "2609.30887", "author": [ { "literal": "Yuchen Sun" }, { "literal": "Chenglin Cai" }, { "literal": "Gongjie Zhang" }, { "literal": "Tianyu Xia" }, { "literal": "Quyu Kong" }, { "literal": "Panrong Tong" }, { "literal": "Zhengwen Zeng" }, { "literal": "Long Chen" }, { "literal": "Steven Hoi" }, { "literal": "Chongyang Zhang" }, { "literal": "Yue Wang" } ], "citation-key": "arxiv_2609_30887", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "838635f067b706c7b36a948c8100b30bf4cacd218470aaed6970e5186fa44fb9", "submitted_at": "2026-09-25T06:50:04Z", "updated_at": "2026-09-25T06:50:04Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.30887v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.30887", "catalog_id": "arxiv:2609.30887", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-25", "identifiers": { "arxiv": "2609.30887" }, "record_updated_at": "2026-09-25" }, "genre": "preprint", "id": "arxiv:2609.30887", "issued": { "date-parts": [ [ 2026, 9, 25 ] ] }, "note": "First published: 2026-09-25; Recorded arXiv version: v1; Recorded version updated: 2026-09-25T06:50:04Z.", "title": "From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.31364v1", "archive": "arXiv", "archive_location": "2609.31364", "author": [ { "literal": "Kiana Hooshanfar" }, { "literal": "Amirhossein Kazerouni" }, { "literal": "Alireza Hosseini" }, { "literal": "Michael Brudno" }, { "literal": "Babak Taati" } ], "citation-key": "arxiv_2609_31364", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9ce76f34abe391289643321027a33ac3cac8b5bd64eaa901f9a5fbf7c5561362", "submitted_at": "2026-09-25T14:59:14Z", "updated_at": "2026-09-25T14:59:14Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.31364v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.31364", "catalog_id": "arxiv:2609.31364", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-09-25", "identifiers": { "arxiv": "2609.31364" }, "record_updated_at": "2026-09-25" }, "genre": "preprint", "id": "arxiv:2609.31364", "issued": { "date-parts": [ [ 2026, 9, 25 ] ] }, "note": "First published: 2026-09-25; Recorded arXiv version: v1; Recorded version updated: 2026-09-25T14:59:14Z.", "title": "OpenVAM: Open-World Visual Attention Modeling with VLMs", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.31957v1", "archive": "arXiv", "archive_location": "2609.31957", "author": [ { "literal": "Zhenhao Zhang" }, { "literal": "Zhaoyu Fan" }, { "literal": "Haohan Ying" }, { "literal": "Jingwen Hu" }, { "literal": "Hancen Fan" }, { "literal": "Junhao Zhou" }, { "literal": "Zitian Chen" }, { "literal": "Linchao Zhu" } ], "citation-key": "arxiv_2609_31957", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fa2bcfa05fcbd6937af6ba3d23e892e5a105248939538dcdc9d7b015daf38593", "submitted_at": "2026-09-25T20:04:24Z", "updated_at": "2026-09-25T20:04:24Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.31957v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.31957", "catalog_id": "arxiv:2609.31957", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-25", "identifiers": { "arxiv": "2609.31957" }, "record_updated_at": "2026-09-25" }, "genre": "preprint", "id": "arxiv:2609.31957", "issued": { "date-parts": [ [ 2026, 9, 25 ] ] }, "note": "First published: 2026-09-25; Recorded arXiv version: v1; Recorded version updated: 2026-09-25T20:04:24Z.", "title": "CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.32351v1", "archive": "arXiv", "archive_location": "2609.32351", "author": [ { "literal": "Yangzhe Peng" }, { "literal": "Xiaoyang Wang" }, { "literal": "Yiyang Zhao" }, { "literal": "Lijun Wu" }, { "literal": "Kun He" } ], "citation-key": "arxiv_2609_32351", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7cc6fd87d2299e2881eab9a2db96e4022663e2d94da5549dcde166c0c8b8be11", "submitted_at": "2026-09-26T08:14:50Z", "updated_at": "2026-09-26T08:14:50Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.32351v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.32351", "catalog_id": "arxiv:2609.32351", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-26", "identifiers": { "arxiv": "2609.32351" }, "record_updated_at": "2026-09-26" }, "genre": "preprint", "id": "arxiv:2609.32351", "issued": { "date-parts": [ [ 2026, 9, 26 ] ] }, "note": "First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T08:14:50Z.", "title": "From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.35814v1", "archive": "arXiv", "archive_location": "2609.35814", "author": [ { "literal": "Xunjian Yin" }, { "literal": "Tianchen Guan" }, { "literal": "Jinao Wang" }, { "literal": "Weili Cao" }, { "literal": "Daisy Xinlei Lin" }, { "literal": "Royce Cheng-Yue" }, { "literal": "Keagan Long" }, { "literal": "Kyle Wong" }, { "literal": "Bhuwan Dhingra" }, { "literal": "Xiangjun Wang" }, { "literal": "Shuyan Zhou" } ], "citation-key": "arxiv_2609_35814", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "197cfb8424584955bc85602d6559037ad31ee815f89b45dc8f9f18c8636552ad", "submitted_at": "2026-09-20T16:16:23Z", "updated_at": "2026-09-20T16:16:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.35814v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.35814", "catalog_id": "arxiv:2609.35814", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-20", "identifiers": { "arxiv": "2609.35814" }, "record_updated_at": "2026-09-20" }, "genre": "preprint", "id": "arxiv:2609.35814", "issued": { "date-parts": [ [ 2026, 9, 20 ] ] }, "note": "First published: 2026-09-20; Recorded arXiv version: v1; Recorded version updated: 2026-09-20T16:16:23Z.", "title": "Constructing Challenging Browser-Use Tasks by Controlled Environment Interventions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.38008v1", "archive": "arXiv", "archive_location": "2609.38008", "author": [ { "literal": "Tongbo Chen" }, { "literal": "Junbo Niu" }, { "literal": "Zhengxi Lu" }, { "literal": "Niu Lian" }, { "literal": "Fei Tang" }, { "literal": "Yuchen Yan" }, { "literal": "Yike Hong" }, { "literal": "Yong Du" }, { "literal": "Yizhou Liu" }, { "literal": "Bofan Chen" }, { "literal": "Yongliang Shen" } ], "citation-key": "arxiv_2609_38008", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b394677ebe37782950cfc56c0be65ca7a93f34e5550ec9425d91921bf1799847", "submitted_at": "2026-09-29T16:57:25Z", "updated_at": "2026-09-29T16:57:25Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.38008v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.38008", "catalog_id": "arxiv:2609.38008", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-29", "identifiers": { "arxiv": "2609.38008" }, "record_updated_at": "2026-09-29" }, "genre": "preprint", "id": "arxiv:2609.38008", "issued": { "date-parts": [ [ 2026, 9, 29 ] ] }, "note": "First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T16:57:25Z.", "title": "HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.39547v1", "archive": "arXiv", "archive_location": "2609.39547", "author": [ { "literal": "Bo Han" }, { "literal": "Qianyi Wang" }, { "literal": "Shuai Liu" }, { "literal": "Xiong Zifan" }, { "literal": "Changqiao Wu" }, { "literal": "Yuanfa Li" }, { "literal": "Pengzhi Gao" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Heng Qu" }, { "literal": "Yunpeng Song" }, { "literal": "Zhongmin Cai" } ], "citation-key": "arxiv_2609_39547", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3594620e97b41f3a7481871588b63ffa4aa8822e8beb42334b2cd888bcfcfaaf", "submitted_at": "2026-09-30T11:45:51Z", "updated_at": "2026-09-30T11:45:51Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.39547v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.39547", "catalog_id": "arxiv:2609.39547", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-30", "identifiers": { "arxiv": "2609.39547" }, "record_updated_at": "2026-09-30" }, "genre": "preprint", "id": "arxiv:2609.39547", "issued": { "date-parts": [ [ 2026, 9, 30 ] ] }, "note": "First published: 2026-09-30; Recorded arXiv version: v1; Recorded version updated: 2026-09-30T11:45:51Z.", "title": "Learning Reliable GUI Agents under Imperfect Priors", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.01215v1", "archive": "arXiv", "archive_location": "2610.01215", "author": [ { "literal": "Cheng Yang" }, { "literal": "Yifan Wu" }, { "literal": "Yutao Huang" }, { "literal": "Zhaohua Zhang" }, { "literal": "Beiduo Chen" }, { "literal": "Muxi Chen" }, { "literal": "Chenchen Zhao" }, { "literal": "Hexuan Deng" }, { "literal": "Haolin Yang" }, { "literal": "Geyuan Zhu" }, { "literal": "Sa Zhu" }, { "literal": "Jianhuan Zhuo" }, { "literal": "Qiuyong Xiao" }, { "literal": "Jianhao Ruan" }, { "literal": "Yiran Peng" }, { "literal": "Jiayi Zhang" }, { "literal": "Tian Ye" }, { "literal": "Xinlei Yu" }, { "literal": "Tianwen Jiang" }, { "literal": "Jihong Zhang" }, { "literal": "Yuyu Luo" } ], "citation-key": "arxiv_2610_01215", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ecd40b78c6de41abb442705b993aad8ebf7b35741536a11e00ebbd60140d1f18", "submitted_at": "2026-10-01T07:22:53Z", "updated_at": "2026-10-01T07:22:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.01215v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.01215", "catalog_id": "arxiv:2610.01215", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-01", "identifiers": { "arxiv": "2610.01215" }, "record_updated_at": "2026-10-01" }, "genre": "preprint", "id": "arxiv:2610.01215", "issued": { "date-parts": [ [ 2026, 10, 1 ] ] }, "note": "First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T07:22:53Z.", "title": "AutoGUIWorld: Image Generators as Visual World Models for GUI Agent", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.02320v1", "archive": "arXiv", "archive_location": "2610.02320", "author": [ { "literal": "A. Said Gurbuz" }, { "literal": "Ahmed Nassar" }, { "literal": "Sunghwan Hong" }, { "literal": "Marc Pollefeys" }, { "literal": "Peter W. J. Staar" } ], "citation-key": "arxiv_2610_02320", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bd66468c2670ec22216e1592719a05e0b56af69606237a50f2067a340172553e", "submitted_at": "2026-10-01T18:00:05Z", "updated_at": "2026-10-01T18:00:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.02320v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.02320", "catalog_id": "arxiv:2610.02320", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-01", "identifiers": { "arxiv": "2610.02320" }, "record_updated_at": "2026-10-01" }, "genre": "preprint", "id": "arxiv:2610.02320", "issued": { "date-parts": [ [ 2026, 10, 1 ] ] }, "note": "First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T18:00:05Z.", "title": "DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.05861v1", "archive": "arXiv", "archive_location": "2610.05861", "author": [ { "literal": "Yongxin Ning" }, { "literal": "Runliang Niu" }, { "literal": "Qianli Xing" }, { "literal": "Zhiyi Duan" }, { "literal": "Qingzu He" }, { "literal": "Pan Wang" }, { "literal": "Qi Wang" } ], "citation-key": "arxiv_2610_05861", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "43845ad64843a0b019c1988d4ba861eccee3c48a7b2c09d0bae7794e5e86347a", "submitted_at": "2026-10-05T06:28:58Z", "updated_at": "2026-10-05T06:28:58Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.05861v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.05861", "catalog_id": "arxiv:2610.05861", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-05", "identifiers": { "arxiv": "2610.05861" }, "record_updated_at": "2026-10-05" }, "genre": "preprint", "id": "arxiv:2610.05861", "issued": { "date-parts": [ [ 2026, 10, 5 ] ] }, "note": "First published: 2026-10-05; Recorded arXiv version: v1; Recorded version updated: 2026-10-05T06:28:58Z.", "title": "Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent Training", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.12611v2", "archive": "arXiv", "archive_location": "2610.12611", "author": [ { "literal": "Tian Jin" }, { "literal": "Wenhao Wang" }, { "literal": "Jing Kang" }, { "literal": "Haoting Shi" }, { "literal": "Rui Ye" }, { "literal": "Yijun Lu" }, { "literal": "Siheng Chen" } ], "citation-key": "arxiv_2610_12611", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "06b25b25e804683e11305e21dd04feb9131aad27f901998eda70ac91e527c6b9", "submitted_at": "2026-10-08T18:31:16Z", "updated_at": "2026-10-14T08:40:10Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2610.12611v2" }, "canonical_source_url": "https://arxiv.org/abs/2610.12611", "catalog_id": "arxiv:2610.12611", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-08", "identifiers": { "arxiv": "2610.12611" }, "record_updated_at": "2026-10-14" }, "genre": "preprint", "id": "arxiv:2610.12611", "issued": { "date-parts": [ [ 2026, 10, 8 ] ] }, "note": "First published: 2026-10-08; Recorded arXiv version: v2; Recorded version updated: 2026-10-14T08:40:10Z.", "title": "SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2610.12984v1", "archive": "arXiv", "archive_location": "2610.12984", "author": [ { "literal": "Yuqi Huang" }, { "literal": "Hui Li" }, { "literal": "Yifei Cao" }, { "literal": "Zikun Cai" }, { "literal": "Tianci Xie" }, { "literal": "Yangfan Gao" }, { "literal": "Pinxue Guo" }, { "literal": "Chaoyun Zhang" }, { "literal": "Bingxuan Li" }, { "literal": "Rui Zheng" }, { "literal": "Hang Yan" }, { "literal": "Ning Liao" } ], "citation-key": "arxiv_2610_12984", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0e90bb713e7034a64821502eb6fc792fa91a5d1e420aff9ff658506d39269f03", "submitted_at": "2026-10-09T04:32:02Z", "updated_at": "2026-10-09T04:32:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.12984v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.12984", "catalog_id": "arxiv:2610.12984", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-09", "identifiers": { "arxiv": "2610.12984" }, "record_updated_at": "2026-10-09" }, "genre": "preprint", "id": "arxiv:2610.12984", "issued": { "date-parts": [ [ 2026, 10, 9 ] ] }, "note": "First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T04:32:02Z.", "title": "Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.13268v1", "archive": "arXiv", "archive_location": "2610.13268", "author": [ { "literal": "Ruotian Zhang" }, { "literal": "Yuhui Zhang" }, { "literal": "Junzhe Huang" }, { "literal": "Yu Xin" }, { "literal": "Hehe Fan" }, { "literal": "Xiaoxiao Sun" } ], "citation-key": "arxiv_2610_13268", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "010e8ebc657dccad670ea6d17985e9c3c1680017f2516eaa86b7ea9db5660990", "submitted_at": "2026-10-09T09:20:02Z", "updated_at": "2026-10-09T09:20:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.13268v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.13268", "catalog_id": "arxiv:2610.13268", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-09", "identifiers": { "arxiv": "2610.13268" }, "record_updated_at": "2026-10-09" }, "genre": "preprint", "id": "arxiv:2610.13268", "issued": { "date-parts": [ [ 2026, 10, 9 ] ] }, "note": "First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T09:20:02Z.", "title": "ConClick: Element-Wise Contrastive Learning Improves GUI Grounding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.14157v1", "archive": "arXiv", "archive_location": "2610.14157", "author": [ { "literal": "Chenyang Yan" }, { "literal": "Yingying Zhang" }, { "literal": "Kanzhi Cheng" }, { "literal": "Qiushi Sun" }, { "literal": "Zhengyuan Pan" }, { "literal": "Zheng Ma" }, { "literal": "Hang Yan" }, { "literal": "Yian Wang" }, { "literal": "Nuo Chen" }, { "literal": "Jialin Cao" }, { "literal": "Xingdong Gong" }, { "literal": "Wenpo Song" }, { "literal": "Han Chen" }, { "literal": "Zichen Ding" }, { "literal": "Fangzhi Xu" }, { "literal": "Shujian Huang" }, { "literal": "Xinyu Dai" }, { "literal": "Yichen Liu" }, { "literal": "Tiankuo Yao" }, { "literal": "Bo Wang" }, { "literal": "Ben Kao" }, { "literal": "Jianbing Zhang" }, { "literal": "Lewei Lu" }, { "literal": "Dahua Lin" } ], "citation-key": "arxiv_2610_14157", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f7d940d3e341fd8c9f23a4829a5ab1150fc07ee231ccda9b108a3f0d785efb9", "submitted_at": "2026-10-09T17:26:38Z", "updated_at": "2026-10-09T17:26:38Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.14157v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.14157", "catalog_id": "arxiv:2610.14157", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-09", "identifiers": { "arxiv": "2610.14157" }, "record_updated_at": "2026-10-09" }, "genre": "preprint", "id": "arxiv:2610.14157", "issued": { "date-parts": [ [ 2026, 10, 9 ] ] }, "note": "First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T17:26:38Z.", "title": "OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.16319v1", "archive": "arXiv", "archive_location": "2610.16319", "author": [ { "literal": "Zijian Cai" }, { "literal": "Haowei Liu" }, { "literal": "Kailai Chen" }, { "literal": "Lin Peng" }, { "literal": "Cong Wan" }, { "literal": "Ziqi Zhang" }, { "literal": "Chunfeng Yuan" }, { "literal": "Bing Li" }, { "literal": "Weiming Hu" }, { "literal": "Haiyang Xu" } ], "citation-key": "arxiv_2610_16319", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4596cc60436c4fa6c2aa0951b4699b804edb73aa1b1a46900b1d14f901d20f3b", "submitted_at": "2026-10-12T07:42:11Z", "updated_at": "2026-10-12T07:42:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.16319v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.16319", "catalog_id": "arxiv:2610.16319", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-12", "identifiers": { "arxiv": "2610.16319" }, "record_updated_at": "2026-10-12" }, "genre": "preprint", "id": "arxiv:2610.16319", "issued": { "date-parts": [ [ 2026, 10, 12 ] ] }, "note": "First published: 2026-10-12; Recorded arXiv version: v1; Recorded version updated: 2026-10-12T07:42:11Z.", "title": "HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.17895v2", "archive": "arXiv", "archive_location": "2610.17895", "author": [ { "literal": "Wayne Chi" }, { "literal": "I-Hung Hsu" }, { "literal": "Li Chen" }, { "literal": "Wei-Lin Chiang" }, { "literal": "Ion Stoica" }, { "literal": "Anastasios Nikolas Angelopoulos" }, { "literal": "Ameet Talwalkar" }, { "literal": "Chris Donahue" }, { "literal": "Cho-Jui Hsieh" } ], "citation-key": "arxiv_2610_17895", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2610.17895", "catalog_id": "arxiv:2610.17895", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-13", "identifiers": { "arxiv": "2610.17895" }, "record_updated_at": "2026-10-14" }, "genre": "preprint", "id": "arxiv:2610.17895", "issued": { "date-parts": [ [ 2026, 10, 13 ] ] }, "note": "First published: 2026-10-13; Recorded arXiv version: v2; Recorded version updated: 2026-10-14T06:37:47Z.", "title": "Interaction-as-a-Judge", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2610.18067v1", "archive": "arXiv", "archive_location": "2610.18067", "author": [ { "literal": "Hang He" }, { "literal": "Linting Wang" }, { "literal": "Guanming Liu" }, { "literal": "Bo Mao" }, { "literal": "Jinxiu Liu" }, { "literal": "Yiran Suo" }, { "literal": "Maosen Zhou" }, { "literal": "Zhiheng Xi" }, { "literal": "Guanting Dong" }, { "literal": "Zhou Shao" }, { "literal": "Rui Zheng" }, { "literal": "Jie Zhou" }, { "literal": "Chengcheng Wan" }, { "literal": "Tao Gui" }, { "literal": "Qi Zhang" }, { "literal": "Xipeng Qiu" }, { "literal": "Xuanjing Huang" } ], "citation-key": "arxiv_2610_18067", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6add363f25f87ea1814c7b79ebf6b51f7431b3745a7d2d910960b78e2d97d13f", "submitted_at": "2026-10-13T09:52:02Z", "updated_at": "2026-10-13T09:52:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.18067v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.18067", "catalog_id": "arxiv:2610.18067", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-13", "identifiers": { "arxiv": "2610.18067" }, "record_updated_at": "2026-10-13" }, "genre": "preprint", "id": "arxiv:2610.18067", "issued": { "date-parts": [ [ 2026, 10, 13 ] ] }, "note": "First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T09:52:02Z.", "title": "WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.19100v1", "archive": "arXiv", "archive_location": "2610.19100", "author": [ { "literal": "Qingsong Xie" }, { "literal": "Jiahao Tian" }, { "literal": "Jiacheng Tang" }, { "literal": "Zhifeng Li" }, { "literal": "Madalina Ciobanu" }, { "literal": "Navan Preet Singh" }, { "literal": "Qingqing Mao" }, { "literal": "Ritankar Das" } ], "citation-key": "arxiv_2610_19100", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "08d90bcec690b238be96207602ca694759c8672fecbed85e30372dd314e4006e", "submitted_at": "2026-10-13T19:37:49Z", "updated_at": "2026-10-13T19:37:49Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.19100v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.19100", "catalog_id": "arxiv:2610.19100", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-13", "identifiers": { "arxiv": "2610.19100" }, "record_updated_at": "2026-10-13" }, "genre": "preprint", "id": "arxiv:2610.19100", "issued": { "date-parts": [ [ 2026, 10, 13 ] ] }, "note": "First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T19:37:49Z.", "title": "GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.19834v1", "archive": "arXiv", "archive_location": "2610.19834", "author": [ { "literal": "Md Farhan Ishmam" }, { "literal": "Kenneth Marino" } ], "citation-key": "arxiv_2610_19834", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6d154a14c5ac85fb352721c203fe7bd709eaba4287ef7376e6a6f5fc395708f1", "submitted_at": "2026-10-14T09:06:49Z", "updated_at": "2026-10-14T09:06:49Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.19834v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.19834", "catalog_id": "arxiv:2610.19834", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-14", "identifiers": { "arxiv": "2610.19834" }, "record_updated_at": "2026-10-14" }, "genre": "preprint", "id": "arxiv:2610.19834", "issued": { "date-parts": [ [ 2026, 10, 14 ] ] }, "note": "First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T09:06:49Z.", "title": "Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.20584v1", "archive": "arXiv", "archive_location": "2610.20584", "author": [ { "literal": "Mingyu Ouyang" }, { "literal": "Yiran Wang" }, { "literal": "Siyuan Hu" }, { "literal": "Xingyilang Yin" }, { "literal": "Huiqiang Sun" }, { "literal": "Guangzhi Wang" }, { "literal": "Junfu Pu" }, { "literal": "Cheng Cheng" }, { "literal": "Honghao Chen" }, { "literal": "Ying Shan" }, { "literal": "Mike Zheng Shou" }, { "literal": "Hwee Tou Ng" } ], "citation-key": "arxiv_2610_20584", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "67b539468bd2bbf0d3b49a5a7eed4791a8ddca4b56ad9515d23a29204d1f069f", "submitted_at": "2026-10-14T17:57:12Z", "updated_at": "2026-10-14T17:57:12Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.20584v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.20584", "catalog_id": "arxiv:2610.20584", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-10-14", "identifiers": { "arxiv": "2610.20584" }, "record_updated_at": "2026-10-14" }, "genre": "preprint", "id": "arxiv:2610.20584", "issued": { "date-parts": [ [ 2026, 10, 14 ] ] }, "note": "First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T17:57:12Z.", "title": "Player-1: Learning to Play from Synthetic Experience", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.23012v1", "archive": "arXiv", "archive_location": "2610.23012", "author": [ { "literal": "Chulhoon Yoon" }, { "literal": "Kyungri Park" }, { "literal": "Jinyeong Yun" }, { "literal": "Daeyun Jeong" }, { "literal": "Sukmin Yun" }, { "literal": "Woohwan Jung" } ], "citation-key": "arxiv_2610_23012", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b9585696d256bacc710dce57bfd7cda6a8037ce5725a30f959028352bc07e97c", "submitted_at": "2026-10-16T06:44:56Z", "updated_at": "2026-10-16T06:44:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.23012v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.23012", "catalog_id": "arxiv:2610.23012", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-16", "identifiers": { "arxiv": "2610.23012" }, "record_updated_at": "2026-10-16" }, "genre": "preprint", "id": "arxiv:2610.23012", "issued": { "date-parts": [ [ 2026, 10, 16 ] ] }, "note": "First published: 2026-10-16; Recorded arXiv version: v1; Recorded version updated: 2026-10-16T06:44:56Z.", "title": "Adaptation of Computer Use Agents to New Software with User Manuals", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.26071v1", "archive": "arXiv", "archive_location": "2610.26071", "author": [ { "literal": "Zhanhui Zhou" }, { "literal": "Weichen Zhang" }, { "literal": "Haoran Liu" }, { "literal": "Lingjie Chen" }, { "literal": "Tianneng Shi" }, { "literal": "Kevin Lin" }, { "literal": "Zhengyuan Yang" }, { "literal": "Lijuan Wang" }, { "literal": "Dawn Song" } ], "citation-key": "arxiv_2610_26071", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0a297401f7ad4dcd2f485ade6bab295e365280bb803dcecc111aebf0693dd203", "submitted_at": "2026-10-19T09:30:54Z", "updated_at": "2026-10-19T09:30:54Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.26071v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.26071", "catalog_id": "arxiv:2610.26071", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-19", "identifiers": { "arxiv": "2610.26071" }, "record_updated_at": "2026-10-19" }, "genre": "preprint", "id": "arxiv:2610.26071", "issued": { "date-parts": [ [ 2026, 10, 19 ] ] }, "note": "First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T09:30:54Z.", "title": "CUA-Lite: An Open Platform for Computer Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.26828v1", "archive": "arXiv", "archive_location": "2610.26828", "author": [ { "literal": "Zhaoyang Wang" }, { "literal": "Qianhui Wu" }, { "literal": "Haorui Wang" }, { "literal": "Simon Yu" }, { "literal": "Baolin Peng" }, { "literal": "Canwen Xu" }, { "literal": "Hao Cheng" }, { "literal": "Wenlin Yao" }, { "literal": "Boyi Liu" }, { "literal": "Yite Wang" }, { "literal": "Jianfeng Gao" }, { "literal": "Huaxiu Yao" } ], "citation-key": "arxiv_2610_26828", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1f1ff33859352b61f017709fff91fd8e32f08636e9423fb044e7ca8e28f06905", "submitted_at": "2026-10-19T17:55:35Z", "updated_at": "2026-10-19T17:55:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.26828v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.26828", "catalog_id": "arxiv:2610.26828", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-19", "identifiers": { "arxiv": "2610.26828" }, "record_updated_at": "2026-10-19" }, "genre": "preprint", "id": "arxiv:2610.26828", "issued": { "date-parts": [ [ 2026, 10, 19 ] ] }, "note": "First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T17:55:35Z.", "title": "Agent World Model in the Wild: Computer-Use Agent Environment Synthesis", "type": "article", "version": "1" }, { "URL": "https://proceedings.mlr.press/v70/shi17a.html", "author": [ { "literal": "Tianlin Shi" }, { "literal": "Andrej Karpathy" }, { "literal": "Linxi Fan" }, { "literal": "Jonathan Hernandez" }, { "literal": "Percy Liang" } ], "citation-key": "cua_ba263493b78b0263c7933138", "collection-title": "Proceedings of Machine Learning Research", "container-title": "Proceedings of the 34th International Conference on Machine Learning", "custom": { "canonical_source_url": "https://proceedings.mlr.press/v70/shi17a.html", "catalog_id": "url:52a3261eb6a19b402e88", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2017-07-17", "identifiers": {}, "publication": { "authors": [ "Tianlin Shi", "Andrej Karpathy", "Linxi Fan", "Jonathan Hernandez", "Percy Liang" ], "date_basis": "Publisher citation_publication_date metadata explicitly states 2017/07/17; this is separate from the conference interval.", "date_parts": [ 2017, 7, 17 ], "doi": null, "event_dates": "06--11 Aug (conference interval reported in the publisher BibTeX month field)", "evidence_urls": [ "https://proceedings.mlr.press/v70/shi17a.html", "https://proceedings.mlr.press/v70/shi17a/shi17a.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": "Publisher citation uses Tianlin Shi and Linxi Fan; the PDF also prints the nicknames Tim and Jim. The ordered publisher author names are retained. DOI not supplied in the retained publisher citation. Publisher metadata supplies the publication date separately from the conference interval.", "pages": "3135-3144", "pdf_url": "https://proceedings.mlr.press/v70/shi17a/shi17a.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "World of Bits: An Open-Domain Platform for Web-Based Agents", "type": "conference-paper", "url": "https://proceedings.mlr.press/v70/shi17a.html", "venue": "Proceedings of the 34th International Conference on Machine Learning", "volume": "70" }, "record_updated_at": null }, "id": "url:52a3261eb6a19b402e88", "issued": { "date-parts": [ [ 2017, 7, 17 ] ] }, "note": "Publication date: 2017-07-17.", "page": "3135-3144", "publisher": "PMLR", "title": "World of Bits: An Open-Domain Platform for Web-Based Agents", "type": "paper-conference", "volume": "70" }, { "DOI": "10.1145/3126594.3126651", "URL": "https://doi.org/10.1145/3126594.3126651", "author": [ { "literal": "Biplab Deka" }, { "literal": "Zifeng Huang" }, { "literal": "Chad Franzen" }, { "literal": "Joshua Hibschman" }, { "literal": "Daniel Afergan" }, { "literal": "Yang Li" }, { "literal": "Jeffrey Nichols" }, { "literal": "Ranjitha Kumar" } ], "citation-key": "cua_402ed654426712089390317c", "container-title": "UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology", "custom": { "canonical_source_url": "https://doi.org/10.1145/3126594.3126651", "catalog_id": "url:b560b5d6abaab98483f6", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2017-10-20", "identifiers": { "doi": "10.1145/3126594.3126651" }, "publication": { "authors": [ "Biplab Deka", "Zifeng Huang", "Chad Franzen", "Joshua Hibschman", "Daniel Afergan", "Yang Li", "Jeffrey Nichols", "Ranjitha Kumar" ], "date_basis": "Supplied day precision: 2017-10-20. PDF cover, Published: 20 October 2017 The 18 January 2026 download date and October 22-25 conference dates are not publication dates.", "date_parts": [ 2017, 10, 20 ], "doi": "10.1145/3126594.3126651", "event_dates": null, "evidence_urls": [ "https://danafergan.com/publications/deka2017rico.pdf", "https://dev.interactionmining.org/archive/rico" ], "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 paper is a distinct resource from the already cataloged Rico dataset (url:0b134b082a7bd507fc6a). The publisher PDF describes 9.7k apps and 72k screens; the project page describes 9.3k apps and 66k screens. The annotation intentionally supplies no merged size claim. No volume number is supplied for this proceedings article.", "pages": "845-854", "pdf_url": "https://danafergan.com/publications/deka2017rico.pdf", "publisher": null, "series": null, "title": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications", "type": "conference-paper", "url": "https://doi.org/10.1145/3126594.3126651", "venue": "UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology", "volume": null }, "record_updated_at": null }, "id": "url:b560b5d6abaab98483f6", "issued": { "date-parts": [ [ 2017, 10, 20 ] ] }, "note": "Publication date: 2017-10-20.", "page": "845-854", "title": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications", "type": "paper-conference" }, { "URL": "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "author": [ { "literal": "Fei Tang" }, { "literal": "Zhangxuan Gu" }, { "literal": "Zhengxi Lu" }, { "literal": "Shangzhan Zhang" }, { "literal": "Zhengwen Zeng" }, { "literal": "Shuheng Shen" }, { "literal": "Changhua Meng" }, { "literal": "Yuchen Yan" }, { "literal": "Wenqi Zhang" }, { "literal": "Yongliang Shen" }, { "literal": "Weiming Lu" }, { "literal": "Yueting Zhuang" } ], "citation-key": "cua_a6fbf231c6d3a11f67403503", "container-title": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "custom": { "canonical_source_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "catalog_id": "url:beb8f1fd6b945ffc9d93", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": {}, "publication": { "authors": [ "Fei Tang", "Zhangxuan Gu", "Zhengxi Lu", "Shangzhan Zhang", "Zhengwen Zeng", "Shuheng Shen", "Changhua Meng", "Yuchen Yan", "Wenqi Zhang", "Yongliang Shen", "Weiming Lu", "Yueting Zhuang" ], "date_basis": "Explicit publisher metadata: month = {June}, year = {2026}; precision=month.", "date_parts": [ 2026, 6 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "https://openaccess.thecvf.com/content/CVPR2026/papers/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.pdf" ], "identity_basis": "No title/DOI/canonical URL match in the current paper catalog or raw archive; closest substantive same-team works were reread and have different contributions.", "issue": null, "notes": "CVF open-access accepted version; PDF states that the final proceedings version is on IEEE Xplore.", "pages": "13007-13016", "pdf_url": "https://openaccess.thecvf.com/content/CVPR2026/papers/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.pdf", "publisher": null, "series": null, "title": "GUI-SAGE: Enhancing GUI Automation with Self-Explanatory Learning", "type": "conference-paper", "url": "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "volume": null }, "record_updated_at": null }, "id": "url:beb8f1fd6b945ffc9d93", "issued": { "date-parts": [ [ 2026, 6 ] ] }, "note": "Publication date: 2026-06.", "page": "13007-13016", "title": "GUI-SAGE: Enhancing GUI Automation with Self-Explanatory Learning", "type": "paper-conference" } ]