[ { "id": "arxiv:2501.16150", "citation-key": "arxiv_2501_16150", "type": "article", "title": "A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions", "URL": "https://arxiv.org/abs/2501.16150v3", "custom": { "catalog_id": "arxiv:2501.16150", "catalog_kind": "survey", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2501.16150", "identifiers": { "arxiv": "2501.16150" }, "first_published_at": "2025-01-27", "record_updated_at": "2026-03-27", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b36fe818cb176c434b953fe8d2c97b67176b58cc6f8426b629231875de3c0896", "submitted_at": "2025-01-27T15:44:02Z", "updated_at": "2026-03-27T07:41:10Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2501.16150v3" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-01-27; Recorded arXiv version: v3; Recorded version updated: 2026-03-27T07:41:10Z.", "author": [ { "literal": "Pascal J. Sager" }, { "literal": "Benjamin Meyer" }, { "literal": "Peng Yan" }, { "literal": "Rebekka von Wartburg-Kottler" }, { "literal": "Layan Etaiwi" }, { "literal": "Aref Enayati" }, { "literal": "Gabriel Nobel" }, { "literal": "Ahmed Abdulkadir" }, { "literal": "Benjamin F. Grewe" }, { "literal": "Thilo Stadelmann" } ], "issued": { "date-parts": [ [ 2025, 1, 27 ] ] }, "archive": "arXiv", "archive_location": "2501.16150", "genre": "preprint", "version": "3" }, { "id": "arxiv:2508.04482", "citation-key": "arxiv_2508_04482", "type": "article", "title": "OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use", "URL": "https://arxiv.org/abs/2508.04482v1", "custom": { "catalog_id": "arxiv:2508.04482", "catalog_kind": "survey", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2508.04482", "identifiers": { "arxiv": "2508.04482" }, "first_published_at": "2025-08-06", "record_updated_at": "2025-08-06", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f14fdd895e52277a3695eeb83e5095472051d139aec63f22f9c63d344c051dad", "submitted_at": "2025-08-06T14:33:45Z", "updated_at": "2025-08-06T14:33:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2508.04482v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-08-06; Recorded arXiv version: v1; Recorded version updated: 2025-08-06T14:33:45Z.", "author": [ { "literal": "Xueyu Hu" }, { "literal": "Tao Xiong" }, { "literal": "Biao Yi" }, { "literal": "Zishu Wei" }, { "literal": "Ruixuan Xiao" }, { "literal": "Yurun Chen" }, { "literal": "Jiasheng Ye" }, { "literal": "Meiling Tao" }, { "literal": "Xiangxin Zhou" }, { "literal": "Ziyu Zhao" }, { "literal": "Yuhuai Li" }, { "literal": "Shengze Xu" }, { "literal": "Shenzhi Wang" }, { "literal": "Xinchen Xu" }, { "literal": "Shuofei Qiao" }, { "literal": "Zhaokai Wang" }, { "literal": "Kun Kuang" }, { "literal": "Tieyong Zeng" }, { "literal": "Liang Wang" }, { "literal": "Jiwei Li" }, { "literal": "Yuchen Eleanor Jiang" }, { "literal": "Wangchunshu Zhou" }, { "literal": "Guoyin Wang" }, { "literal": "Keting Yin" }, { "literal": "Zhou Zhao" }, { "literal": "Hongxia Yang" }, { "literal": "Fan Wu" }, { "literal": "Shengyu Zhang" }, { "literal": "Fei Wu" } ], "issued": { "date-parts": [ [ 2025, 8, 6 ] ] }, "archive": "arXiv", "archive_location": "2508.04482", "genre": "preprint", "version": "1" }, { "id": "arxiv:2411.18279", "citation-key": "arxiv_2411_18279", "type": "article", "title": "Large Language Model-Brained GUI Agents: A Survey", "URL": "https://arxiv.org/abs/2411.18279v12", "custom": { "catalog_id": "arxiv:2411.18279", "catalog_kind": "survey", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2411.18279", "identifiers": { "arxiv": "2411.18279" }, "first_published_at": "2024-11-27", "record_updated_at": "2025-05-06", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2f692aa06152820ae60359fc2cc52aaed2ca8a97fe1efb9b8037de973956467a", "submitted_at": "2024-11-27T12:13:39Z", "updated_at": "2025-05-06T15:08:00Z", "version": 12, "versioned_url": "https://arxiv.org/abs/2411.18279v12" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-11-27; Recorded arXiv version: v12; Recorded version updated: 2025-05-06T15:08:00Z.", "author": [ { "literal": "Chaoyun Zhang" }, { "literal": "Shilin He" }, { "literal": "Jiaxu Qian" }, { "literal": "Bowen Li" }, { "literal": "Liqun Li" }, { "literal": "Si Qin" }, { "literal": "Yu Kang" }, { "literal": "Minghua Ma" }, { "literal": "Guyue Liu" }, { "literal": "Qingwei Lin" }, { "literal": "Saravan Rajmohan" }, { "literal": "Dongmei Zhang" }, { "literal": "Qi Zhang" } ], "issued": { "date-parts": [ [ 2024, 11, 27 ] ] }, "archive": "arXiv", "archive_location": "2411.18279", "genre": "preprint", "version": "12" }, { "id": "arxiv:2210.03347", "citation-key": "arxiv_2210_03347", "type": "article", "title": "Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding", "URL": "https://arxiv.org/abs/2210.03347v2", "custom": { "catalog_id": "arxiv:2210.03347", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2210.03347", "identifiers": { "arxiv": "2210.03347" }, "first_published_at": "2022-10-07", "record_updated_at": "2023-06-15", "catalog_scope": "adjacent", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2022-10-07; Recorded arXiv version: v2; Recorded version updated: 2023-06-15T21:34:23Z.", "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" } ], "issued": { "date-parts": [ [ 2022, 10, 7 ] ] }, "archive": "arXiv", "archive_location": "2210.03347", "genre": "preprint", "version": "2" }, { "id": "url:cccd967aa993404d74d0", "citation-key": "cua_1b4a3a269ca9f1884a566476", "type": "paper-conference", "title": "Koala: Capture, Share, Automate, Personalize Business Processes on the Web", "URL": "https://doi.org/10.1145/1240624.1240767", "custom": { "catalog_id": "url:cccd967aa993404d74d0", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://doi.org/10.1145/1240624.1240767", "identifiers": { "doi": "10.1145/1240624.1240767" }, "first_published_at": null, "record_updated_at": null, "catalog_scope": "core", "publication": { "authors": [ "Greg Little", "Tessa A. Lau", "Allen Cypher", "James Lin", "Eben M. Haber", "Eser Kandogan" ], "date_basis": "Supplied year precision: 2007. CHI 2007 proceedings heading and copyright year The IBM page has an unlabeled Date of 22 Oct 2007, while the paper gives April/May event dates. Their roles do not establish a reliable day-level publication date.", "date_parts": [ 2007 ], "doi": "10.1145/1240624.1240767", "event_dates": null, "evidence_urls": [ "https://research.ibm.com/publications/koala-capture-share-automate-personalize-business-processes-on-the-web", "https://plunk.org/eben/PublishedPapers/KoalaCHI.pdf" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "This proposal is the specific Koala paper. It does not automatically merge every later CoScripter publication or project record. Exact publication date is unresolved; only the clearly established year is proposed.", "pages": "943-946", "pdf_url": "https://plunk.org/eben/PublishedPapers/KoalaCHI.pdf", "publisher": null, "series": null, "title": "Koala: Capture, Share, Automate, Personalize Business Processes on the Web", "type": "conference-paper", "url": "https://doi.org/10.1145/1240624.1240767", "venue": "CHI 2007 Proceedings", "volume": null }, "citation_edition": "publication", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "Publication date: 2007.", "author": [ { "literal": "Greg Little" }, { "literal": "Tessa A. Lau" }, { "literal": "Allen Cypher" }, { "literal": "James Lin" }, { "literal": "Eben M. Haber" }, { "literal": "Eser Kandogan" } ], "issued": { "date-parts": [ [ 2007 ] ] }, "DOI": "10.1145/1240624.1240767", "container-title": "CHI 2007 Proceedings", "page": "943-946" }, { "id": "url:a4cdb2ee0d07d3980651", "citation-key": "cua_510831381c08385eb74fb95e", "type": "paper-conference", "title": "Sikuli: Using GUI screenshots for search and automation", "URL": "https://doi.org/10.1145/1622176.1622213", "custom": { "catalog_id": "url:a4cdb2ee0d07d3980651", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://doi.org/10.1145/1622176.1622213", "identifiers": { "doi": "10.1145/1622176.1622213" }, "first_published_at": null, "record_updated_at": null, "catalog_scope": "core", "publication": { "authors": [ "Tom Yeh", "Tsung-Hsiang Chang", "Robert C. Miller" ], "date_basis": "Supplied month precision: 2009-10. Date Issued: October 2009", "date_parts": [ 2009, 10 ], "doi": "10.1145/1622176.1622213", "event_dates": null, "evidence_urls": [ "https://dspace.mit.edu/entities/publication/604a3f79-451d-4186-a94e-d12690ffe40a" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Institutional abstract and published-version citation supply the retained evidence; the institution identifies an author final manuscript record. Exact publication day is not supplied. Operating-system-specific experiments are not asserted.", "pages": "183-192", "pdf_url": null, "publisher": null, "series": null, "title": "Sikuli: Using GUI screenshots for search and automation", "type": "conference-paper", "url": "https://doi.org/10.1145/1622176.1622213", "venue": "Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology (UIST '09)", "volume": null }, "citation_edition": "publication", "manuscript_read_level": "abstract_and_author_project_only" }, "note": "Publication date: 2009-10.", "author": [ { "literal": "Tom Yeh" }, { "literal": "Tsung-Hsiang Chang" }, { "literal": "Robert C. Miller" } ], "issued": { "date-parts": [ [ 2009, 10 ] ] }, "DOI": "10.1145/1622176.1622213", "container-title": "Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology (UIST '09)", "page": "183-192" }, { "id": "url:392a602c660ffa91be46", "citation-key": "cua_6b7f9d608ed89d1625610eb1", "type": "paper-conference", "title": "SUGILITE: Creating Multimodal Smartphone Automation by Demonstration", "URL": "https://doi.org/10.1145/3025453.3025483", "custom": { "catalog_id": "url:392a602c660ffa91be46", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://doi.org/10.1145/3025453.3025483", "identifiers": { "doi": "10.1145/3025453.3025483" }, "first_published_at": null, "record_updated_at": null, "catalog_scope": "core", "publication": { "authors": [ "Toby Jia-Jun Li", "Amos Azaria", "Brad A. Myers" ], "date_basis": "Supplied year precision: 2017. Publications: SUGILITE, CHI 2017 Only publication year is asserted; event dates are kept separate.", "date_parts": [ 2017 ], "doi": "10.1145/3025453.3025483", "event_dates": null, "evidence_urls": [ "https://www.cs.cmu.edu/~NatProg/sugilite.html", "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Related to later APPINITE and PUMICE work but distinguished here by its 2017 three-author publication and base demonstration-automation contribution. Publication month/day are not independently identified by the retained sources.", "pages": "6038-6049", "pdf_url": "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf", "publisher": null, "series": null, "title": "SUGILITE: Creating Multimodal Smartphone Automation by Demonstration", "type": "conference-paper", "url": "https://doi.org/10.1145/3025453.3025483", "venue": "Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems", "volume": null }, "citation_edition": "publication", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "Publication date: 2017.", "author": [ { "literal": "Toby Jia-Jun Li" }, { "literal": "Amos Azaria" }, { "literal": "Brad A. Myers" } ], "issued": { "date-parts": [ [ 2017 ] ] }, "DOI": "10.1145/3025453.3025483", "container-title": "Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems", "page": "6038-6049" }, { "id": "url:b560b5d6abaab98483f6", "citation-key": "cua_402ed654426712089390317c", "type": "paper-conference", "title": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications", "URL": "https://doi.org/10.1145/3126594.3126651", "custom": { "catalog_id": "url:b560b5d6abaab98483f6", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://doi.org/10.1145/3126594.3126651", "identifiers": { "doi": "10.1145/3126594.3126651" }, "first_published_at": "2017-10-20", "record_updated_at": null, "catalog_scope": "core", "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 }, "citation_edition": "publication", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "Publication date: 2017-10-20.", "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" } ], "issued": { "date-parts": [ [ 2017, 10, 20 ] ] }, "DOI": "10.1145/3126594.3126651", "container-title": "UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology", "page": "845-854" }, { "id": "url:52a3261eb6a19b402e88", "citation-key": "cua_ba263493b78b0263c7933138", "type": "paper-conference", "title": "World of Bits: An Open-Domain Platform for Web-Based Agents", "URL": "https://proceedings.mlr.press/v70/shi17a.html", "custom": { "catalog_id": "url:52a3261eb6a19b402e88", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://proceedings.mlr.press/v70/shi17a.html", "identifiers": {}, "first_published_at": "2017-07-17", "record_updated_at": null, "catalog_scope": "core", "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" }, "citation_edition": "publication", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "Publication date: 2017-07-17.", "author": [ { "literal": "Tianlin Shi" }, { "literal": "Andrej Karpathy" }, { "literal": "Linxi Fan" }, { "literal": "Jonathan Hernandez" }, { "literal": "Percy Liang" } ], "issued": { "date-parts": [ [ 2017, 7, 17 ] ] }, "container-title": "Proceedings of the 34th International Conference on Machine Learning", "publisher": "PMLR", "collection-title": "Proceedings of Machine Learning Research", "volume": "70", "page": "3135-3144" }, { "id": "arxiv:1802.08802", "citation-key": "arxiv_1802_08802", "type": "article", "title": "Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration", "URL": "https://arxiv.org/abs/1802.08802v1", "custom": { "catalog_id": "arxiv:1802.08802", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/1802.08802", "identifiers": { "arxiv": "1802.08802" }, "first_published_at": "2018-02-24", "record_updated_at": "2018-02-24", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "75d19fa97ce85a93bb9665a8ae06607bc0b90fde1c8376cdd60e99b55e90729c", "submitted_at": "2018-02-24T05:32:47Z", "updated_at": "2018-02-24T05:32:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/1802.08802v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2018-02-24; Recorded arXiv version: v1; Recorded version updated: 2018-02-24T05:32:47Z.", "author": [ { "literal": "Evan Zheran Liu" }, { "literal": "Kelvin Guu" }, { "literal": "Panupong Pasupat" }, { "literal": "Tianlin Shi" }, { "literal": "Percy Liang" } ], "issued": { "date-parts": [ [ 2018, 2, 24 ] ] }, "archive": "arXiv", "archive_location": "1802.08802", "genre": "preprint", "version": "1" }, { "id": "arxiv:2307.10088", "citation-key": "arxiv_2307_10088", "type": "article", "title": "Android in the Wild: A Large-Scale Dataset for Android Device Control", "URL": "https://arxiv.org/abs/2307.10088v2", "custom": { "catalog_id": "arxiv:2307.10088", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2307.10088", "identifiers": { "arxiv": "2307.10088" }, "first_published_at": "2023-07-19", "record_updated_at": "2023-10-27", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "def4616f7cb13fe839e500c4b3171eafbe37b155b5d14301137806d6a5cde939", "submitted_at": "2023-07-19T15:57:24Z", "updated_at": "2023-10-27T14:24:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2307.10088v2" }, "publication": { "authors": [ "Christopher Rawles", "Alice Li", "Daniel Rodriguez", "Oriana Riva", "Timothy Lillicrap" ], "date_basis": "Explicit publisher citation_publication_date: 2023-12-15. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2023, 12, 15 ], "doi": "10.52202/075280-2609", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "59708-59728", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2023/file/bbbb6308b402fe909c39dd29950c32e0-Paper-Datasets_and_Benchmarks.pdf", "publisher": null, "series": null, "title": "AndroidInTheWild: A Large-Scale Dataset For Android Device Control", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html", "venue": "Advances in Neural Information Processing Systems", "volume": "36" }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2023-07-19; Recorded arXiv version: v2; Recorded version updated: 2023-10-27T14:24:31Z.", "author": [ { "literal": "Christopher Rawles" }, { "literal": "Alice Li" }, { "literal": "Daniel Rodriguez" }, { "literal": "Oriana Riva" }, { "literal": "Timothy Lillicrap" } ], "issued": { "date-parts": [ [ 2023, 7, 19 ] ] }, "archive": "arXiv", "archive_location": "2307.10088", "genre": "preprint", "version": "2" }, { "id": "arxiv:2207.01206", "citation-key": "arxiv_2207_01206", "type": "article", "title": "WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents", "URL": "https://arxiv.org/abs/2207.01206v4", "custom": { "catalog_id": "arxiv:2207.01206", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2207.01206", "identifiers": { "arxiv": "2207.01206" }, "first_published_at": "2022-07-04", "record_updated_at": "2023-02-08", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6de4ab2a89875f1ccd99bbaa075c234d82979e845f27fe9530bdad0539c49570", "submitted_at": "2022-07-04T05:30:22Z", "updated_at": "2023-02-08T01:39:30Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2207.01206v4" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2022-07-04; Recorded arXiv version: v4; Recorded version updated: 2023-02-08T01:39:30Z.", "author": [ { "literal": "Shunyu Yao" }, { "literal": "Howard Chen" }, { "literal": "John Yang" }, { "literal": "Karthik Narasimhan" } ], "issued": { "date-parts": [ [ 2022, 7, 4 ] ] }, "archive": "arXiv", "archive_location": "2207.01206", "genre": "preprint", "version": "4" }, { "id": "arxiv:2306.06070", "citation-key": "arxiv_2306_06070", "type": "article", "title": "Mind2Web: Towards a Generalist Agent for the Web", "URL": "https://arxiv.org/abs/2306.06070v3", "custom": { "catalog_id": "arxiv:2306.06070", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2306.06070", "identifiers": { "arxiv": "2306.06070" }, "first_published_at": "2023-06-09", "record_updated_at": "2023-12-09", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2023-06-09; Recorded arXiv version: v3; Recorded version updated: 2023-12-09T05:57:46Z.", "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" } ], "issued": { "date-parts": [ [ 2023, 6, 9 ] ] }, "archive": "arXiv", "archive_location": "2306.06070", "genre": "preprint", "version": "3" }, { "id": "arxiv:2307.13854", "citation-key": "arxiv_2307_13854", "type": "article", "title": "WebArena: A Realistic Web Environment for Building Autonomous Agents", "URL": "https://arxiv.org/abs/2307.13854v4", "custom": { "catalog_id": "arxiv:2307.13854", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2307.13854", "identifiers": { "arxiv": "2307.13854" }, "first_published_at": "2023-07-25", "record_updated_at": "2024-04-16", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0e9eca0165573ba53b663acbb1c7962fd2d64bc6633f10397f9cad229772a363", "submitted_at": "2023-07-25T22:59:32Z", "updated_at": "2024-04-16T15:13:18Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2307.13854v4" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2023-07-25; Recorded arXiv version: v4; Recorded version updated: 2024-04-16T15:13:18Z.", "author": [ { "literal": "Shuyan Zhou" }, { "literal": "Frank F. Xu" }, { "literal": "Hao Zhu" }, { "literal": "Xuhui Zhou" }, { "literal": "Robert Lo" }, { "literal": "Abishek Sridhar" }, { "literal": "Xianyi Cheng" }, { "literal": "Tianyue Ou" }, { "literal": "Yonatan Bisk" }, { "literal": "Daniel Fried" }, { "literal": "Uri Alon" }, { "literal": "Graham Neubig" } ], "issued": { "date-parts": [ [ 2023, 7, 25 ] ] }, "archive": "arXiv", "archive_location": "2307.13854", "genre": "preprint", "version": "4" }, { "id": "arxiv:2404.07972", "citation-key": "arxiv_2404_07972", "type": "article", "title": "OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments", "URL": "https://arxiv.org/abs/2404.07972v2", "custom": { "catalog_id": "arxiv:2404.07972", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2404.07972", "identifiers": { "arxiv": "2404.07972" }, "first_published_at": "2024-04-11", "record_updated_at": "2024-05-30", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a347bfcb4de03a60410392b52d522e5b7ad5dbabb474d60fc1ec097e74c4008d", "submitted_at": "2024-04-11T17:56:05Z", "updated_at": "2024-05-30T08:55:12Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2404.07972v2" }, "publication": { "authors": [ "Tianbao Xie", "Danyang Zhang", "Jixuan Chen", "Xiaochuan Li", "Siheng Zhao", "Ruisheng Cao", "Toh J. Hua", "Zhoujun Cheng", "Dongchan Shin", "Fangyu Lei", "Yitao Liu", "Yiheng Xu", "Shuyan Zhou", "Silvio Savarese", "Caiming Xiong", "Victor Zhong", "Tao Yu" ], "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": "10.52202/079017-1650", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/5d413e48f84dc61244b6be550f1cd8f5-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. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "52040-52094", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/5d413e48f84dc61244b6be550f1cd8f5-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/5d413e48f84dc61244b6be550f1cd8f5-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-04-11; Recorded arXiv version: v2; Recorded version updated: 2024-05-30T08:55:12Z.", "author": [ { "literal": "Tianbao Xie" }, { "literal": "Danyang Zhang" }, { "literal": "Jixuan Chen" }, { "literal": "Xiaochuan Li" }, { "literal": "Siheng Zhao" }, { "literal": "Ruisheng Cao" }, { "literal": "Toh Jing Hua" }, { "literal": "Zhoujun Cheng" }, { "literal": "Dongchan Shin" }, { "literal": "Fangyu Lei" }, { "literal": "Yitao Liu" }, { "literal": "Yiheng Xu" }, { "literal": "Shuyan Zhou" }, { "literal": "Silvio Savarese" }, { "literal": "Caiming Xiong" }, { "literal": "Victor Zhong" }, { "literal": "Tao Yu" } ], "issued": { "date-parts": [ [ 2024, 4, 11 ] ] }, "archive": "arXiv", "archive_location": "2404.07972", "genre": "preprint", "version": "2" }, { "id": "arxiv:2405.14573", "citation-key": "arxiv_2405_14573", "type": "article", "title": "AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents", "URL": "https://arxiv.org/abs/2405.14573v5", "custom": { "catalog_id": "arxiv:2405.14573", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2405.14573", "identifiers": { "arxiv": "2405.14573" }, "first_published_at": "2024-05-23", "record_updated_at": "2025-04-06", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a33b8b0a03c0dc7ac3f699c34193a526d20791bfedfdde2a2fb89604959e08c2", "submitted_at": "2024-05-23T13:48:54Z", "updated_at": "2025-04-06T20:37:50Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2405.14573v5" }, "publication": { "authors": [ "Chris Rawles", "Sarah Clinckemaillie", "Yifan Chang", "Jonathan Waltz", "Gabrielle Lau", "Marybeth Fair", "Alice Li", "William Bishop", "Wei Li", "Folawiyo Campbell-Ajala", "Daniel Toyama", "Robert Berry", "Divya Tyamagundlu", "Timothy Lillicrap", "Oriana Riva" ], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 5, 1 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://proceedings.iclr.cc/paper_files/paper/2025/hash/01a83bc2f2732a58e6aa731e659e7101-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "406-441", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/01a83bc2f2732a58e6aa731e659e7101-Paper-Conference.pdf", "publisher": null, "series": null, "title": "AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/01a83bc2f2732a58e6aa731e659e7101-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-05-23; Recorded arXiv version: v5; Recorded version updated: 2025-04-06T20:37:50Z.", "author": [ { "literal": "Christopher Rawles" }, { "literal": "Sarah Clinckemaillie" }, { "literal": "Yifan Chang" }, { "literal": "Jonathan Waltz" }, { "literal": "Gabrielle Lau" }, { "literal": "Marybeth Fair" }, { "literal": "Alice Li" }, { "literal": "William Bishop" }, { "literal": "Wei Li" }, { "literal": "Folawiyo Campbell-Ajala" }, { "literal": "Daniel Toyama" }, { "literal": "Robert Berry" }, { "literal": "Divya Tyamagundlu" }, { "literal": "Timothy Lillicrap" }, { "literal": "Oriana Riva" } ], "issued": { "date-parts": [ [ 2024, 5, 23 ] ] }, "archive": "arXiv", "archive_location": "2405.14573", "genre": "preprint", "version": "5" }, { "id": "arxiv:2411.04890", "citation-key": "arxiv_2411_04890", "type": "article", "title": "GUI Agents with Foundation Models: A Comprehensive Survey", "URL": "https://arxiv.org/abs/2411.04890v2", "custom": { "catalog_id": "arxiv:2411.04890", "catalog_kind": "survey", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2411.04890", "identifiers": { "arxiv": "2411.04890" }, "first_published_at": "2024-11-07", "record_updated_at": "2025-02-13", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "57670445f9b0041bfb505a195d01a9ded6234e01e44c9aa43a6aee5ebd57dd93", "submitted_at": "2024-11-07T17:28:10Z", "updated_at": "2025-02-13T10:09:37Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2411.04890v2" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-11-07; Recorded arXiv version: v2; Recorded version updated: 2025-02-13T10:09:37Z.", "author": [ { "literal": "Shuai Wang" }, { "literal": "Weiwen Liu" }, { "literal": "Jingxuan Chen" }, { "literal": "Yuqi Zhou" }, { "literal": "Weinan Gan" }, { "literal": "Xingshan Zeng" }, { "literal": "Yuhan Che" }, { "literal": "Shuai Yu" }, { "literal": "Xinlong Hao" }, { "literal": "Kun Shao" }, { "literal": "Bin Wang" }, { "literal": "Chuhan Wu" }, { "literal": "Yasheng Wang" }, { "literal": "Ruiming Tang" }, { "literal": "Jianye Hao" } ], "issued": { "date-parts": [ [ 2024, 11, 7 ] ] }, "archive": "arXiv", "archive_location": "2411.04890", "genre": "preprint", "version": "2" }, { "id": "arxiv:2503.23350", "citation-key": "arxiv_2503_23350", "type": "article", "title": "A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models", "URL": "https://arxiv.org/abs/2503.23350v4", "custom": { "catalog_id": "arxiv:2503.23350", "catalog_kind": "survey", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2503.23350", "identifiers": { "arxiv": "2503.23350" }, "first_published_at": "2025-03-30", "record_updated_at": "2025-08-05", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4b214bd8e5a34c0e8ca16a3be4fcf638a59a17ca524276dbef3c6b75f08398bb", "submitted_at": "2025-03-30T08:15:44Z", "updated_at": "2025-08-05T11:47:41Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2503.23350v4" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-03-30; Recorded arXiv version: v4; Recorded version updated: 2025-08-05T11:47:41Z.", "author": [ { "literal": "Liangbo Ning" }, { "literal": "Ziran Liang" }, { "literal": "Zhuohang Jiang" }, { "literal": "Haohao Qu" }, { "literal": "Yujuan Ding" }, { "literal": "Wenqi Fan" }, { "literal": "Xiao-yong Wei" }, { "literal": "Shanru Lin" }, { "literal": "Hui Liu" }, { "literal": "Philip S. Yu" }, { "literal": "Qing Li" } ], "issued": { "date-parts": [ [ 2025, 3, 30 ] ] }, "archive": "arXiv", "archive_location": "2503.23350", "genre": "preprint", "version": "4" }, { "id": "arxiv:2504.19838", "citation-key": "arxiv_2504_19838", "type": "article", "title": "LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects", "URL": "https://arxiv.org/abs/2504.19838v3", "custom": { "catalog_id": "arxiv:2504.19838", "catalog_kind": "survey", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2504.19838", "identifiers": { "arxiv": "2504.19838" }, "first_published_at": "2025-04-28", "record_updated_at": "2025-11-17", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9103197fa1274fac79ae9e4472f5fbdc9a210548afb024f1d4259c6bb0131bf2", "submitted_at": "2025-04-28T14:39:25Z", "updated_at": "2025-11-17T15:51:58Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2504.19838v3" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-04-28; Recorded arXiv version: v3; Recorded version updated: 2025-11-17T15:51:58Z.", "author": [ { "literal": "Guangyi Liu" }, { "literal": "Pengxiang Zhao" }, { "literal": "Yaozhen Liang" }, { "literal": "Liang Liu" }, { "literal": "Yaxuan Guo" }, { "literal": "Han Xiao" }, { "literal": "Weifeng Lin" }, { "literal": "Yuxiang Chai" }, { "literal": "Yue Han" }, { "literal": "Shuai Ren" }, { "literal": "Hao Wang" }, { "literal": "Xiaoyu Liang" }, { "literal": "WenHao Wang" }, { "literal": "Tianze Wu" }, { "literal": "Zhengxi Lu" }, { "literal": "Siheng Chen" }, { "literal": "LiLinghao" }, { "literal": "Hao Wang" }, { "literal": "Guanjing Xiong" }, { "literal": "Yong Liu" }, { "literal": "Hongsheng Li" } ], "issued": { "date-parts": [ [ 2025, 4, 28 ] ] }, "archive": "arXiv", "archive_location": "2504.19838", "genre": "preprint", "version": "3" }, { "id": "arxiv:2503.23434", "citation-key": "arxiv_2503_23434", "type": "article", "title": "Towards Trustworthy GUI Agents: A Survey", "URL": "https://arxiv.org/abs/2503.23434v2", "custom": { "catalog_id": "arxiv:2503.23434", "catalog_kind": "survey", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2503.23434", "identifiers": { "arxiv": "2503.23434" }, "first_published_at": "2025-03-30", "record_updated_at": "2026-02-24", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5a6811c6d0c3b30d4e6af2f7b0beef8aa8f1ad99ceb325182305e571fe5c398f", "submitted_at": "2025-03-30T13:26:00Z", "updated_at": "2026-02-24T05:24:23Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.23434v2" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-03-30; Recorded arXiv version: v2; Recorded version updated: 2026-02-24T05:24:23Z.", "author": [ { "literal": "Yucheng Shi" }, { "literal": "Wenhao Yu" }, { "literal": "Jingyuan Huang" }, { "literal": "Wenlin Yao" }, { "literal": "Wenhu Chen" }, { "literal": "Ninghao Liu" } ], "issued": { "date-parts": [ [ 2025, 3, 30 ] ] }, "archive": "arXiv", "archive_location": "2503.23434", "genre": "preprint", "version": "2" }, { "id": "arxiv:2609.02309", "citation-key": "arxiv_2609_02309", "type": "article", "title": "Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization", "URL": "https://arxiv.org/abs/2609.02309v1", "custom": { "catalog_id": "arxiv:2609.02309", "catalog_kind": "survey", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2609.02309", "identifiers": { "arxiv": "2609.02309" }, "first_published_at": "2026-09-02", "record_updated_at": "2026-09-02", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ec439fd2cfdf7319d77ef5ab58e50143bceb3f8205ccffa0d83555f10dece42a", "submitted_at": "2026-09-02T08:54:58Z", "updated_at": "2026-09-02T08:54:58Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.02309v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T08:54:58Z.", "author": [ { "literal": "Bizhe Bai" }, { "literal": "Jiakang Yuan" }, { "literal": "Hongming Wu" }, { "literal": "Xinyue Wang" }, { "literal": "Jie Ren" }, { "literal": "Siyao Chen" }, { "literal": "Yuchen Ya" }, { "literal": "Fan Bai" }, { "literal": "Pai Peng" }, { "literal": "Huafeng Qin" }, { "literal": "Tao Chen" } ], "issued": { "date-parts": [ [ 2026, 9, 2 ] ] }, "archive": "arXiv", "archive_location": "2609.02309", "genre": "preprint", "version": "1" }, { "id": "release:awesomecua:v2026.10.18", "citation-key": "awesomecua2026", "type": "dataset", "title": "AwesomeCUA catalog: v2026.10.18", "author": [ { "literal": "AwesomeCUA contributors" } ], "issued": { "date-parts": [ [ 2026, 10, 18 ] ] }, "URL": "https://github.com/reacher-z/Awesome-CUA/releases/tag/v2026.10.18", "version": "v2026.10.18", "custom": { "source_commit": "87166fe8ad9c8e832f7a90ee84b2e93c6e0e40db", "catalog_sha256": "7f71a1683ab013e587a20086c3e357956981f517a24ae8bc8e81791108c66e4f", "bibliography_authority": "Published tag, catalog bytes and release asset integrity independently verified.", "manuscript_read_level": "dataset_snapshot_integrity_inspection" } }, { "id": "arxiv:2410.05243", "citation-key": "arxiv_2410_05243", "type": "article", "title": "Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents", "URL": "https://arxiv.org/abs/2410.05243v3", "custom": { "catalog_id": "arxiv:2410.05243", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2410.05243", "identifiers": { "arxiv": "2410.05243" }, "first_published_at": "2024-10-07", "record_updated_at": "2025-06-17", "catalog_scope": "core", "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" }, "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" }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-10-07; Recorded arXiv version: v3; Recorded version updated: 2025-06-17T15:06:02Z.", "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" } ], "issued": { "date-parts": [ [ 2024, 10, 7 ] ] }, "archive": "arXiv", "archive_location": "2410.05243", "genre": "preprint", "version": "3" }, { "id": "arxiv:2501.12326", "citation-key": "arxiv_2501_12326", "type": "article", "title": "UI-TARS: Pioneering Automated GUI Interaction with Native Agents", "URL": "https://arxiv.org/abs/2501.12326v1", "custom": { "catalog_id": "arxiv:2501.12326", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2501.12326", "identifiers": { "arxiv": "2501.12326" }, "first_published_at": "2025-01-21", "record_updated_at": "2025-01-21", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-01-21; Recorded arXiv version: v1; Recorded version updated: 2025-01-21T17:48:10Z.", "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" } ], "issued": { "date-parts": [ [ 2025, 1, 21 ] ] }, "archive": "arXiv", "archive_location": "2501.12326", "genre": "preprint", "version": "1" }, { "id": "arxiv:2401.01614", "citation-key": "arxiv_2401_01614", "type": "article", "title": "GPT-4V(ision) is a Generalist Web Agent, if Grounded", "URL": "https://arxiv.org/abs/2401.01614v2", "custom": { "catalog_id": "arxiv:2401.01614", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2401.01614", "identifiers": { "arxiv": "2401.01614" }, "first_published_at": "2024-01-03", "record_updated_at": "2024-03-12", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a005fb14b21cf17521f4ea966e555d9963092b709bd9280c6e72a9bf0f5fa93a", "submitted_at": "2024-01-03T08:33:09Z", "updated_at": "2024-03-12T23:14:33Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2401.01614v2" }, "publication": { "authors": [ "Boyuan Zheng", "Boyu Gou", "Jihyung Kil", "Huan Sun", "Yu Su" ], "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/zheng24e.html" ], "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 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": "61349-61385", "pdf_url": "https://raw.githubusercontent.com/mlresearch/v235/main/assets/zheng24e/zheng24e.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "GPT-4V(ision) is a Generalist Web Agent, if Grounded", "type": "conference-paper", "url": "https://proceedings.mlr.press/v235/zheng24e.html", "venue": "Proceedings of the 41st International Conference on Machine Learning", "volume": "235" }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-01-03; Recorded arXiv version: v2; Recorded version updated: 2024-03-12T23:14:33Z.", "author": [ { "literal": "Boyuan Zheng" }, { "literal": "Boyu Gou" }, { "literal": "Jihyung Kil" }, { "literal": "Huan Sun" }, { "literal": "Yu Su" } ], "issued": { "date-parts": [ [ 2024, 1, 3 ] ] }, "archive": "arXiv", "archive_location": "2401.01614", "genre": "preprint", "version": "2" }, { "id": "arxiv:2401.13919", "citation-key": "arxiv_2401_13919", "type": "article", "title": "WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models", "URL": "https://arxiv.org/abs/2401.13919v4", "custom": { "catalog_id": "arxiv:2401.13919", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2401.13919", "identifiers": { "arxiv": "2401.13919" }, "first_published_at": "2024-01-25", "record_updated_at": "2024-06-06", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dbc7121c9606c5987df0941b849c216ad8731bebcc74a061cf3f154379d7b8da", "submitted_at": "2024-01-25T03:33:18Z", "updated_at": "2024-06-06T18:37:34Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2401.13919v4" }, "publication": { "authors": [ "Hongliang He", "Wenlin Yao", "Kaixin Ma", "Wenhao Yu", "Yong Dai", "Hongming Zhang", "Zhenzhong Lan", "Dong Yu" ], "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 8 ], "doi": "10.18653/v1/2024.acl-long.371", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.acl-long.371/" ], "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": "6864-6890", "pdf_url": "https://aclanthology.org/2024.acl-long.371.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models", "type": "conference-paper", "url": "https://aclanthology.org/2024.acl-long.371/", "venue": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-01-25; Recorded arXiv version: v4; Recorded version updated: 2024-06-06T18:37:34Z.", "author": [ { "literal": "Hongliang He" }, { "literal": "Wenlin Yao" }, { "literal": "Kaixin Ma" }, { "literal": "Wenhao Yu" }, { "literal": "Yong Dai" }, { "literal": "Hongming Zhang" }, { "literal": "Zhenzhong Lan" }, { "literal": "Dong Yu" } ], "issued": { "date-parts": [ [ 2024, 1, 25 ] ] }, "archive": "arXiv", "archive_location": "2401.13919", "genre": "preprint", "version": "4" }, { "id": "arxiv:2312.13771", "citation-key": "arxiv_2312_13771", "type": "article", "title": "AppAgent: Multimodal Agents as Smartphone Users", "URL": "https://arxiv.org/abs/2312.13771v3", "custom": { "catalog_id": "arxiv:2312.13771", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2312.13771", "identifiers": { "arxiv": "2312.13771" }, "first_published_at": "2023-12-21", "record_updated_at": "2026-07-05", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "61e54d83304755ce89c2ab69f7bb93a7fdc4d68cb5182daad9b5210f809d7ae1", "submitted_at": "2023-12-21T11:52:45Z", "updated_at": "2026-07-05T07:51:04Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2312.13771v3" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2023-12-21; Recorded arXiv version: v3; Recorded version updated: 2026-07-05T07:51:04Z.", "author": [ { "literal": "Chi Zhang" }, { "literal": "Zhao Yang" }, { "literal": "Jiaxuan Liu" }, { "literal": "Yanda Li" }, { "literal": "Yucheng Han" }, { "literal": "Xin Chen" }, { "literal": "Zebiao Huang" }, { "literal": "Bin Fu" }, { "literal": "Gang Yu" } ], "issued": { "date-parts": [ [ 2023, 12, 21 ] ] }, "archive": "arXiv", "archive_location": "2312.13771", "genre": "preprint", "version": "3" }, { "id": "arxiv:2401.16158", "citation-key": "arxiv_2401_16158", "type": "article", "title": "Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception", "URL": "https://arxiv.org/abs/2401.16158v2", "custom": { "catalog_id": "arxiv:2401.16158", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2401.16158", "identifiers": { "arxiv": "2401.16158" }, "first_published_at": "2024-01-29", "record_updated_at": "2024-04-18", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "81ac041a3e5f98bfc23c91f768b32ad7adc3f28d8c9d55a285bb29906c8b5a9c", "submitted_at": "2024-01-29T13:46:37Z", "updated_at": "2024-04-18T06:53:38Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2401.16158v2" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-01-29; Recorded arXiv version: v2; Recorded version updated: 2024-04-18T06:53:38Z.", "author": [ { "literal": "Junyang Wang" }, { "literal": "Haiyang Xu" }, { "literal": "Jiabo Ye" }, { "literal": "Ming Yan" }, { "literal": "Weizhou Shen" }, { "literal": "Ji Zhang" }, { "literal": "Fei Huang" }, { "literal": "Jitao Sang" } ], "issued": { "date-parts": [ [ 2024, 1, 29 ] ] }, "archive": "arXiv", "archive_location": "2401.16158", "genre": "preprint", "version": "2" }, { "id": "arxiv:2401.10935", "citation-key": "arxiv_2401_10935", "type": "article", "title": "SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents", "URL": "https://arxiv.org/abs/2401.10935v2", "custom": { "catalog_id": "arxiv:2401.10935", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2401.10935", "identifiers": { "arxiv": "2401.10935" }, "first_published_at": "2024-01-17", "record_updated_at": "2024-02-23", "catalog_scope": "core", "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" }, "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 }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-01-17; Recorded arXiv version: v2; Recorded version updated: 2024-02-23T04:36:51Z.", "author": [ { "literal": "Kanzhi Cheng" }, { "literal": "Qiushi Sun" }, { "literal": "Yougang Chu" }, { "literal": "Fangzhi Xu" }, { "literal": "Yantao Li" }, { "literal": "Jianbing Zhang" }, { "literal": "Zhiyong Wu" } ], "issued": { "date-parts": [ [ 2024, 1, 17 ] ] }, "archive": "arXiv", "archive_location": "2401.10935", "genre": "preprint", "version": "2" }, { "id": "arxiv:2312.08914", "citation-key": "arxiv_2312_08914", "type": "article", "title": "CogAgent: A Visual Language Model for GUI Agents", "URL": "https://arxiv.org/abs/2312.08914v3", "custom": { "catalog_id": "arxiv:2312.08914", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2312.08914", "identifiers": { "arxiv": "2312.08914" }, "first_published_at": "2023-12-14", "record_updated_at": "2024-12-27", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "755198d83a3af9fe6d032f1446ec9bf57bf7e6f314d37787ce8a6aaa16bddc47", "submitted_at": "2023-12-14T13:20:57Z", "updated_at": "2024-12-27T06:56:18Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2312.08914v3" }, "publication": { "authors": [ "Wenyi Hong", "Weihan Wang", "Qingsong Lv", "Jiazheng Xu", "Wenmeng Yu", "Junhui Ji", "Yan Wang", "Zihan Wang", "Yuxiao Dong", "Ming Ding", "Jie Tang" ], "date_basis": "Year from publisher citation metadata and month from the same page's embedded BibTeX; no day is supplied.", "date_parts": [ 2024, 6 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://openaccess.thecvf.com/content/CVPR2024/html/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.html", "https://openaccess.thecvf.com/content/CVPR2024/papers/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.pdf" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher page directly links this arXiv identifier. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. The publisher PDF, page 1, and landing page list eleven authors; the retained arXiv snapshot lists fourteen. Each edition retains its own authors.", "pages": "14281-14290", "pdf_url": "https://openaccess.thecvf.com/content/CVPR2024/papers/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.pdf", "publisher": null, "series": null, "title": "CogAgent: A Visual Language Model for GUI Agents", "type": "conference-paper", "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.html", "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition", "volume": null }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2023-12-14; Recorded arXiv version: v3; Recorded version updated: 2024-12-27T06:56:18Z.", "author": [ { "literal": "Wenyi Hong" }, { "literal": "Weihan Wang" }, { "literal": "Qingsong Lv" }, { "literal": "Jiazheng Xu" }, { "literal": "Wenmeng Yu" }, { "literal": "Junhui Ji" }, { "literal": "Yan Wang" }, { "literal": "Zihan Wang" }, { "literal": "Yuxuan Zhang" }, { "literal": "Juanzi Li" }, { "literal": "Bin Xu" }, { "literal": "Yuxiao Dong" }, { "literal": "Ming Ding" }, { "literal": "Jie Tang" } ], "issued": { "date-parts": [ [ 2023, 12, 14 ] ] }, "archive": "arXiv", "archive_location": "2312.08914", "genre": "preprint", "version": "3" }, { "id": "arxiv:2412.16256", "citation-key": "arxiv_2412_16256", "type": "article", "title": "Aria-UI: Visual Grounding for GUI Instructions", "URL": "https://arxiv.org/abs/2412.16256v2", "custom": { "catalog_id": "arxiv:2412.16256", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2412.16256", "identifiers": { "arxiv": "2412.16256" }, "first_published_at": "2024-12-20", "record_updated_at": "2025-07-08", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9b49d45aa539c224846a7e14cee9b537d032228e19e86a9cb3cdd9f5004aa429", "submitted_at": "2024-12-20T07:16:57Z", "updated_at": "2025-07-08T08:49:17Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2412.16256v2" }, "publication": { "authors": [ "Yuhao Yang", "Yue Wang", "Dongxu Li", "Ziyang Luo", "Bei Chen", "Chao Huang", "Junnan Li" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.findings-acl.1152", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.1152/" ], "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": "22418-22433", "pdf_url": "https://aclanthology.org/2025.findings-acl.1152.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Aria-UI: Visual Grounding for GUI Instructions", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.1152/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-12-20; Recorded arXiv version: v2; Recorded version updated: 2025-07-08T08:49:17Z.", "author": [ { "literal": "Yuhao Yang" }, { "literal": "Yue Wang" }, { "literal": "Dongxu Li" }, { "literal": "Ziyang Luo" }, { "literal": "Bei Chen" }, { "literal": "Chao Huang" }, { "literal": "Junnan Li" } ], "issued": { "date-parts": [ [ 2024, 12, 20 ] ] }, "archive": "arXiv", "archive_location": "2412.16256", "genre": "preprint", "version": "2" }, { "id": "arxiv:2410.23218", "citation-key": "arxiv_2410_23218", "type": "article", "title": "OS-ATLAS: A Foundation Action Model for Generalist GUI Agents", "URL": "https://arxiv.org/abs/2410.23218v1", "custom": { "catalog_id": "arxiv:2410.23218", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2410.23218", "identifiers": { "arxiv": "2410.23218" }, "first_published_at": "2024-10-30", "record_updated_at": "2024-10-30", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-10-30; Recorded arXiv version: v1; Recorded version updated: 2024-10-30T17:10:19Z.", "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" } ], "issued": { "date-parts": [ [ 2024, 10, 30 ] ] }, "archive": "arXiv", "archive_location": "2410.23218", "genre": "preprint", "version": "1" }, { "id": "arxiv:2411.17465", "citation-key": "arxiv_2411_17465", "type": "article", "title": "ShowUI: One Vision-Language-Action Model for GUI Visual Agent", "URL": "https://arxiv.org/abs/2411.17465v1", "custom": { "catalog_id": "arxiv:2411.17465", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2411.17465", "identifiers": { "arxiv": "2411.17465" }, "first_published_at": "2024-11-26", "record_updated_at": "2024-11-26", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8c8f5c0a7fc5f194ffa6ca914619b9402c947d15f100b124505883ad8ff23ac7", "submitted_at": "2024-11-26T14:29:47Z", "updated_at": "2024-11-26T14:29:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2411.17465v1" }, "publication": { "authors": [ "Kevin Qinghong Lin", "Linjie Li", "Difei Gao", "Zhengyuan Yang", "Shiwei Wu", "Zechen Bai", "Stan Weixian Lei", "Lijuan Wang", "Mike Zheng Shou" ], "date_basis": "Year from publisher citation metadata and month from the same page's embedded BibTeX; no day is supplied.", "date_parts": [ 2025, 6 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://openaccess.thecvf.com/content/CVPR2025/html/Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper.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 publisher page directly links this arXiv identifier.", "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": "19498-19508", "pdf_url": "https://openaccess.thecvf.com/content/CVPR2025/papers/Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper.pdf", "publisher": null, "series": null, "title": "ShowUI: One Vision-Language-Action Model for GUI Visual Agent", "type": "conference-paper", "url": "https://openaccess.thecvf.com/content/CVPR2025/html/Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper.html", "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition", "volume": null }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-11-26; Recorded arXiv version: v1; Recorded version updated: 2024-11-26T14:29:47Z.", "author": [ { "literal": "Kevin Qinghong Lin" }, { "literal": "Linjie Li" }, { "literal": "Difei Gao" }, { "literal": "Zhengyuan Yang" }, { "literal": "Shiwei Wu" }, { "literal": "Zechen Bai" }, { "literal": "Weixian Lei" }, { "literal": "Lijuan Wang" }, { "literal": "Mike Zheng Shou" } ], "issued": { "date-parts": [ [ 2024, 11, 26 ] ] }, "archive": "arXiv", "archive_location": "2411.17465", "genre": "preprint", "version": "1" }, { "id": "arxiv:2402.07939", "citation-key": "arxiv_2402_07939", "type": "article", "title": "UFO: A UI-Focused Agent for Windows OS Interaction", "URL": "https://arxiv.org/abs/2402.07939v5", "custom": { "catalog_id": "arxiv:2402.07939", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2402.07939", "identifiers": { "arxiv": "2402.07939" }, "first_published_at": "2024-02-08", "record_updated_at": "2024-05-23", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "533acb1c9aa3f1c77adb2c67779da86e3d5de95264ba3ec1f81d803f67da7753", "submitted_at": "2024-02-08T15:40:35Z", "updated_at": "2024-05-23T05:18:58Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2402.07939v5" }, "publication": { "authors": [ "Chaoyun Zhang", "Liqun Li", "Shilin He", "Xu Zhang", "Bo Qiao", "Si Qin", "Minghua Ma", "Yu Kang", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang" ], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 4 ], "doi": "10.18653/v1/2025.naacl-long.26", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.naacl-long.26/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "597-622", "pdf_url": "https://aclanthology.org/2025.naacl-long.26.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "UFO: A UI-Focused Agent for Windows OS Interaction", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-long.26/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", "volume": null }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-02-08; Recorded arXiv version: v5; Recorded version updated: 2024-05-23T05:18:58Z.", "author": [ { "literal": "Chaoyun Zhang" }, { "literal": "Liqun Li" }, { "literal": "Shilin He" }, { "literal": "Xu Zhang" }, { "literal": "Bo Qiao" }, { "literal": "Si Qin" }, { "literal": "Minghua Ma" }, { "literal": "Yu Kang" }, { "literal": "Qingwei Lin" }, { "literal": "Saravan Rajmohan" }, { "literal": "Dongmei Zhang" }, { "literal": "Qi Zhang" } ], "issued": { "date-parts": [ [ 2024, 2, 8 ] ] }, "archive": "arXiv", "archive_location": "2402.07939", "genre": "preprint", "version": "5" }, { "id": "arxiv:2410.08164", "citation-key": "arxiv_2410_08164", "type": "article", "title": "Agent S: An Open Agentic Framework that Uses Computers Like a Human", "URL": "https://arxiv.org/abs/2410.08164v1", "custom": { "catalog_id": "arxiv:2410.08164", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2410.08164", "identifiers": { "arxiv": "2410.08164" }, "first_published_at": "2024-10-10", "record_updated_at": "2024-10-10", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "284888d16b049767f76448f23f5d35fda25b109fd67f450105950173ae81c97b", "submitted_at": "2024-10-10T17:43:51Z", "updated_at": "2024-10-10T17:43:51Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2410.08164v1" }, "publication": { "authors": [ "Saaket Agashe", "Jiuzhou Han", "Shuyu Gan", "Jiachen Yang", "Ang Li", "Xin Wang" ], "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/394c7c30ea87b5c3521b4d9e9d419071-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": "22924-22946", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/394c7c30ea87b5c3521b4d9e9d419071-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Agent S: An Open Agentic Framework that Uses Computers Like a Human", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/394c7c30ea87b5c3521b4d9e9d419071-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-10-10; Recorded arXiv version: v1; Recorded version updated: 2024-10-10T17:43:51Z.", "author": [ { "literal": "Saaket Agashe" }, { "literal": "Jiuzhou Han" }, { "literal": "Shuyu Gan" }, { "literal": "Jiachen Yang" }, { "literal": "Ang Li" }, { "literal": "Xin Eric Wang" } ], "issued": { "date-parts": [ [ 2024, 10, 10 ] ] }, "archive": "arXiv", "archive_location": "2410.08164", "genre": "preprint", "version": "1" }, { "id": "arxiv:2412.04454", "citation-key": "arxiv_2412_04454", "type": "article", "title": "Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction", "URL": "https://arxiv.org/abs/2412.04454v2", "custom": { "catalog_id": "arxiv:2412.04454", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2412.04454", "identifiers": { "arxiv": "2412.04454" }, "first_published_at": "2024-12-05", "record_updated_at": "2025-05-05", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-12-05; Recorded arXiv version: v2; Recorded version updated: 2025-05-05T16:17:20Z.", "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" } ], "issued": { "date-parts": [ [ 2024, 12, 5 ] ] }, "archive": "arXiv", "archive_location": "2412.04454", "genre": "preprint", "version": "2" }, { "id": "arxiv:2504.00906", "citation-key": "arxiv_2504_00906", "type": "article", "title": "Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents", "URL": "https://arxiv.org/abs/2504.00906v1", "custom": { "catalog_id": "arxiv:2504.00906", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2504.00906", "identifiers": { "arxiv": "2504.00906" }, "first_published_at": "2025-04-01", "record_updated_at": "2025-04-01", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "11958f69503db514a91af8721870a4cbc1fa19dabf94e3f4ce4118d2fad9862a", "submitted_at": "2025-04-01T15:40:27Z", "updated_at": "2025-04-01T15:40:27Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2504.00906v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-04-01; Recorded arXiv version: v1; Recorded version updated: 2025-04-01T15:40:27Z.", "author": [ { "literal": "Saaket Agashe" }, { "literal": "Kyle Wong" }, { "literal": "Vincent Tu" }, { "literal": "Jiachen Yang" }, { "literal": "Ang Li" }, { "literal": "Xin Eric Wang" } ], "issued": { "date-parts": [ [ 2025, 4, 1 ] ] }, "archive": "arXiv", "archive_location": "2504.00906", "genre": "preprint", "version": "1" }, { "id": "arxiv:2504.14603", "citation-key": "arxiv_2504_14603", "type": "article", "title": "UFO2: The Desktop AgentOS", "URL": "https://arxiv.org/abs/2504.14603v2", "custom": { "catalog_id": "arxiv:2504.14603", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2504.14603", "identifiers": { "arxiv": "2504.14603" }, "first_published_at": "2025-04-20", "record_updated_at": "2025-04-25", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dc47a80b48a6a5f126e36fa14639d56d8c8025a453fbcee2cbdb73eb67945561", "submitted_at": "2025-04-20T13:04:43Z", "updated_at": "2025-04-25T05:14:14Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.14603v2" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-04-20; Recorded arXiv version: v2; Recorded version updated: 2025-04-25T05:14:14Z.", "author": [ { "literal": "Chaoyun Zhang" }, { "literal": "He Huang" }, { "literal": "Chiming Ni" }, { "literal": "Jian Mu" }, { "literal": "Si Qin" }, { "literal": "Shilin He" }, { "literal": "Lu Wang" }, { "literal": "Fangkai Yang" }, { "literal": "Pu Zhao" }, { "literal": "Chao Du" }, { "literal": "Liqun Li" }, { "literal": "Yu Kang" }, { "literal": "Zhao Jiang" }, { "literal": "Suzhen Zheng" }, { "literal": "Rujia Wang" }, { "literal": "Jiaxu Qian" }, { "literal": "Minghua Ma" }, { "literal": "Jian-Guang Lou" }, { "literal": "Qingwei Lin" }, { "literal": "Saravan Rajmohan" }, { "literal": "Dongmei Zhang" } ], "issued": { "date-parts": [ [ 2025, 4, 20 ] ] }, "archive": "arXiv", "archive_location": "2504.14603", "genre": "preprint", "version": "2" }, { "id": "arxiv:2509.02544", "citation-key": "arxiv_2509_02544", "type": "article", "title": "UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning", "URL": "https://arxiv.org/abs/2509.02544v2", "custom": { "catalog_id": "arxiv:2509.02544", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2509.02544", "identifiers": { "arxiv": "2509.02544" }, "first_published_at": "2025-09-02", "record_updated_at": "2025-09-05", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-09-02; Recorded arXiv version: v2; Recorded version updated: 2025-09-05T14:59:27Z.", "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" } ], "issued": { "date-parts": [ [ 2025, 9, 2 ] ] }, "archive": "arXiv", "archive_location": "2509.02544", "genre": "preprint", "version": "2" }, { "id": "arxiv:2609.30186", "citation-key": "arxiv_2609_30186", "type": "article", "title": "Jev-Mobile: Jev as an Executor for Mobile GUI Agents", "URL": "https://arxiv.org/abs/2609.30186v1", "custom": { "catalog_id": "arxiv:2609.30186", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2609.30186", "identifiers": { "arxiv": "2609.30186" }, "first_published_at": "2026-09-24", "record_updated_at": "2026-09-24", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b387c1cfe77f6e06477415944b3923189a1f0ca30be0680f01815cb65b0067bc", "submitted_at": "2026-09-24T17:30:32Z", "updated_at": "2026-09-24T17:30:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.30186v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-09-24; Recorded arXiv version: v1; Recorded version updated: 2026-09-24T17:30:32Z.", "author": [ { "literal": "Linghua Zhang" } ], "issued": { "date-parts": [ [ 2026, 9, 24 ] ] }, "archive": "arXiv", "archive_location": "2609.30186", "genre": "preprint", "version": "1" }, { "id": "arxiv:2409.07429", "citation-key": "arxiv_2409_07429", "type": "article", "title": "Agent Workflow Memory", "URL": "https://arxiv.org/abs/2409.07429v1", "custom": { "catalog_id": "arxiv:2409.07429", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2409.07429", "identifiers": { "arxiv": "2409.07429" }, "first_published_at": "2024-09-11", "record_updated_at": "2024-09-11", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d4c142be3a9c37bbb0d4f401a02de25bd25b4c3968f42ad9a61513abff2b5460", "submitted_at": "2024-09-11T17:21:00Z", "updated_at": "2024-09-11T17:21:00Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2409.07429v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-09-11; Recorded arXiv version: v1; Recorded version updated: 2024-09-11T17:21:00Z.", "author": [ { "literal": "Zora Zhiruo Wang" }, { "literal": "Jiayuan Mao" }, { "literal": "Daniel Fried" }, { "literal": "Graham Neubig" } ], "issued": { "date-parts": [ [ 2024, 9, 11 ] ] }, "archive": "arXiv", "archive_location": "2409.07429", "genre": "preprint", "version": "1" }, { "id": "arxiv:2605.18652", "citation-key": "arxiv_2605_18652", "type": "article", "title": "MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents", "URL": "https://arxiv.org/abs/2605.18652v1", "custom": { "catalog_id": "arxiv:2605.18652", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2605.18652", "identifiers": { "arxiv": "2605.18652" }, "first_published_at": "2026-05-18", "record_updated_at": "2026-05-18", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-05-18; Recorded arXiv version: v1; Recorded version updated: 2026-05-18T16:57:36Z.", "author": [ { "literal": "Ziyun Zeng" }, { "literal": "Hang Hua" }, { "literal": "Bocheng Zou" }, { "literal": "Mu Cai" }, { "literal": "Rogerio Feris" }, { "literal": "Jiebo Luo" } ], "issued": { "date-parts": [ [ 2026, 5, 18 ] ] }, "archive": "arXiv", "archive_location": "2605.18652", "genre": "preprint", "version": "1" }, { "id": "arxiv:2510.06042", "citation-key": "arxiv_2510_06042", "type": "article", "title": "Agent+P: Guiding UI Agents via Symbolic Planning", "URL": "https://arxiv.org/abs/2510.06042v3", "custom": { "catalog_id": "arxiv:2510.06042", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2510.06042", "identifiers": { "arxiv": "2510.06042" }, "first_published_at": "2025-10-07", "record_updated_at": "2026-09-27", "arxiv_snapshot": { "version": 3, "versioned_url": "https://arxiv.org/abs/2510.06042v3", "submitted_at": "2025-10-07T15:36:04Z", "updated_at": "2026-09-27T17:25:57Z", "abstract_sha256": "4bf0a561460c080b14da6fd13f6d92781e01e52b08dc691fe019e70b88e44c86", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-10-07; Recorded arXiv version: v3; Recorded version updated: 2026-09-27T17:25:57Z.", "author": [ { "literal": "Shang Ma" }, { "literal": "Xusheng Xiao" }, { "literal": "Yanfang Ye" } ], "issued": { "date-parts": [ [ 2025, 10, 7 ] ] }, "archive": "arXiv", "archive_location": "2510.06042", "genre": "preprint", "version": "3" }, { "id": "arxiv:2602.20502", "citation-key": "arxiv_2602_20502", "type": "article", "title": "ActionEngine: From Reactive to Programmatic Web Agents via State Machine Memory", "URL": "https://arxiv.org/abs/2602.20502v2", "custom": { "catalog_id": "arxiv:2602.20502", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2602.20502", "identifiers": { "arxiv": "2602.20502" }, "first_published_at": "2026-02-24", "record_updated_at": "2026-09-28", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e179c833d43a88098d576e31e726eb3e4289f728659697364d0b448282df3fc1", "submitted_at": "2026-02-24T03:03:18Z", "updated_at": "2026-09-28T17:40:20Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.20502v2" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-02-24; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T17:40:20Z.", "author": [ { "literal": "Hongbin Zhong" }, { "literal": "Fazle Faisal" }, { "literal": "Luis França" }, { "literal": "Tanakorn Leesatapornwongsa" }, { "literal": "Adriana Szekeres" }, { "literal": "Kexin Rong" }, { "literal": "Suman Nath" } ], "issued": { "date-parts": [ [ 2026, 2, 24 ] ] }, "archive": "arXiv", "archive_location": "2602.20502", "genre": "preprint", "version": "2" }, { "id": "arxiv:2412.09605", "citation-key": "arxiv_2412_09605", "type": "article", "title": "AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials", "URL": "https://arxiv.org/abs/2412.09605v2", "custom": { "catalog_id": "arxiv:2412.09605", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2412.09605", "identifiers": { "arxiv": "2412.09605" }, "first_published_at": "2024-12-12", "record_updated_at": "2025-03-03", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-12-12; Recorded arXiv version: v2; Recorded version updated: 2025-03-03T18:59:36Z.", "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" } ], "issued": { "date-parts": [ [ 2024, 12, 12 ] ] }, "archive": "arXiv", "archive_location": "2412.09605", "genre": "preprint", "version": "2" }, { "id": "arxiv:2508.09123", "citation-key": "arxiv_2508_09123", "type": "article", "title": "OpenCUA: Open Foundations for Computer-Use Agents", "URL": "https://arxiv.org/abs/2508.09123v3", "custom": { "catalog_id": "arxiv:2508.09123", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2508.09123", "identifiers": { "arxiv": "2508.09123" }, "first_published_at": "2025-08-12", "record_updated_at": "2025-10-04", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-08-12; Recorded arXiv version: v3; Recorded version updated: 2025-10-04T17:38:02Z.", "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" } ], "issued": { "date-parts": [ [ 2025, 8, 12 ] ] }, "archive": "arXiv", "archive_location": "2508.09123", "genre": "preprint", "version": "3" }, { "id": "arxiv:2502.11357", "citation-key": "arxiv_2502_11357", "type": "article", "title": "Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents", "URL": "https://arxiv.org/abs/2502.11357v4", "custom": { "catalog_id": "arxiv:2502.11357", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2502.11357", "identifiers": { "arxiv": "2502.11357" }, "first_published_at": "2025-02-17", "record_updated_at": "2025-05-30", "catalog_scope": "core", "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" }, "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 }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-02-17; Recorded arXiv version: v4; Recorded version updated: 2025-05-30T02:30:57Z.", "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" } ], "issued": { "date-parts": [ [ 2025, 2, 17 ] ] }, "archive": "arXiv", "archive_location": "2502.11357", "genre": "preprint", "version": "4" }, { "id": "arxiv:2412.19723", "citation-key": "arxiv_2412_19723", "type": "article", "title": "OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis", "URL": "https://arxiv.org/abs/2412.19723v3", "custom": { "catalog_id": "arxiv:2412.19723", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2412.19723", "identifiers": { "arxiv": "2412.19723" }, "first_published_at": "2024-12-27", "record_updated_at": "2025-06-27", "catalog_scope": "core", "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" }, "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 }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-12-27; Recorded arXiv version: v3; Recorded version updated: 2025-06-27T08:25:48Z.", "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" } ], "issued": { "date-parts": [ [ 2024, 12, 27 ] ] }, "archive": "arXiv", "archive_location": "2412.19723", "genre": "preprint", "version": "3" }, { "id": "arxiv:2504.10458", "citation-key": "arxiv_2504_10458", "type": "article", "title": "GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents", "URL": "https://arxiv.org/abs/2504.10458v4", "custom": { "catalog_id": "arxiv:2504.10458", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2504.10458", "identifiers": { "arxiv": "2504.10458" }, "first_published_at": "2025-04-14", "record_updated_at": "2025-10-01", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b875617b795e0f8d7d6348e22ec85ccc9ab4dd931e66850182348927b1e5209f", "submitted_at": "2025-04-14T17:45:54Z", "updated_at": "2025-10-01T04:55:20Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2504.10458v4" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-04-14; Recorded arXiv version: v4; Recorded version updated: 2025-10-01T04:55:20Z.", "author": [ { "literal": "Run Luo" }, { "literal": "Lu Wang" }, { "literal": "Wanwei He" }, { "literal": "Longze Chen" }, { "literal": "Jiaming Li" }, { "literal": "Xiaobo Xia" } ], "issued": { "date-parts": [ [ 2025, 4, 14 ] ] }, "archive": "arXiv", "archive_location": "2504.10458", "genre": "preprint", "version": "4" }, { "id": "arxiv:2506.07976", "citation-key": "arxiv_2506_07976", "type": "article", "title": "Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction", "URL": "https://arxiv.org/abs/2506.07976v2", "custom": { "catalog_id": "arxiv:2506.07976", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2506.07976", "identifiers": { "arxiv": "2506.07976" }, "first_published_at": "2025-06-09", "record_updated_at": "2025-06-10", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e4b6c8b297e88dae689ba2a48724a441698cd5309a3bbe1198f38343e88aceb1", "submitted_at": "2025-06-09T17:50:02Z", "updated_at": "2025-06-10T12:50:18Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2506.07976v2" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-06-09; Recorded arXiv version: v2; Recorded version updated: 2025-06-10T12:50:18Z.", "author": [ { "literal": "Junhong Shen" }, { "literal": "Hao Bai" }, { "literal": "Lunjun Zhang" }, { "literal": "Yifei Zhou" }, { "literal": "Amrith Setlur" }, { "literal": "Shengbang Tong" }, { "literal": "Diego Caples" }, { "literal": "Nan Jiang" }, { "literal": "Tong Zhang" }, { "literal": "Ameet Talwalkar" }, { "literal": "Aviral Kumar" } ], "issued": { "date-parts": [ [ 2025, 6, 9 ] ] }, "archive": "arXiv", "archive_location": "2506.07976", "genre": "preprint", "version": "2" }, { "id": "arxiv:2411.02337", "citation-key": "arxiv_2411_02337", "type": "article", "title": "WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning", "URL": "https://arxiv.org/abs/2411.02337v3", "custom": { "catalog_id": "arxiv:2411.02337", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2411.02337", "identifiers": { "arxiv": "2411.02337" }, "first_published_at": "2024-11-04", "record_updated_at": "2025-01-27", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "db039a2592cd79a1f8f7f1c985c2ddf42447c63d1f58d2815ba1d6ef2369da47", "submitted_at": "2024-11-04T17:59:58Z", "updated_at": "2025-01-27T11:56:15Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2411.02337v3" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-11-04; Recorded arXiv version: v3; Recorded version updated: 2025-01-27T11:56:15Z.", "author": [ { "literal": "Zehan Qi" }, { "literal": "Xiao Liu" }, { "literal": "Iat Long Iong" }, { "literal": "Hanyu Lai" }, { "literal": "Xueqiao Sun" }, { "literal": "Wenyi Zhao" }, { "literal": "Yu Yang" }, { "literal": "Xinyue Yang" }, { "literal": "Jiadai Sun" }, { "literal": "Shuntian Yao" }, { "literal": "Tianjie Zhang" }, { "literal": "Wei Xu" }, { "literal": "Jie Tang" }, { "literal": "Yuxiao Dong" } ], "issued": { "date-parts": [ [ 2024, 11, 4 ] ] }, "archive": "arXiv", "archive_location": "2411.02337", "genre": "preprint", "version": "3" }, { "id": "arxiv:2606.05597", "citation-key": "arxiv_2606_05597", "type": "article", "title": "AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents", "URL": "https://arxiv.org/abs/2606.05597v3", "custom": { "catalog_id": "arxiv:2606.05597", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2606.05597", "identifiers": { "arxiv": "2606.05597" }, "first_published_at": "2026-06-04", "record_updated_at": "2026-08-07", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8a8afe44ffa73739505070c5f8004d8b4bbe98455fc0f5f3cef4b450bf441c74", "submitted_at": "2026-06-04T02:18:44Z", "updated_at": "2026-08-07T17:58:32Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2606.05597v3" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-06-04; Recorded arXiv version: v3; Recorded version updated: 2026-08-07T17:58:32Z.", "author": [ { "literal": "Hao Bai" }, { "literal": "Rui Yang" }, { "literal": "Chenlu Ye" }, { "literal": "Spencer Whitehead" }, { "literal": "Aviral Kumar" }, { "literal": "Tong Zhang" } ], "issued": { "date-parts": [ [ 2026, 6, 4 ] ] }, "archive": "arXiv", "archive_location": "2606.05597", "genre": "preprint", "version": "3" }, { "id": "arxiv:2607.28227", "citation-key": "arxiv_2607_28227", "type": "article", "title": "Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents", "URL": "https://arxiv.org/abs/2607.28227v1", "custom": { "catalog_id": "arxiv:2607.28227", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2607.28227", "identifiers": { "arxiv": "2607.28227" }, "first_published_at": "2026-07-30", "record_updated_at": "2026-07-30", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "52fb1b49501132f1dbe3564daa02cca22a93fc8d7c28dec8ee6070a23889574a", "submitted_at": "2026-07-30T13:58:41Z", "updated_at": "2026-07-30T13:58:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.28227v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T13:58:41Z.", "author": [ { "literal": "Hanzhang Zhou" }, { "literal": "Panrong Tong" }, { "literal": "Xu Zhang" }, { "literal": "Quyu Kong" }, { "literal": "Chenglin Cai" }, { "literal": "Tianyu Xia" }, { "literal": "Gongjie Zhang" }, { "literal": "Jianan Zhang" }, { "literal": "Long Li" }, { "literal": "Long Chen" }, { "literal": "Lei Wang" }, { "literal": "Gaole Dai" }, { "literal": "Pengxiang Li" }, { "literal": "Liangyu Chen" }, { "literal": "Yue Wang" }, { "literal": "Steven Hoi" } ], "issued": { "date-parts": [ [ 2026, 7, 30 ] ] }, "archive": "arXiv", "archive_location": "2607.28227", "genre": "preprint", "version": "1" }, { "id": "arxiv:2605.17320", "citation-key": "arxiv_2605_17320", "type": "article", "title": "TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents", "URL": "https://arxiv.org/abs/2605.17320v1", "custom": { "catalog_id": "arxiv:2605.17320", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2605.17320", "identifiers": { "arxiv": "2605.17320" }, "first_published_at": "2026-05-17", "record_updated_at": "2026-05-17", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "51576fb9bde23f769d3200a0d593ad610eb27248917132aff1bcf6eb7ff03cea", "submitted_at": "2026-05-17T08:24:01Z", "updated_at": "2026-05-17T08:24:01Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.17320v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-05-17; Recorded arXiv version: v1; Recorded version updated: 2026-05-17T08:24:01Z.", "author": [ { "literal": "Yutong Huang" }, { "literal": "Vikranth Srivatsa" }, { "literal": "Alex Asch" }, { "literal": "Hansin Tushar Patwa" }, { "literal": "Yiying Zhang" } ], "issued": { "date-parts": [ [ 2026, 5, 17 ] ] }, "archive": "arXiv", "archive_location": "2605.17320", "genre": "preprint", "version": "1" }, { "id": "arxiv:2606.20622", "citation-key": "arxiv_2606_20622", "type": "article", "title": "Darwin Mobile Agent: A Roadmap for Self-Evolution", "URL": "https://arxiv.org/abs/2606.20622v1", "custom": { "catalog_id": "arxiv:2606.20622", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2606.20622", "identifiers": { "arxiv": "2606.20622" }, "first_published_at": "2026-05-26", "record_updated_at": "2026-05-26", "arxiv_snapshot": { "version": 1, "versioned_url": "https://arxiv.org/abs/2606.20622v1", "submitted_at": "2026-05-26T13:32:14Z", "updated_at": "2026-05-26T13:32:14Z", "abstract_sha256": "9e761b20caa6882605ecfd6cd001aeda4a2d36b2e702eea9a6d70451fc0ea9eb", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-05-26; Recorded arXiv version: v1; Recorded version updated: 2026-05-26T13:32:14Z.", "author": [ { "literal": "Daniel Beechey" }, { "literal": "Derek Yuen" }, { "literal": "Jianheng Liu" }, { "literal": "Dezhao Luo" }, { "literal": "Tiantian He" }, { "literal": "Weilin Luo" }, { "literal": "Jun Wang" }, { "literal": "Kun Shao" } ], "issued": { "date-parts": [ [ 2026, 5, 26 ] ] }, "archive": "arXiv", "archive_location": "2606.20622", "genre": "preprint", "version": "1" }, { "id": "arxiv:2601.19306", "citation-key": "arxiv_2601_19306", "type": "article", "title": "Curiosity Driven Knowledge Retrieval for Mobile Agents", "URL": "https://arxiv.org/abs/2601.19306v1", "custom": { "catalog_id": "arxiv:2601.19306", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2601.19306", "identifiers": { "arxiv": "2601.19306" }, "first_published_at": "2026-01-27", "record_updated_at": "2026-01-27", "arxiv_snapshot": { "version": 1, "versioned_url": "https://arxiv.org/abs/2601.19306v1", "submitted_at": "2026-01-27T07:46:05Z", "updated_at": "2026-01-27T07:46:05Z", "abstract_sha256": "223b9a915e5ea9849644318e1e5426e64ad8655ab46d0b007c30e1967130dc50", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-01-27; Recorded arXiv version: v1; Recorded version updated: 2026-01-27T07:46:05Z.", "author": [ { "literal": "Sijia Li" }, { "literal": "Xiaoyu Tan" }, { "literal": "Shahir Ali" }, { "literal": "Niels Schmidt" }, { "literal": "Gengchen Ma" }, { "literal": "Xihe Qiu" } ], "issued": { "date-parts": [ [ 2026, 1, 27 ] ] }, "archive": "arXiv", "archive_location": "2601.19306", "genre": "preprint", "version": "1" }, { "id": "arxiv:2605.05765", "citation-key": "arxiv_2605_05765", "type": "article", "title": "X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction", "URL": "https://arxiv.org/abs/2605.05765v2", "custom": { "catalog_id": "arxiv:2605.05765", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2605.05765", "identifiers": { "arxiv": "2605.05765" }, "first_published_at": "2026-05-07", "record_updated_at": "2026-05-21", "arxiv_snapshot": { "version": 2, "versioned_url": "https://arxiv.org/abs/2605.05765v2", "submitted_at": "2026-05-07T06:58:34Z", "updated_at": "2026-05-21T06:55:40Z", "abstract_sha256": "2ece93c00c5556dfe50ddd0ba3f52b725f34d1bee18ea3565951bb78343d8ed0", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-05-07; Recorded arXiv version: v2; Recorded version updated: 2026-05-21T06:55:40Z.", "author": [ { "literal": "Xiaoming Ren" }, { "literal": "Ru Zhen" }, { "literal": "Chao Li" }, { "literal": "Yang Song" }, { "literal": "Qiuxia Hou" }, { "literal": "Yanhao Zhang" }, { "literal": "Peng Liu" }, { "literal": "Qi Qi" }, { "literal": "Quanlong Zheng" }, { "literal": "Qi Wu" }, { "literal": "Zhenyi Liao" }, { "literal": "Binqiang Pan" }, { "literal": "Haobo Ji" }, { "literal": "Haonan Lu" } ], "issued": { "date-parts": [ [ 2026, 5, 7 ] ] }, "archive": "arXiv", "archive_location": "2605.05765", "genre": "preprint", "version": "2" }, { "id": "arxiv:2508.18040", "citation-key": "arxiv_2508_18040", "type": "article", "title": "PerPilot: Personalizing VLM-based Mobile Agents via Memory and Exploration", "URL": "https://arxiv.org/abs/2508.18040v1", "custom": { "catalog_id": "arxiv:2508.18040", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2508.18040", "identifiers": { "arxiv": "2508.18040" }, "first_published_at": "2025-08-25", "record_updated_at": "2025-08-25", "arxiv_snapshot": { "version": 1, "versioned_url": "https://arxiv.org/abs/2508.18040v1", "submitted_at": "2025-08-25T13:57:02Z", "updated_at": "2025-08-25T13:57:02Z", "abstract_sha256": "57d5fc98a2eb2232f237d71b34060df0acef89cfeaa4bc247580a4dda3223e0b", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-08-25; Recorded arXiv version: v1; Recorded version updated: 2025-08-25T13:57:02Z.", "author": [ { "literal": "Xin Wang" }, { "literal": "Zhiyao Cui" }, { "literal": "Hao Li" }, { "literal": "Ya Zeng" }, { "literal": "Chenxu Wang" }, { "literal": "Ruiqi Song" }, { "literal": "Yihang Chen" }, { "literal": "Kun Shao" }, { "literal": "Qiaosheng Zhang" }, { "literal": "Jinzhuo Liu" }, { "literal": "Siyue Ren" }, { "literal": "Shuyue Hu" }, { "literal": "Zhen Wang" } ], "issued": { "date-parts": [ [ 2025, 8, 25 ] ] }, "archive": "arXiv", "archive_location": "2508.18040", "genre": "preprint", "version": "1" }, { "id": "arxiv:2509.02444", "citation-key": "arxiv_2509_02444", "type": "article", "title": "AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent", "URL": "https://arxiv.org/abs/2509.02444v2", "custom": { "catalog_id": "arxiv:2509.02444", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2509.02444", "identifiers": { "arxiv": "2509.02444" }, "first_published_at": "2025-09-02", "record_updated_at": "2025-10-17", "arxiv_snapshot": { "version": 2, "versioned_url": "https://arxiv.org/abs/2509.02444v2", "submitted_at": "2025-09-02T15:48:21Z", "updated_at": "2025-10-17T00:57:58Z", "abstract_sha256": "49a887b12b3395821aa100a66e61aac808309ef947ae752475df3d2db9a4fcd8", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-09-02; Recorded arXiv version: v2; Recorded version updated: 2025-10-17T00:57:58Z.", "author": [ { "literal": "Jingru Fan" }, { "literal": "Yufan Dang" }, { "literal": "Jingyao Wu" }, { "literal": "Huatao Li" }, { "literal": "Runde Yang" }, { "literal": "Xiyuan Yang" }, { "literal": "Yuheng Wang" }, { "literal": "Chen Qian" } ], "issued": { "date-parts": [ [ 2025, 9, 2 ] ] }, "archive": "arXiv", "archive_location": "2509.02444", "genre": "preprint", "version": "2" }, { "id": "arxiv:2412.05467", "citation-key": "arxiv_2412_05467", "type": "article", "title": "The BrowserGym Ecosystem for Web Agent Research", "URL": "https://arxiv.org/abs/2412.05467v4", "custom": { "catalog_id": "arxiv:2412.05467", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2412.05467", "identifiers": { "arxiv": "2412.05467" }, "first_published_at": "2024-12-06", "record_updated_at": "2025-02-28", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "572a993cd37a83bf7100dca71f0a44473ed6547f521409abf0f4ee22733a28cc", "submitted_at": "2024-12-06T23:43:59Z", "updated_at": "2025-02-28T16:02:27Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2412.05467v4" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-12-06; Recorded arXiv version: v4; Recorded version updated: 2025-02-28T16:02:27Z.", "author": [ { "literal": "Thibault Le Sellier De Chezelles" }, { "literal": "Maxime Gasse" }, { "literal": "Alexandre Drouin" }, { "literal": "Massimo Caccia" }, { "literal": "Léo Boisvert" }, { "literal": "Megh Thakkar" }, { "literal": "Tom Marty" }, { "literal": "Rim Assouel" }, { "literal": "Sahar Omidi Shayegan" }, { "literal": "Lawrence Keunho Jang" }, { "literal": "Xing Han Lù" }, { "literal": "Ori Yoran" }, { "literal": "Dehan Kong" }, { "literal": "Frank F. Xu" }, { "literal": "Siva Reddy" }, { "literal": "Quentin Cappart" }, { "literal": "Graham Neubig" }, { "literal": "Ruslan Salakhutdinov" }, { "literal": "Nicolas Chapados" }, { "literal": "Alexandre Lacoste" } ], "issued": { "date-parts": [ [ 2024, 12, 6 ] ] }, "archive": "arXiv", "archive_location": "2412.05467", "genre": "preprint", "version": "4" }, { "id": "arxiv:2401.13649", "citation-key": "arxiv_2401_13649", "type": "article", "title": "VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks", "URL": "https://arxiv.org/abs/2401.13649v2", "custom": { "catalog_id": "arxiv:2401.13649", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2401.13649", "identifiers": { "arxiv": "2401.13649" }, "first_published_at": "2024-01-24", "record_updated_at": "2024-06-06", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3a705b87b43464120ebb01b28b0f6a9e31fad68f3d463c88354f2005dab940c3", "submitted_at": "2024-01-24T18:35:21Z", "updated_at": "2024-06-06T02:01:09Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2401.13649v2" }, "publication": { "authors": [ "Jing Yu Koh", "Robert Lo", "Lawrence Jang", "Vikram Duvvur", "Ming Chong Lim", "Po-Yu Huang", "Graham Neubig", "Shuyan Zhou", "Ruslan Salakhutdinov", "Daniel Fried" ], "date_basis": "Explicit publisher metadata: 2024/8; precision=month.", "date_parts": [ 2024, 8 ], "doi": "10.18653/v1/2024.acl-long.50", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.acl-long.50/", "https://aclanthology.org/2024.acl-long.50.pdf" ], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The formal PDF title adds Visually Grounded; the landing metadata uses Visual Web Tasks. PDF authors include Ming Chong Lim and Ruslan Salakhutdinov; the landing abbreviates them to Ming Lim and Russ Salakhutdinov. Publication title/authors use the PDF; the retained arXiv title remains unchanged. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "881-905", "pdf_url": "https://aclanthology.org/2024.acl-long.50.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "VisualWebArena: Evaluating Multimodal Agents on Realistic Visually Grounded Web Tasks", "type": "conference-paper", "url": "https://aclanthology.org/2024.acl-long.50/", "venue": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-01-24; Recorded arXiv version: v2; Recorded version updated: 2024-06-06T02:01:09Z.", "author": [ { "literal": "Jing Yu Koh" }, { "literal": "Robert Lo" }, { "literal": "Lawrence Jang" }, { "literal": "Vikram Duvvur" }, { "literal": "Ming Chong Lim" }, { "literal": "Po-Yu Huang" }, { "literal": "Graham Neubig" }, { "literal": "Shuyan Zhou" }, { "literal": "Ruslan Salakhutdinov" }, { "literal": "Daniel Fried" } ], "issued": { "date-parts": [ [ 2024, 1, 24 ] ] }, "archive": "arXiv", "archive_location": "2401.13649", "genre": "preprint", "version": "2" }, { "id": "arxiv:2403.07718", "citation-key": "arxiv_2403_07718", "type": "article", "title": "WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?", "URL": "https://arxiv.org/abs/2403.07718v5", "custom": { "catalog_id": "arxiv:2403.07718", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2403.07718", "identifiers": { "arxiv": "2403.07718" }, "first_published_at": "2024-03-12", "record_updated_at": "2024-07-23", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8033f9c26a5f95a49000374a6edebb4dead83e100ebcf5226007f06b7573c305", "submitted_at": "2024-03-12T14:58:45Z", "updated_at": "2024-07-23T06:19:28Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2403.07718v5" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-03-12; Recorded arXiv version: v5; Recorded version updated: 2024-07-23T06:19:28Z.", "author": [ { "literal": "Alexandre Drouin" }, { "literal": "Maxime Gasse" }, { "literal": "Massimo Caccia" }, { "literal": "Issam H. Laradji" }, { "literal": "Manuel Del Verme" }, { "literal": "Tom Marty" }, { "literal": "Léo Boisvert" }, { "literal": "Megh Thakkar" }, { "literal": "Quentin Cappart" }, { "literal": "David Vazquez" }, { "literal": "Nicolas Chapados" }, { "literal": "Alexandre Lacoste" } ], "issued": { "date-parts": [ [ 2024, 3, 12 ] ] }, "archive": "arXiv", "archive_location": "2403.07718", "genre": "preprint", "version": "5" }, { "id": "arxiv:2409.08264", "citation-key": "arxiv_2409_08264", "type": "article", "title": "Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale", "URL": "https://arxiv.org/abs/2409.08264v2", "custom": { "catalog_id": "arxiv:2409.08264", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2409.08264", "identifiers": { "arxiv": "2409.08264" }, "first_published_at": "2024-09-12", "record_updated_at": "2024-09-13", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fe77f7f8ffd7490192ab54b7f6d49c0cb5b10be6df0a645bfb181b3be724118a", "submitted_at": "2024-09-12T17:56:43Z", "updated_at": "2024-09-13T20:17:13Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.08264v2" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-09-12; Recorded arXiv version: v2; Recorded version updated: 2024-09-13T20:17:13Z.", "author": [ { "literal": "Rogerio Bonatti" }, { "literal": "Dan Zhao" }, { "literal": "Francesco Bonacci" }, { "literal": "Dillon Dupont" }, { "literal": "Sara Abdali" }, { "literal": "Yinheng Li" }, { "literal": "Yadong Lu" }, { "literal": "Justin Wagle" }, { "literal": "Kazuhito Koishida" }, { "literal": "Arthur Bucker" }, { "literal": "Lawrence Jang" }, { "literal": "Zack Hui" } ], "issued": { "date-parts": [ [ 2024, 9, 12 ] ] }, "archive": "arXiv", "archive_location": "2409.08264", "genre": "preprint", "version": "2" }, { "id": "arxiv:2407.05291", "citation-key": "arxiv_2407_05291", "type": "article", "title": "WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks", "URL": "https://arxiv.org/abs/2407.05291v2", "custom": { "catalog_id": "arxiv:2407.05291", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2407.05291", "identifiers": { "arxiv": "2407.05291" }, "first_published_at": "2024-07-07", "record_updated_at": "2025-02-05", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2b56a6208e4fa3523cae3fbae673affcd5fe3d6a9c19df482d27fe71d43ffef5", "submitted_at": "2024-07-07T07:15:49Z", "updated_at": "2025-02-05T21:50:07Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2407.05291v2" }, "publication": { "authors": [ "Léo Boisvert", "Megh Thakkar", "Maxime Gasse", "Massimo Caccia", "Thibault L. De Chezelles", "Quentin Cappart", "Nicolas Chapados", "Alexandre Lacoste", "Alexandre Drouin" ], "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": "10.52202/079017-0195", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/0b82662b6c32e887bb252a74d8cb2d5e-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. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "5996-6051", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/0b82662b6c32e887bb252a74d8cb2d5e-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/0b82662b6c32e887bb252a74d8cb2d5e-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-07-07; Recorded arXiv version: v2; Recorded version updated: 2025-02-05T21:50:07Z.", "author": [ { "literal": "Léo Boisvert" }, { "literal": "Megh Thakkar" }, { "literal": "Maxime Gasse" }, { "literal": "Massimo Caccia" }, { "literal": "Thibault Le Sellier De Chezelles" }, { "literal": "Quentin Cappart" }, { "literal": "Nicolas Chapados" }, { "literal": "Alexandre Lacoste" }, { "literal": "Alexandre Drouin" } ], "issued": { "date-parts": [ [ 2024, 7, 7 ] ] }, "archive": "arXiv", "archive_location": "2407.05291", "genre": "preprint", "version": "2" }, { "id": "arxiv:2407.15711", "citation-key": "arxiv_2407_15711", "type": "article", "title": "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?", "URL": "https://arxiv.org/abs/2407.15711v2", "custom": { "catalog_id": "arxiv:2407.15711", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2407.15711", "identifiers": { "arxiv": "2407.15711" }, "first_published_at": "2024-07-22", "record_updated_at": "2024-10-21", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2f028fb7f4d64fd4c29886d49b5d6f0fabddba309b669e019edf13586deb9c90", "submitted_at": "2024-07-22T15:18:45Z", "updated_at": "2024-10-21T15:45:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2407.15711v2" }, "publication": { "authors": [ "Ori Yoran", "Samuel Joseph Amouyal", "Chaitanya Malaviya", "Ben Bogin", "Ofir Press", "Jonathan Berant" ], "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.emnlp-main.505", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.emnlp-main.505/" ], "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": "8938-8968", "pdf_url": "https://aclanthology.org/2024.emnlp-main.505.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?", "type": "conference-paper", "url": "https://aclanthology.org/2024.emnlp-main.505/", "venue": "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", "volume": null }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-07-22; Recorded arXiv version: v2; Recorded version updated: 2024-10-21T15:45:31Z.", "author": [ { "literal": "Ori Yoran" }, { "literal": "Samuel Joseph Amouyal" }, { "literal": "Chaitanya Malaviya" }, { "literal": "Ben Bogin" }, { "literal": "Ofir Press" }, { "literal": "Jonathan Berant" } ], "issued": { "date-parts": [ [ 2024, 7, 22 ] ] }, "archive": "arXiv", "archive_location": "2407.15711", "genre": "preprint", "version": "2" }, { "id": "arxiv:2609.24890", "citation-key": "arxiv_2609_24890", "type": "article", "title": "OSWorld-Pro: Process-based Evaluation for Computer Use Agents", "URL": "https://arxiv.org/abs/2609.24890v1", "custom": { "catalog_id": "arxiv:2609.24890", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2609.24890", "identifiers": { "arxiv": "2609.24890" }, "first_published_at": "2026-09-21", "record_updated_at": "2026-09-21", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0d3cb920a677108910530788eb68c263127dba9510274f182910aed9c2f848c9", "submitted_at": "2026-09-21T16:55:24Z", "updated_at": "2026-09-21T16:55:24Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.24890v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-09-21; Recorded arXiv version: v1; Recorded version updated: 2026-09-21T16:55:24Z.", "author": [ { "literal": "Zhilin Wang" }, { "literal": "Shaokun Zhang" }, { "literal": "Yifan Zhang" }, { "literal": "Hao Zhang" }, { "literal": "Jin Xu" }, { "literal": "Binfeng Xu" }, { "literal": "Jian Hu" }, { "literal": "Yunheng Zou" }, { "literal": "Karan Sapra" }, { "literal": "Andrew Tao" }, { "literal": "Jan Kautz" }, { "literal": "Yi Dong" } ], "issued": { "date-parts": [ [ 2026, 9, 21 ] ] }, "archive": "arXiv", "archive_location": "2609.24890", "genre": "preprint", "version": "1" }, { "id": "arxiv:2406.03679", "citation-key": "arxiv_2406_03679", "type": "article", "title": "On the Effects of Data Scale on UI Control Agents", "URL": "https://arxiv.org/abs/2406.03679v6", "custom": { "catalog_id": "arxiv:2406.03679", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2406.03679", "identifiers": { "arxiv": "2406.03679" }, "first_published_at": "2024-06-06", "record_updated_at": "2024-11-13", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6eb3209d8e2a431987fe19f01cd0818f9fb490e684d7369e7d3002dc388ff271", "submitted_at": "2024-06-06T01:49:29Z", "updated_at": "2024-11-13T16:42:22Z", "version": 6, "versioned_url": "https://arxiv.org/abs/2406.03679v6" }, "publication": { "authors": [ "Wei Li", "William Bishop", "Alice Li", "Chris Rawles", "Folawiyo Campbell-Ajala", "Divya Tyamagundlu", "Oriana Riva" ], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 12, 16 ], "doi": "10.52202/079017-2925", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "92130-92154", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/a79f3ef3b445fd4659f44648f7ea8ffd-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "On the Effects of Data Scale on UI Control Agents", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-06-06; Recorded arXiv version: v6; Recorded version updated: 2024-11-13T16:42:22Z.", "author": [ { "literal": "Wei Li" }, { "literal": "William Bishop" }, { "literal": "Alice Li" }, { "literal": "Chris Rawles" }, { "literal": "Folawiyo Campbell-Ajala" }, { "literal": "Divya Tyamagundlu" }, { "literal": "Oriana Riva" } ], "issued": { "date-parts": [ [ 2024, 6, 6 ] ] }, "archive": "arXiv", "archive_location": "2406.03679", "genre": "preprint", "version": "6" }, { "id": "arxiv:2406.08451", "citation-key": "arxiv_2406_08451", "type": "article", "title": "GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices", "URL": "https://arxiv.org/abs/2406.08451v2", "custom": { "catalog_id": "arxiv:2406.08451", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2406.08451", "identifiers": { "arxiv": "2406.08451" }, "first_published_at": "2024-06-12", "record_updated_at": "2025-08-01", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-06-12; Recorded arXiv version: v2; Recorded version updated: 2025-08-01T03:37:57Z.", "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" } ], "issued": { "date-parts": [ [ 2024, 6, 12 ] ] }, "archive": "arXiv", "archive_location": "2406.08451", "genre": "preprint", "version": "2" }, { "id": "arxiv:2504.07981", "citation-key": "arxiv_2504_07981", "type": "article", "title": "ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use", "URL": "https://arxiv.org/abs/2504.07981v1", "custom": { "catalog_id": "arxiv:2504.07981", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2504.07981", "identifiers": { "arxiv": "2504.07981" }, "first_published_at": "2025-04-04", "record_updated_at": "2025-04-04", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "679bfcac736544e9a241c579adfda0cacbc40838452ea56ad631f8086868415a", "submitted_at": "2025-04-04T14:25:17Z", "updated_at": "2025-04-04T14:25:17Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2504.07981v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-04-04; Recorded arXiv version: v1; Recorded version updated: 2025-04-04T14:25:17Z.", "author": [ { "literal": "Kaixin Li" }, { "literal": "Ziyang Meng" }, { "literal": "Hongzhan Lin" }, { "literal": "Ziyang Luo" }, { "literal": "Yuchen Tian" }, { "literal": "Jing Ma" }, { "literal": "Zhiyong Huang" }, { "literal": "Tat-Seng Chua" } ], "issued": { "date-parts": [ [ 2025, 4, 4 ] ] }, "archive": "arXiv", "archive_location": "2504.07981", "genre": "preprint", "version": "1" }, { "id": "arxiv:2506.14866", "citation-key": "arxiv_2506_14866", "type": "article", "title": "OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents", "URL": "https://arxiv.org/abs/2506.14866v2", "custom": { "catalog_id": "arxiv:2506.14866", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2506.14866", "identifiers": { "arxiv": "2506.14866" }, "first_published_at": "2025-06-17", "record_updated_at": "2025-10-29", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f551b861012fc4eddbf010a619bc65e77b524b05958761b738a88bcae377e9a9", "submitted_at": "2025-06-17T17:59:31Z", "updated_at": "2025-10-29T10:34:04Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2506.14866v2" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-06-17; Recorded arXiv version: v2; Recorded version updated: 2025-10-29T10:34:04Z.", "author": [ { "literal": "Thomas Kuntz" }, { "literal": "Agatha Duzan" }, { "literal": "Hao Zhao" }, { "literal": "Francesco Croce" }, { "literal": "Zico Kolter" }, { "literal": "Nicolas Flammarion" }, { "literal": "Maksym Andriushchenko" } ], "issued": { "date-parts": [ [ 2025, 6, 17 ] ] }, "archive": "arXiv", "archive_location": "2506.14866", "genre": "preprint", "version": "2" }, { "id": "arxiv:2608.07775", "citation-key": "arxiv_2608_07775", "type": "article", "title": "AndroidReality: How Far Are Mobile Agents from the Real World?", "URL": "https://arxiv.org/abs/2608.07775v1", "custom": { "catalog_id": "arxiv:2608.07775", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2608.07775", "identifiers": { "arxiv": "2608.07775" }, "first_published_at": "2026-08-07", "record_updated_at": "2026-08-07", "arxiv_snapshot": { "version": 1, "versioned_url": "https://arxiv.org/abs/2608.07775v1", "submitted_at": "2026-08-07T21:47:43Z", "updated_at": "2026-08-07T21:47:43Z", "abstract_sha256": "4d99685a75d2023db5c9ad943e103ec779eebd037fe7a113848d8a31e08fd68b", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-08-07; Recorded arXiv version: v1; Recorded version updated: 2026-08-07T21:47:43Z.", "author": [ { "literal": "Xiaoou Liu" }, { "literal": "Longchao Da" }, { "literal": "Hanyang Chen" }, { "literal": "Yuan Ling" }, { "literal": "Hua Wei" } ], "issued": { "date-parts": [ [ 2026, 8, 7 ] ] }, "archive": "arXiv", "archive_location": "2608.07775", "genre": "preprint", "version": "1" }, { "id": "arxiv:2610.06898", "citation-key": "arxiv_2610_06898", "type": "article", "title": "DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections", "URL": "https://arxiv.org/abs/2610.06898v1", "custom": { "catalog_id": "arxiv:2610.06898", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2610.06898", "identifiers": { "arxiv": "2610.06898" }, "first_published_at": "2026-09-29", "record_updated_at": "2026-09-29", "arxiv_snapshot": { "version": 1, "versioned_url": "https://arxiv.org/abs/2610.06898v1", "submitted_at": "2026-09-29T03:03:00Z", "updated_at": "2026-09-29T03:03:00Z", "abstract_sha256": "5afea9414462386ee921b9ead9381c0204963c710c9f616a96f4bc47079f059e", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T03:03:00Z.", "author": [ { "literal": "Li Hu" }, { "literal": "Kanghua Mo" }, { "literal": "Yingbin Jin" }, { "literal": "Qingqing Ye" }, { "literal": "Haibo Hu" } ], "issued": { "date-parts": [ [ 2026, 9, 29 ] ] }, "archive": "arXiv", "archive_location": "2610.06898", "genre": "preprint", "version": "1" }, { "id": "arxiv:2506.16042", "citation-key": "arxiv_2506_16042", "type": "article", "title": "OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents", "URL": "https://arxiv.org/abs/2506.16042v2", "custom": { "catalog_id": "arxiv:2506.16042", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2506.16042", "identifiers": { "arxiv": "2506.16042" }, "first_published_at": "2025-06-19", "record_updated_at": "2026-05-18", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "df3f654ef1364aeb6cdaeaea1c6334da949a798b2f8256c9ddc4e6a88a588e19", "submitted_at": "2025-06-19T05:26:40Z", "updated_at": "2026-05-18T17:55:59Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2506.16042v2" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-06-19; Recorded arXiv version: v2; Recorded version updated: 2026-05-18T17:55:59Z.", "author": [ { "literal": "Reyna Abhyankar" }, { "literal": "Qi Qi" }, { "literal": "Yiying Zhang" } ], "issued": { "date-parts": [ [ 2025, 6, 19 ] ] }, "archive": "arXiv", "archive_location": "2506.16042", "genre": "preprint", "version": "2" }, { "id": "arxiv:2610.01491", "citation-key": "arxiv_2610_01491", "type": "article", "title": "Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and Trajectories", "URL": "https://arxiv.org/abs/2610.01491v1", "custom": { "catalog_id": "arxiv:2610.01491", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2610.01491", "identifiers": { "arxiv": "2610.01491" }, "first_published_at": "2026-10-01", "record_updated_at": "2026-10-01", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9a5b97264b3928c8dc74b955cc4baa7005cd34b0ce9e42cbc48a63bc6dd1f5a7", "submitted_at": "2026-10-01T11:31:37Z", "updated_at": "2026-10-01T11:31:37Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.01491v1" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T11:31:37Z.", "author": [ { "literal": "Chengguang Gan" }, { "literal": "Zimeng He" }, { "literal": "Yoshihiro Tsujii" }, { "literal": "Ken-ichiro Kobayashi" }, { "literal": "Hiroki Itoh" }, { "literal": "Kotaro Funakoshi" } ], "issued": { "date-parts": [ [ 2026, 10, 1 ] ] }, "archive": "arXiv", "archive_location": "2610.01491", "genre": "preprint", "version": "1" }, { "id": "arxiv:2510.18488", "citation-key": "arxiv_2510_18488", "type": "article", "title": "AndroidControl-Curated: Revealing the True Potential of GUI Agents through Benchmark Purification", "URL": "https://arxiv.org/abs/2510.18488v1", "custom": { "catalog_id": "arxiv:2510.18488", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2510.18488", "identifiers": { "arxiv": "2510.18488" }, "first_published_at": "2025-10-21", "record_updated_at": "2025-10-21", "catalog_scope": "core", "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" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-10-21; Recorded arXiv version: v1; Recorded version updated: 2025-10-21T10:11:33Z.", "author": [ { "literal": "Ho Fai Leung" }, { "literal": "Xiaoyan Xi" }, { "literal": "Fei Zuo" } ], "issued": { "date-parts": [ [ 2025, 10, 21 ] ] }, "archive": "arXiv", "archive_location": "2510.18488", "genre": "preprint", "version": "1" }, { "id": "arxiv:2410.17520", "citation-key": "arxiv_2410_17520", "type": "article", "title": "MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control", "URL": "https://arxiv.org/abs/2410.17520v3", "custom": { "catalog_id": "arxiv:2410.17520", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2410.17520", "identifiers": { "arxiv": "2410.17520" }, "first_published_at": "2024-10-23", "record_updated_at": "2026-01-27", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "362cbf7ea267ddc4a64505aa95c4f16a9f3631f95319ce10eef9981e2c85937b", "submitted_at": "2024-10-23T02:51:43Z", "updated_at": "2026-01-27T01:51:55Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.17520v3" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-10-23; Recorded arXiv version: v3; Recorded version updated: 2026-01-27T01:51:55Z.", "author": [ { "literal": "Juyong Lee" }, { "literal": "Dongyoon Hahm" }, { "literal": "June Suk Choi" }, { "literal": "W. Bradley Knox" }, { "literal": "Kimin Lee" } ], "issued": { "date-parts": [ [ 2024, 10, 23 ] ] }, "archive": "arXiv", "archive_location": "2410.17520", "genre": "preprint", "version": "3" }, { "id": "arxiv:2504.18575", "citation-key": "arxiv_2504_18575", "type": "article", "title": "WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks", "URL": "https://arxiv.org/abs/2504.18575v3", "custom": { "catalog_id": "arxiv:2504.18575", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2504.18575", "identifiers": { "arxiv": "2504.18575" }, "first_published_at": "2025-04-22", "record_updated_at": "2025-05-16", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3a104d9076797555795766749f6b4eeec9428d0efb9340f7e55cffecd5d727b0", "submitted_at": "2025-04-22T17:51:03Z", "updated_at": "2025-05-16T22:42:29Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2504.18575v3" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-04-22; Recorded arXiv version: v3; Recorded version updated: 2025-05-16T22:42:29Z.", "author": [ { "literal": "Ivan Evtimov" }, { "literal": "Arman Zharmagambetov" }, { "literal": "Aaron Grattafiori" }, { "literal": "Chuan Guo" }, { "literal": "Kamalika Chaudhuri" } ], "issued": { "date-parts": [ [ 2025, 4, 22 ] ] }, "archive": "arXiv", "archive_location": "2504.18575", "genre": "preprint", "version": "3" }, { "id": "arxiv:2406.12814", "citation-key": "arxiv_2406_12814", "type": "article", "title": "Dissecting Adversarial Robustness of Multimodal LM Agents", "URL": "https://arxiv.org/abs/2406.12814v3", "custom": { "catalog_id": "arxiv:2406.12814", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2406.12814", "identifiers": { "arxiv": "2406.12814" }, "first_published_at": "2024-06-18", "record_updated_at": "2025-02-04", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7cc1c1ac93f8e328d33accf7cdaa1d65487c4f7abec15234b9e596a501947550", "submitted_at": "2024-06-18T17:32:48Z", "updated_at": "2025-02-04T20:02:17Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2406.12814v3" }, "publication": { "authors": [ "Chen Wu", "Rishi Shah", "Jing Yu Koh", "Russ Salakhutdinov", "Daniel Fried", "Aditi Raghunathan" ], "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/460a1d8eac34125dad453b28d6d64446-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. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "28362-28383", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/460a1d8eac34125dad453b28d6d64446-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Dissecting Adversarial Robustness of Multimodal LM Agents", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/460a1d8eac34125dad453b28d6d64446-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "citation_edition": "record", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2024-06-18; Recorded arXiv version: v3; Recorded version updated: 2025-02-04T20:02:17Z.", "author": [ { "literal": "Chen Henry Wu" }, { "literal": "Rishi Shah" }, { "literal": "Jing Yu Koh" }, { "literal": "Ruslan Salakhutdinov" }, { "literal": "Daniel Fried" }, { "literal": "Aditi Raghunathan" } ], "issued": { "date-parts": [ [ 2024, 6, 18 ] ] }, "archive": "arXiv", "archive_location": "2406.12814", "genre": "preprint", "version": "3" }, { "id": "arxiv:2505.21936", "citation-key": "arxiv_2505_21936", "type": "article", "title": "RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments", "URL": "https://arxiv.org/abs/2505.21936v5", "custom": { "catalog_id": "arxiv:2505.21936", "catalog_kind": "paper", "catalog_review_status": "curated", "canonical_source_url": "https://arxiv.org/abs/2505.21936", "identifiers": { "arxiv": "2505.21936" }, "first_published_at": "2025-05-28", "record_updated_at": "2026-03-01", "catalog_scope": "core", "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7fe3bdb1357a375de0b1700a6eda7d5987f358bd47fddf3405c27272a3453f2f", "submitted_at": "2025-05-28T03:42:09Z", "updated_at": "2026-03-01T07:50:09Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2505.21936v5" }, "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-05-28; Recorded arXiv version: v5; Recorded version updated: 2026-03-01T07:50:09Z.", "author": [ { "literal": "Zeyi Liao" }, { "literal": "Jaylen Jones" }, { "literal": "Linxi Jiang" }, { "literal": "Yuting Ning" }, { "literal": "Eric Fosler-Lussier" }, { "literal": "Yu Su" }, { "literal": "Zhiqiang Lin" }, { "literal": "Huan Sun" } ], "issued": { "date-parts": [ [ 2025, 5, 28 ] ] }, "archive": "arXiv", "archive_location": "2505.21936", "genre": "preprint", "version": "5" }, { "id": "arxiv:2607.00333", "citation-key": "arxiv_2607_00333", "type": "article", "title": "(A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile Agents", "URL": "https://arxiv.org/abs/2607.00333v2", "custom": { "catalog_id": "arxiv:2607.00333", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2607.00333", "identifiers": { "arxiv": "2607.00333" }, "first_published_at": "2026-07-01", "record_updated_at": "2026-07-14", "arxiv_snapshot": { "version": 2, "versioned_url": "https://arxiv.org/abs/2607.00333v2", "submitted_at": "2026-07-01T02:17:19Z", "updated_at": "2026-07-14T03:01:43Z", "abstract_sha256": "cd4d31e477d5915626d471682e52e5cd6083d9b0c67196f6de5de2a29c6a3058", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-07-01; Recorded arXiv version: v2; Recorded version updated: 2026-07-14T03:01:43Z.", "author": [ { "literal": "Zidong Zhang" }, { "literal": "Zhentao Xie" }, { "literal": "Wenrui Diao" }, { "literal": "Jianliang Wu" } ], "issued": { "date-parts": [ [ 2026, 7, 1 ] ] }, "archive": "arXiv", "archive_location": "2607.00333", "genre": "preprint", "version": "2" }, { "id": "arxiv:2506.13205", "citation-key": "arxiv_2506_13205", "type": "article", "title": "Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents", "URL": "https://arxiv.org/abs/2506.13205v6", "custom": { "catalog_id": "arxiv:2506.13205", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2506.13205", "identifiers": { "arxiv": "2506.13205" }, "first_published_at": "2025-06-16", "record_updated_at": "2025-09-05", "arxiv_snapshot": { "version": 6, "versioned_url": "https://arxiv.org/abs/2506.13205v6", "submitted_at": "2025-06-16T08:09:32Z", "updated_at": "2025-09-05T14:19:03Z", "abstract_sha256": "390304ce515886fa15fb8cd74d8b2df161a75b9adc0f4d2fad1f65976c6a6ce7", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-06-16; Recorded arXiv version: v6; Recorded version updated: 2025-09-05T14:19:03Z.", "author": [ { "literal": "Xuan Wang" }, { "literal": "Siyuan Liang" }, { "literal": "Zhe Liu" }, { "literal": "Yi Yu" }, { "literal": "Aishan Liu" }, { "literal": "Yuliang Lu" }, { "literal": "Xitong Gao" }, { "literal": "Ee-Chien Chang" } ], "issued": { "date-parts": [ [ 2025, 6, 16 ] ] }, "archive": "arXiv", "archive_location": "2506.13205", "genre": "preprint", "version": "6" }, { "id": "arxiv:2507.00841", "citation-key": "arxiv_2507_00841", "type": "article", "title": "SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents", "URL": "https://arxiv.org/abs/2507.00841v1", "custom": { "catalog_id": "arxiv:2507.00841", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2507.00841", "identifiers": { "arxiv": "2507.00841" }, "first_published_at": "2025-07-01", "record_updated_at": "2025-07-01", "arxiv_snapshot": { "version": 1, "versioned_url": "https://arxiv.org/abs/2507.00841v1", "submitted_at": "2025-07-01T15:10:00Z", "updated_at": "2025-07-01T15:10:00Z", "abstract_sha256": "78dd523ad6123fe1ee5164685a3853719c9a4442adac8661050f147ff6a9f619", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-07-01; Recorded arXiv version: v1; Recorded version updated: 2025-07-01T15:10:00Z.", "author": [ { "literal": "Siyuan Liang" }, { "literal": "Tianmeng Fang" }, { "literal": "Zhe Liu" }, { "literal": "Aishan Liu" }, { "literal": "Yan Xiao" }, { "literal": "Jinyuan He" }, { "literal": "Ee-Chien Chang" }, { "literal": "Xiaochun Cao" } ], "issued": { "date-parts": [ [ 2025, 7, 1 ] ] }, "archive": "arXiv", "archive_location": "2507.00841", "genre": "preprint", "version": "1" }, { "id": "arxiv:2608.14132", "citation-key": "arxiv_2608_14132", "type": "article", "title": "Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions", "URL": "https://arxiv.org/abs/2608.14132v1", "custom": { "catalog_id": "arxiv:2608.14132", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2608.14132", "identifiers": { "arxiv": "2608.14132" }, "first_published_at": "2026-08-14", "record_updated_at": "2026-08-14", "arxiv_snapshot": { "version": 1, "versioned_url": "https://arxiv.org/abs/2608.14132v1", "submitted_at": "2026-08-14T09:36:59Z", "updated_at": "2026-08-14T09:36:59Z", "abstract_sha256": "e2660e01921a78bed7280b34f35a1b587e62339c2e280d6294bbb6d6e666786e", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-08-14; Recorded arXiv version: v1; Recorded version updated: 2026-08-14T09:36:59Z.", "author": [ { "literal": "Xiaokai Yan" }, { "literal": "Jingtao Ding" }, { "literal": "Yong Li" }, { "literal": "Zhiwen Yu" } ], "issued": { "date-parts": [ [ 2026, 8, 14 ] ] }, "archive": "arXiv", "archive_location": "2608.14132", "genre": "preprint", "version": "1" }, { "id": "arxiv:2507.18165", "citation-key": "arxiv_2507_18165", "type": "article", "title": "ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent", "URL": "https://arxiv.org/abs/2507.18165v1", "custom": { "catalog_id": "arxiv:2507.18165", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2507.18165", "identifiers": { "arxiv": "2507.18165" }, "first_published_at": "2025-07-24", "record_updated_at": "2025-07-24", "arxiv_snapshot": { "version": 1, "versioned_url": "https://arxiv.org/abs/2507.18165v1", "submitted_at": "2025-07-24T08:02:35Z", "updated_at": "2025-07-24T08:02:35Z", "abstract_sha256": "e3c271f330c5bf27e2831efd96fb1d6f843bd79942791686a866df1b4812de2f", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2025-07-24; Recorded arXiv version: v1; Recorded version updated: 2025-07-24T08:02:35Z.", "author": [ { "literal": "Yuheng Zhao" }, { "literal": "Xueli Shu" }, { "literal": "Liwen Fan" }, { "literal": "Lin Gao" }, { "literal": "Yu Zhang" }, { "literal": "Siming Chen" } ], "issued": { "date-parts": [ [ 2025, 7, 24 ] ] }, "archive": "arXiv", "archive_location": "2507.18165", "genre": "preprint", "version": "1" }, { "id": "arxiv:2608.09944", "citation-key": "arxiv_2608_09944", "type": "article", "title": "Navigation Alone Is Not Enough: Evaluating Explanatory Assistive UI Agents", "URL": "https://arxiv.org/abs/2608.09944v1", "custom": { "catalog_id": "arxiv:2608.09944", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/2608.09944", "identifiers": { "arxiv": "2608.09944" }, "first_published_at": "2026-07-01", "record_updated_at": "2026-07-01", "arxiv_snapshot": { "version": 1, "versioned_url": "https://arxiv.org/abs/2608.09944v1", "submitted_at": "2026-07-01T16:24:07Z", "updated_at": "2026-07-01T16:24:07Z", "abstract_sha256": "d5ccb0d41798a1a3236e6f9b4361814cccdd40facf9b43bf0bf52932337484dc", "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1" }, "manuscript_bibliography_basis": "Fresh official arXiv title-search metadata; no production catalog approval implied.", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2026-07-01; Recorded arXiv version: v1; Recorded version updated: 2026-07-01T16:24:07Z.", "author": [ { "literal": "Santosh Patapati" } ], "issued": { "date-parts": [ [ 2026, 7, 1 ] ] }, "archive": "arXiv", "archive_location": "2608.09944", "genre": "preprint", "version": "1" }, { "id": "doi:10.1038/sdata.2016.18", "citation-key": "wilkinson2016fair", "type": "article-journal", "title": "The FAIR Guiding Principles for scientific data management and stewardship", "URL": "https://www.nature.com/articles/sdata201618", "custom": { "catalog_id": "doi:10.1038/sdata.2016.18", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://www.nature.com/articles/sdata201618", "identifiers": { "doi": "10.1038/sdata.2016.18" }, "first_published_at": null, "record_updated_at": null, "publication": { "type": "journal-article", "title": "The FAIR Guiding Principles for scientific data management and stewardship", "authors": [ "Wilkinson, Mark D.", "Dumontier, Michel", "Aalbersberg, IJsbrand Jan", "Appleton, Gabrielle", "Axton, Myles", "Baak, Arie", "Blomberg, Niklas", "Boiten, Jan-Willem", "da Silva Santos, Luiz Bonino", "Bourne, Philip E.", "Bouwman, Jildau", "Brookes, Anthony J.", "Clark, Tim", "Crosas, Mercè", "Dillo, Ingrid", "Dumon, Olivier", "Edmunds, Scott", "Evelo, Chris T.", "Finkers, Richard", "Gonzalez-Beltran, Alejandra", "Gray, Alasdair J.G.", "Groth, Paul", "Goble, Carole", "Grethe, Jeffrey S.", "Heringa, Jaap", "’t Hoen, Peter A.C", "Hooft, Rob", "Kuhn, Tobias", "Kok, Ruben", "Kok, Joost", "Lusher, Scott J.", "Martone, Maryann E.", "Mons, Albert", "Packer, Abel L.", "Persson, Bengt", "Rocca-Serra, Philippe", "Roos, Marco", "van Schaik, Rene", "Sansone, Susanna-Assunta", "Schultes, Erik", "Sengstag, Thierry", "Slater, Ted", "Strawn, George", "Swertz, Morris A.", "Thompson, Mark", "van der Lei, Johan", "van Mulligen, Erik", "Velterop, Jan", "Waagmeester, Andra", "Wittenburg, Peter", "Wolstencroft, Katherine", "Zhao, Jun", "Mons, Barend" ], "date_parts": [ 2016 ], "url": "https://www.nature.com/articles/sdata201618", "doi": "10.1038/sdata.2016.18", "venue": "Scientific Data", "volume": "3" }, "citation_edition": "publication", "bibliography_authority": "official publisher metadata and visible publication date", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "Publication date: 2016.", "author": [ { "literal": "Wilkinson, Mark D." }, { "literal": "Dumontier, Michel" }, { "literal": "Aalbersberg, IJsbrand Jan" }, { "literal": "Appleton, Gabrielle" }, { "literal": "Axton, Myles" }, { "literal": "Baak, Arie" }, { "literal": "Blomberg, Niklas" }, { "literal": "Boiten, Jan-Willem" }, { "literal": "da Silva Santos, Luiz Bonino" }, { "literal": "Bourne, Philip E." }, { "literal": "Bouwman, Jildau" }, { "literal": "Brookes, Anthony J." }, { "literal": "Clark, Tim" }, { "literal": "Crosas, Mercè" }, { "literal": "Dillo, Ingrid" }, { "literal": "Dumon, Olivier" }, { "literal": "Edmunds, Scott" }, { "literal": "Evelo, Chris T." }, { "literal": "Finkers, Richard" }, { "literal": "Gonzalez-Beltran, Alejandra" }, { "literal": "Gray, Alasdair J.G." }, { "literal": "Groth, Paul" }, { "literal": "Goble, Carole" }, { "literal": "Grethe, Jeffrey S." }, { "literal": "Heringa, Jaap" }, { "literal": "’t Hoen, Peter A.C" }, { "literal": "Hooft, Rob" }, { "literal": "Kuhn, Tobias" }, { "literal": "Kok, Ruben" }, { "literal": "Kok, Joost" }, { "literal": "Lusher, Scott J." }, { "literal": "Martone, Maryann E." }, { "literal": "Mons, Albert" }, { "literal": "Packer, Abel L." }, { "literal": "Persson, Bengt" }, { "literal": "Rocca-Serra, Philippe" }, { "literal": "Roos, Marco" }, { "literal": "van Schaik, Rene" }, { "literal": "Sansone, Susanna-Assunta" }, { "literal": "Schultes, Erik" }, { "literal": "Sengstag, Thierry" }, { "literal": "Slater, Ted" }, { "literal": "Strawn, George" }, { "literal": "Swertz, Morris A." }, { "literal": "Thompson, Mark" }, { "literal": "van der Lei, Johan" }, { "literal": "van Mulligen, Erik" }, { "literal": "Velterop, Jan" }, { "literal": "Waagmeester, Andra" }, { "literal": "Wittenburg, Peter" }, { "literal": "Wolstencroft, Katherine" }, { "literal": "Zhao, Jun" }, { "literal": "Mons, Barend" } ], "issued": { "date-parts": [ [ 2016 ] ] }, "DOI": "10.1038/sdata.2016.18", "container-title": "Scientific Data", "volume": "3", "article-number": "160018" }, { "id": "doi:10.1038/s41597-022-01710-x", "citation-key": "barker2022fair4rs", "type": "article-journal", "title": "Introducing the FAIR Principles for research software", "URL": "https://www.nature.com/articles/s41597-022-01710-x", "custom": { "catalog_id": "doi:10.1038/s41597-022-01710-x", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://www.nature.com/articles/s41597-022-01710-x", "identifiers": { "doi": "10.1038/s41597-022-01710-x" }, "first_published_at": null, "record_updated_at": null, "publication": { "type": "journal-article", "title": "Introducing the FAIR Principles for research software", "authors": [ "Barker, Michelle", "Chue Hong, Neil P.", "Katz, Daniel S.", "Lamprecht, Anna-Lena", "Martinez-Ortiz, Carlos", "Psomopoulos, Fotis", "Harrow, Jennifer", "Castro, Leyla Jael", "Gruenpeter, Morane", "Martinez, Paula Andrea", "Honeyman, Tom" ], "date_parts": [ 2022 ], "url": "https://www.nature.com/articles/s41597-022-01710-x", "doi": "10.1038/s41597-022-01710-x", "venue": "Scientific Data", "volume": "9" }, "citation_edition": "publication", "bibliography_authority": "official publisher metadata and visible publication date", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "Publication date: 2022.", "author": [ { "literal": "Barker, Michelle" }, { "literal": "Chue Hong, Neil P." }, { "literal": "Katz, Daniel S." }, { "literal": "Lamprecht, Anna-Lena" }, { "literal": "Martinez-Ortiz, Carlos" }, { "literal": "Psomopoulos, Fotis" }, { "literal": "Harrow, Jennifer" }, { "literal": "Castro, Leyla Jael" }, { "literal": "Gruenpeter, Morane" }, { "literal": "Martinez, Paula Andrea" }, { "literal": "Honeyman, Tom" } ], "issued": { "date-parts": [ [ 2022 ] ] }, "DOI": "10.1038/s41597-022-01710-x", "container-title": "Scientific Data", "volume": "9", "article-number": "622" }, { "id": "arxiv:1803.09010", "citation-key": "arxiv_1803_09010", "type": "article", "title": "Datasheets for Datasets", "URL": "https://arxiv.org/abs/1803.09010v8", "custom": { "catalog_id": "arxiv:1803.09010", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/1803.09010v8", "identifiers": { "arxiv": "1803.09010" }, "first_published_at": "2018-03-23", "record_updated_at": "2021-12-01", "arxiv_snapshot": { "version": 8, "versioned_url": "https://arxiv.org/abs/1803.09010v8" }, "bibliography_authority": "official arXiv abstract/version history; v8 full-text selected sections read", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2018-03-23; Recorded arXiv version: v8; Recorded version updated: 2021-12-01.", "author": [ { "literal": "Timnit Gebru" }, { "literal": "Jamie Morgenstern" }, { "literal": "Briana Vecchione" }, { "literal": "Jennifer Wortman Vaughan" }, { "literal": "Hanna Wallach" }, { "literal": "Hal Daumé III" }, { "literal": "Kate Crawford" } ], "issued": { "date-parts": [ [ 2018, 3, 23 ] ] }, "archive": "arXiv", "archive_location": "1803.09010", "genre": "preprint", "version": "8" }, { "id": "arxiv:1810.03993", "citation-key": "arxiv_1810_03993", "type": "article", "title": "Model Cards for Model Reporting", "URL": "https://arxiv.org/abs/1810.03993v2", "custom": { "catalog_id": "arxiv:1810.03993", "catalog_kind": "paper", "catalog_review_status": "metadata_verified", "canonical_source_url": "https://arxiv.org/abs/1810.03993v2", "identifiers": { "arxiv": "1810.03993" }, "first_published_at": "2018-10-05", "record_updated_at": "2019-01-14", "arxiv_snapshot": { "version": 2, "versioned_url": "https://arxiv.org/abs/1810.03993v2" }, "bibliography_authority": "official arXiv abstract/version history; v2 full-text selected sections read", "manuscript_read_level": "selected_fulltext_sections_read" }, "note": "First published: 2018-10-05; Recorded arXiv version: v2; Recorded version updated: 2019-01-14.", "author": [ { "literal": "Margaret Mitchell" }, { "literal": "Simone Wu" }, { "literal": "Andrew Zaldivar" }, { "literal": "Parker Barnes" }, { "literal": "Lucy Vasserman" }, { "literal": "Ben Hutchinson" }, { "literal": "Elena Spitzer" }, { "literal": "Inioluwa Deborah Raji" }, { "literal": "Timnit Gebru" } ], "issued": { "date-parts": [ [ 2018, 10, 5 ] ] }, "archive": "arXiv", "archive_location": "1810.03993", "genre": "preprint", "version": "2" } ]