[ { "URL": "https://arxiv.org/abs/2403.10170v2", "archive": "arXiv", "archive_location": "2403.10170", "author": [ { "literal": "Andrés Muñoz" }, { "literal": "Daniel Borrajo" } ], "citation-key": "arxiv_2403_10170", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aacb4d2cac31e478aa56ee25b6b39e5ba8fe164f89102e665f8fb25cf3822e7b", "submitted_at": "2024-03-15T10:26:52Z", "updated_at": "2024-08-27T18:36:12Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2403.10170v2" }, "canonical_source_url": "https://arxiv.org/abs/2403.10170", "catalog_id": "arxiv:2403.10170", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-03-15", "identifiers": { "arxiv": "2403.10170" }, "record_updated_at": "2024-08-27" }, "genre": "preprint", "id": "arxiv:2403.10170", "issued": { "date-parts": [ [ 2024, 3, 15 ] ] }, "note": "First published: 2024-03-15; Recorded arXiv version: v2; Recorded version updated: 2024-08-27T18:36:12Z.", "title": "Computer User Interface Understanding. A New Dataset and a Learning Framework", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2403.17918v3", "archive": "arXiv", "archive_location": "2403.17918", "author": [ { "literal": "Longtao Zheng" }, { "literal": "Zhiyuan Huang" }, { "literal": "Zhenghai Xue" }, { "literal": "Xinrun Wang" }, { "literal": "Bo An" }, { "literal": "Shuicheng Yan" } ], "citation-key": "arxiv_2403_17918", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fe1432b46c15566182418bf3fa2f918607e8b0e9a383459416d03e28dc7e347c", "submitted_at": "2024-03-26T17:54:15Z", "updated_at": "2025-02-14T08:13:39Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2403.17918v3" }, "canonical_source_url": "https://arxiv.org/abs/2403.17918", "catalog_id": "arxiv:2403.17918", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-03-26", "identifiers": { "arxiv": "2403.17918" }, "record_updated_at": "2025-02-14" }, "genre": "preprint", "id": "arxiv:2403.17918", "issued": { "date-parts": [ [ 2024, 3, 26 ] ] }, "note": "First published: 2024-03-26; Recorded arXiv version: v3; Recorded version updated: 2025-02-14T08:13:39Z.", "title": "AgentStudio: A Toolkit for Building General Virtual Agents", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2406.10227v1", "archive": "arXiv", "archive_location": "2406.10227", "author": [ { "literal": "Kevin Qinghong Lin" }, { "literal": "Linjie Li" }, { "literal": "Difei Gao" }, { "literal": "Qinchen WU" }, { "literal": "Mingyi Yan" }, { "literal": "Zhengyuan Yang" }, { "literal": "Lijuan Wang" }, { "literal": "Mike Zheng Shou" } ], "citation-key": "arxiv_2406_10227", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "66b5fb1e839490df80e9750fdc049f7fe3d2d4686c4090d78ea01bc542fe55b0", "submitted_at": "2024-06-14T17:59:08Z", "updated_at": "2024-06-14T17:59:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2406.10227v1" }, "canonical_source_url": "https://arxiv.org/abs/2406.10227", "catalog_id": "arxiv:2406.10227", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-06-14", "identifiers": { "arxiv": "2406.10227" }, "publication": { "authors": [ "Kevin Q. Lin", "Linjie Li", "Difei Gao", "Qinchen Wu", "Mingyi Yan", "Zhengyuan Yang", "Lijuan Wang", "Mike Z. Shou" ], "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": "10.52202/079017-2214", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/804e757b7d7043c26701c3a313032101-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": "69329-69360", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/804e757b7d7043c26701c3a313032101-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "VideoGUI: A Benchmark for GUI Automation from Instructional Videos", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/804e757b7d7043c26701c3a313032101-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "record_updated_at": "2024-06-14" }, "genre": "preprint", "id": "arxiv:2406.10227", "issued": { "date-parts": [ [ 2024, 6, 14 ] ] }, "note": "First published: 2024-06-14; Recorded arXiv version: v1; Recorded version updated: 2024-06-14T17:59:08Z.", "title": "VideoGUI: A Benchmark for GUI Automation from Instructional Videos", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2406.10819v2", "archive": "arXiv", "archive_location": "2406.10819", "author": [ { "literal": "Dongping Chen" }, { "literal": "Yue Huang" }, { "literal": "Siyuan Wu" }, { "literal": "Jingyu Tang" }, { "literal": "Liuyi Chen" }, { "literal": "Yilin Bai" }, { "literal": "Zhigang He" }, { "literal": "Chenlong Wang" }, { "literal": "Huichi Zhou" }, { "literal": "Yiqiang Li" }, { "literal": "Tianshuo Zhou" }, { "literal": "Yue Yu" }, { "literal": "Chujie Gao" }, { "literal": "Qihui Zhang" }, { "literal": "Yi Gui" }, { "literal": "Zhen Li" }, { "literal": "Yao Wan" }, { "literal": "Pan Zhou" }, { "literal": "Jianfeng Gao" }, { "literal": "Lichao Sun" } ], "citation-key": "arxiv_2406_10819", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9997c3ab43f0e3e69ad4dcbe15257ea4392d36fa3c82f90c6b7730667a067f99", "submitted_at": "2024-06-16T06:56:53Z", "updated_at": "2025-03-24T11:46:14Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2406.10819v2" }, "canonical_source_url": "https://arxiv.org/abs/2406.10819", "catalog_id": "arxiv:2406.10819", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-06-16", "identifiers": { "arxiv": "2406.10819" }, "record_updated_at": "2025-03-24" }, "genre": "preprint", "id": "arxiv:2406.10819", "issued": { "date-parts": [ [ 2024, 6, 16 ] ] }, "note": "First published: 2024-06-16; Recorded arXiv version: v2; Recorded version updated: 2025-03-24T11:46:14Z.", "title": "GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2406.13264v2", "archive": "arXiv", "archive_location": "2406.13264", "author": [ { "literal": "Michael Wornow" }, { "literal": "Avanika Narayan" }, { "literal": "Ben Viggiano" }, { "literal": "Ishan S. Khare" }, { "literal": "Tathagat Verma" }, { "literal": "Tibor Thompson" }, { "literal": "Miguel Angel Fuentes Hernandez" }, { "literal": "Sudharsan Sundar" }, { "literal": "Chloe Trujillo" }, { "literal": "Krrish Chawla" }, { "literal": "Rongfei Lu" }, { "literal": "Justin Shen" }, { "literal": "Divya Nagaraj" }, { "literal": "Joshua Martinez" }, { "literal": "Vardhan Agrawal" }, { "literal": "Althea Hudson" }, { "literal": "Nigam H. Shah" }, { "literal": "Christopher Re" } ], "citation-key": "arxiv_2406_13264", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a7e7d00030ea8c77b9ed6f950d62f2bd417d3870f24b2f4589d8068c9484e328", "submitted_at": "2024-06-19T06:50:15Z", "updated_at": "2024-10-11T00:06:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2406.13264v2" }, "canonical_source_url": "https://arxiv.org/abs/2406.13264", "catalog_id": "arxiv:2406.13264", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-06-19", "identifiers": { "arxiv": "2406.13264" }, "record_updated_at": "2024-10-11" }, "genre": "preprint", "id": "arxiv:2406.13264", "issued": { "date-parts": [ [ 2024, 6, 19 ] ] }, "note": "First published: 2024-06-19; Recorded arXiv version: v2; Recorded version updated: 2024-10-11T00:06:31Z.", "title": "WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2406.13719v1", "archive": "arXiv", "archive_location": "2406.13719", "author": [ { "literal": "Qinchen Wu" }, { "literal": "Difei Gao" }, { "literal": "Kevin Qinghong Lin" }, { "literal": "Zhuoyu Wu" }, { "literal": "Xiangwu Guo" }, { "literal": "Peiran Li" }, { "literal": "Weichen Zhang" }, { "literal": "Hengxu Wang" }, { "literal": "Mike Zheng Shou" } ], "citation-key": "arxiv_2406_13719", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "369c32dba4bab0cfc05b41db16c73d5672605b7f81caabb2dbd72f581b3290ec", "submitted_at": "2024-06-19T17:22:11Z", "updated_at": "2024-06-19T17:22:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2406.13719v1" }, "canonical_source_url": "https://arxiv.org/abs/2406.13719", "catalog_id": "arxiv:2406.13719", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-06-19", "identifiers": { "arxiv": "2406.13719" }, "record_updated_at": "2024-06-19" }, "genre": "preprint", "id": "arxiv:2406.13719", "issued": { "date-parts": [ [ 2024, 6, 19 ] ] }, "note": "First published: 2024-06-19; Recorded arXiv version: v1; Recorded version updated: 2024-06-19T17:22:11Z.", "title": "GUI Action Narrator: Where and When Did That Action Take Place?", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2410.19100v3", "archive": "arXiv", "archive_location": "2410.19100", "author": [ { "literal": "Lawrence Jang" }, { "literal": "Yinheng Li" }, { "literal": "Dan Zhao" }, { "literal": "Charles Ding" }, { "literal": "Justin Lin" }, { "literal": "Paul Pu Liang" }, { "literal": "Rogerio Bonatti" }, { "literal": "Kazuhito Koishida" } ], "citation-key": "arxiv_2410_19100", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f413943bd5c2a395ddb5cf38a1a5ad61754b35a9eb5de43e8d980bd83e4adff", "submitted_at": "2024-10-24T19:03:01Z", "updated_at": "2025-02-15T05:19:38Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.19100v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.19100", "catalog_id": "arxiv:2410.19100", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-10-24", "identifiers": { "arxiv": "2410.19100" }, "publication": { "authors": [ "Lawrence Jang", "Yinheng Li", "Dan Zhao", "Charles Ding", "Justin Lin", "Paul Pu Liang", "Rogerio Bonatti", "Kazuhito Koishida" ], "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/5b555804d495321df2e3208cc27f4fbc-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "36934-36958", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/5b555804d495321df2e3208cc27f4fbc-Paper-Conference.pdf", "publisher": null, "series": null, "title": "VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/5b555804d495321df2e3208cc27f4fbc-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "record_updated_at": "2025-02-15" }, "genre": "preprint", "id": "arxiv:2410.19100", "issued": { "date-parts": [ [ 2024, 10, 24 ] ] }, "note": "First published: 2024-10-24; Recorded arXiv version: v3; Recorded version updated: 2025-02-15T05:19:38Z.", "title": "VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2502.17110v3", "archive": "arXiv", "archive_location": "2502.17110", "author": [ { "literal": "Junyang Wang" }, { "literal": "Haiyang Xu" }, { "literal": "Xi Zhang" }, { "literal": "Ming Yan" }, { "literal": "Ji Zhang" }, { "literal": "Fei Huang" }, { "literal": "Jitao Sang" } ], "citation-key": "arxiv_2502_17110", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d723cb764deb78b194ff0199c7f1b921a12b6a41655c07b06ae88c3d0af58358", "submitted_at": "2025-02-24T12:51:23Z", "updated_at": "2025-06-03T08:37:03Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2502.17110v3" }, "canonical_source_url": "https://arxiv.org/abs/2502.17110", "catalog_id": "arxiv:2502.17110", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-02-24", "identifiers": { "arxiv": "2502.17110" }, "record_updated_at": "2025-06-03" }, "genre": "preprint", "id": "arxiv:2502.17110", "issued": { "date-parts": [ [ 2025, 2, 24 ] ] }, "note": "First published: 2025-02-24; Recorded arXiv version: v3; Recorded version updated: 2025-06-03T08:37:03Z.", "title": "Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2503.07919v3", "archive": "arXiv", "archive_location": "2503.07919", "author": [ { "literal": "Yixiao Song" }, { "literal": "Katherine Thai" }, { "literal": "Chau Minh Pham" }, { "literal": "Yapei Chang" }, { "literal": "Mazin Nadaf" }, { "literal": "Mohit Iyyer" } ], "citation-key": "arxiv_2503_07919", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e1cd6327559d11982fb4a97e739cb6b5234c509859692084ed78130241f6d252", "submitted_at": "2025-03-10T23:50:30Z", "updated_at": "2025-07-24T17:45:05Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2503.07919v3" }, "canonical_source_url": "https://arxiv.org/abs/2503.07919", "catalog_id": "arxiv:2503.07919", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-03-10", "identifiers": { "arxiv": "2503.07919" }, "record_updated_at": "2025-07-24" }, "genre": "preprint", "id": "arxiv:2503.07919", "issued": { "date-parts": [ [ 2025, 3, 10 ] ] }, "note": "First published: 2025-03-10; Recorded arXiv version: v3; Recorded version updated: 2025-07-24T17:45:05Z.", "title": "BEARCUBS: A benchmark for computer-using web agents", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2503.17709v1", "archive": "arXiv", "archive_location": "2503.17709", "author": [ { "literal": "Yuchen Sun" }, { "literal": "Shanhui Zhao" }, { "literal": "Tao Yu" }, { "literal": "Hao Wen" }, { "literal": "Samith Va" }, { "literal": "Mengwei Xu" }, { "literal": "Yuanchun Li" }, { "literal": "Chongyang Zhang" } ], "citation-key": "arxiv_2503_17709", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "80bb507bf3cdccf6f023d0c334899d9d7099c362e9f37c314b15ff9388bae65c", "submitted_at": "2025-03-22T09:30:37Z", "updated_at": "2025-03-22T09:30:37Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2503.17709v1" }, "canonical_source_url": "https://arxiv.org/abs/2503.17709", "catalog_id": "arxiv:2503.17709", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-03-22", "identifiers": { "arxiv": "2503.17709" }, "record_updated_at": "2025-03-22" }, "genre": "preprint", "id": "arxiv:2503.17709", "issued": { "date-parts": [ [ 2025, 3, 22 ] ] }, "note": "First published: 2025-03-22; Recorded arXiv version: v1; Recorded version updated: 2025-03-22T09:30:37Z.", "title": "GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2504.12679v4", "archive": "arXiv", "archive_location": "2504.12679", "author": [ { "literal": "Bofei Zhang" }, { "literal": "Zirui Shang" }, { "literal": "Zhi Gao" }, { "literal": "Wang Zhang" }, { "literal": "Rui Xie" }, { "literal": "Xiaojian Ma" }, { "literal": "Tao Yuan" }, { "literal": "Xinxiao Wu" }, { "literal": "Song-Chun Zhu" }, { "literal": "Qing Li" } ], "citation-key": "arxiv_2504_12679", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "346fc4db7f8fbf2dc66c32e36f5cc5ace22228d60bdd4c61b6b7ac65487a4a8c", "submitted_at": "2025-04-17T06:15:56Z", "updated_at": "2025-12-04T15:01:09Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2504.12679v4" }, "canonical_source_url": "https://arxiv.org/abs/2504.12679", "catalog_id": "arxiv:2504.12679", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-17", "identifiers": { "arxiv": "2504.12679" }, "record_updated_at": "2025-12-04" }, "genre": "preprint", "id": "arxiv:2504.12679", "issued": { "date-parts": [ [ 2025, 4, 17 ] ] }, "note": "First published: 2025-04-17; Recorded arXiv version: v4; Recorded version updated: 2025-12-04T15:01:09Z.", "title": "TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2505.12632v1", "archive": "arXiv", "archive_location": "2505.12632", "author": [ { "literal": "Yunseok Jang" }, { "literal": "Yeda Song" }, { "literal": "Sungryull Sohn" }, { "literal": "Lajanugen Logeswaran" }, { "literal": "Tiange Luo" }, { "literal": "Dong-Ki Kim" }, { "literal": "Kyunghoon Bae" }, { "literal": "Honglak Lee" } ], "citation-key": "arxiv_2505_12632", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "64672e6a3450256a8b04d9db231e885e2dd4e8688235f6c7853d70d6276610ff", "submitted_at": "2025-05-19T02:39:03Z", "updated_at": "2025-05-19T02:39:03Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.12632v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.12632", "catalog_id": "arxiv:2505.12632", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-19", "identifiers": { "arxiv": "2505.12632" }, "record_updated_at": "2025-05-19" }, "genre": "preprint", "id": "arxiv:2505.12632", "issued": { "date-parts": [ [ 2025, 5, 19 ] ] }, "note": "First published: 2025-05-19; Recorded arXiv version: v1; Recorded version updated: 2025-05-19T02:39:03Z.", "title": "Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.24838v2", "archive": "arXiv", "archive_location": "2505.24838", "author": [ { "literal": "Brandon Man" }, { "literal": "Ghadi Nehme" }, { "literal": "Md Ferdous Alam" }, { "literal": "Faez Ahmed" } ], "citation-key": "arxiv_2505_24838", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f913b87f07fdad0e4c45264c58c8d9b9d13ca26695306d9e0644eb856f18ced7", "submitted_at": "2025-05-30T17:39:52Z", "updated_at": "2025-11-08T18:27:03Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2505.24838v2" }, "canonical_source_url": "https://arxiv.org/abs/2505.24838", "catalog_id": "arxiv:2505.24838", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-30", "identifiers": { "arxiv": "2505.24838" }, "record_updated_at": "2025-11-08" }, "genre": "preprint", "id": "arxiv:2505.24838", "issued": { "date-parts": [ [ 2025, 5, 30 ] ] }, "note": "First published: 2025-05-30; Recorded arXiv version: v2; Recorded version updated: 2025-11-08T18:27:03Z.", "title": "VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Video", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2510.19488v1", "archive": "arXiv", "archive_location": "2510.19488", "author": [ { "literal": "Dunjie Lu" }, { "literal": "Yiheng Xu" }, { "literal": "Junli Wang" }, { "literal": "Haoyuan Wu" }, { "literal": "Xinyuan Wang" }, { "literal": "Zekun Wang" }, { "literal": "Junlin Yang" }, { "literal": "Hongjin Su" }, { "literal": "Jixuan Chen" }, { "literal": "Junda Chen" }, { "literal": "Yuchen Mao" }, { "literal": "Jingren Zhou" }, { "literal": "Junyang Lin" }, { "literal": "Binyuan Hui" }, { "literal": "Tao Yu" } ], "citation-key": "arxiv_2510_19488", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ebb064e1a9c3e2255677d9b4cd9ce33d2a97dd26a379c321721d576e7c5d6399", "submitted_at": "2025-10-22T11:25:48Z", "updated_at": "2025-10-22T11:25:48Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.19488v1" }, "canonical_source_url": "https://arxiv.org/abs/2510.19488", "catalog_id": "arxiv:2510.19488", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-22", "identifiers": { "arxiv": "2510.19488" }, "record_updated_at": "2025-10-22" }, "genre": "preprint", "id": "arxiv:2510.19488", "issued": { "date-parts": [ [ 2025, 10, 22 ] ] }, "note": "First published: 2025-10-22; Recorded arXiv version: v1; Recorded version updated: 2025-10-22T11:25:48Z.", "title": "VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2511.04137v1", "archive": "arXiv", "archive_location": "2511.04137", "author": [ { "literal": "Yujian Liu" }, { "literal": "Ze Wang" }, { "literal": "Hao Chen" }, { "literal": "Ximeng Sun" }, { "literal": "Xiaodong Yu" }, { "literal": "Jialian Wu" }, { "literal": "Jiang Liu" }, { "literal": "Emad Barsoum" }, { "literal": "Zicheng Liu" }, { "literal": "Shiyu Chang" } ], "citation-key": "arxiv_2511_04137", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a91413c1e80869860d411402ab49f6e5968787b3bca83f0a9066a0e9c2f75d40", "submitted_at": "2025-11-06T07:29:02Z", "updated_at": "2025-11-06T07:29:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.04137v1" }, "canonical_source_url": "https://arxiv.org/abs/2511.04137", "catalog_id": "arxiv:2511.04137", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-06", "identifiers": { "arxiv": "2511.04137" }, "record_updated_at": "2025-11-06" }, "genre": "preprint", "id": "arxiv:2511.04137", "issued": { "date-parts": [ [ 2025, 11, 6 ] ] }, "note": "First published: 2025-11-06; Recorded arXiv version: v1; Recorded version updated: 2025-11-06T07:29:02Z.", "title": "Learning from Online Videos at Inference Time for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.10178v1", "archive": "arXiv", "archive_location": "2603.10178", "author": [ { "literal": "Linxin Song" }, { "literal": "Jieyu Zhang" }, { "literal": "Huanxin Sheng" }, { "literal": "Taiwei Shi" }, { "literal": "Gupta Rahul" }, { "literal": "Yang Liu" }, { "literal": "Ranjay Krishna" }, { "literal": "Jian Kang" }, { "literal": "Jieyu Zhao" } ], "citation-key": "arxiv_2603_10178", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "22b3001540ac8cc75117cdfb4f381462fe7df3fe7700a86e14b9f522803316ac", "submitted_at": "2026-03-10T19:17:22Z", "updated_at": "2026-03-10T19:17:22Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.10178v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.10178", "catalog_id": "arxiv:2603.10178", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-10", "identifiers": { "arxiv": "2603.10178" }, "record_updated_at": "2026-03-10" }, "genre": "preprint", "id": "arxiv:2603.10178", "issued": { "date-parts": [ [ 2026, 3, 10 ] ] }, "note": "First published: 2026-03-10; Recorded arXiv version: v1; Recorded version updated: 2026-03-10T19:17:22Z.", "title": "Video-Based Reward Modeling for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.22529v1", "archive": "arXiv", "archive_location": "2603.22529", "author": [ { "literal": "Shoubin Yu" }, { "literal": "Lei Shu" }, { "literal": "Antoine Yang" }, { "literal": "Yao Fu" }, { "literal": "Srinivas Sunkara" }, { "literal": "Maria Wang" }, { "literal": "Jindong Chen" }, { "literal": "Mohit Bansal" }, { "literal": "Boqing Gong" } ], "citation-key": "arxiv_2603_22529", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3e4ed7391969359c2594e8b96b8a3a559ef98d2c84a10c1a2c39b3bd962b58c5", "submitted_at": "2026-03-23T19:47:58Z", "updated_at": "2026-03-23T19:47:58Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.22529v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.22529", "catalog_id": "arxiv:2603.22529", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-23", "identifiers": { "arxiv": "2603.22529" }, "record_updated_at": "2026-03-23" }, "genre": "preprint", "id": "arxiv:2603.22529", "issued": { "date-parts": [ [ 2026, 3, 23 ] ] }, "note": "First published: 2026-03-23; Recorded arXiv version: v1; Recorded version updated: 2026-03-23T19:47:58Z.", "title": "Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.24440v1", "archive": "arXiv", "archive_location": "2603.24440", "author": [ { "literal": "Xiangru Jian" }, { "literal": "Shravan Nayak" }, { "literal": "Kevin Qinghong Lin" }, { "literal": "Aarash Feizi" }, { "literal": "Kaixin Li" }, { "literal": "Patrice Bechard" }, { "literal": "Spandana Gella" }, { "literal": "Sai Rajeswar" } ], "citation-key": "arxiv_2603_24440", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "15237fda2f3799314009635017487749dbedc9b1a0ffdd6b56a8d28eaf01481d", "submitted_at": "2026-03-25T15:52:56Z", "updated_at": "2026-03-25T15:52:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.24440v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.24440", "catalog_id": "arxiv:2603.24440", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-25", "identifiers": { "arxiv": "2603.24440" }, "record_updated_at": "2026-03-25" }, "genre": "preprint", "id": "arxiv:2603.24440", "issued": { "date-parts": [ [ 2026, 3, 25 ] ] }, "note": "First published: 2026-03-25; Recorded arXiv version: v1; Recorded version updated: 2026-03-25T15:52:56Z.", "title": "CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.25864v1", "archive": "arXiv", "archive_location": "2603.25864", "author": [ { "literal": "Saelyne Yang" }, { "literal": "Jaesang Yu" }, { "literal": "Yi-Hao Peng" }, { "literal": "Kevin Qinghong Lin" }, { "literal": "Jae Won Cho" }, { "literal": "Yale Song" }, { "literal": "Juho Kim" } ], "citation-key": "arxiv_2603_25864", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9b3dd3efca196fa3dd168431102dbb5f0f763e7d9e54b3d709ad2362a9c6f154", "submitted_at": "2026-03-26T19:37:53Z", "updated_at": "2026-03-26T19:37:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.25864v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.25864", "catalog_id": "arxiv:2603.25864", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-26", "identifiers": { "arxiv": "2603.25864" }, "record_updated_at": "2026-03-26" }, "genre": "preprint", "id": "arxiv:2603.25864", "issued": { "date-parts": [ [ 2026, 3, 26 ] ] }, "note": "First published: 2026-03-26; Recorded arXiv version: v1; Recorded version updated: 2026-03-26T19:37:53Z.", "title": "GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.26266v3", "archive": "arXiv", "archive_location": "2603.26266", "author": [ { "literal": "Rui Xie" }, { "literal": "Zhi Gao" }, { "literal": "Chenrui Shi" }, { "literal": "Zirui Shang" }, { "literal": "Lu Chen" }, { "literal": "Qing Li" } ], "citation-key": "arxiv_2603_26266", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b388086aeb8ac47e386099e5cd68cb89bb03978ee7d5897950181035d0abb723", "submitted_at": "2026-03-27T10:33:08Z", "updated_at": "2026-06-30T04:47:42Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2603.26266v3" }, "canonical_source_url": "https://arxiv.org/abs/2603.26266", "catalog_id": "arxiv:2603.26266", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-27", "identifiers": { "arxiv": "2603.26266" }, "record_updated_at": "2026-06-30" }, "genre": "preprint", "id": "arxiv:2603.26266", "issued": { "date-parts": [ [ 2026, 3, 27 ] ] }, "note": "First published: 2026-03-27; Recorded arXiv version: v3; Recorded version updated: 2026-06-30T04:47:42Z.", "title": "GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2603.28069v1", "archive": "arXiv", "archive_location": "2603.28069", "author": [ { "literal": "Christopher Clark" }, { "literal": "Yue Yang" }, { "literal": "Jae Sung Park" }, { "literal": "Zixian Ma" }, { "literal": "Jieyu Zhang" }, { "literal": "Rohun Tripathi" }, { "literal": "Mohammadreza Salehi" }, { "literal": "Sangho Lee" }, { "literal": "Taira Anderson" }, { "literal": "Winson Han" }, { "literal": "Ranjay Krishna" } ], "citation-key": "arxiv_2603_28069", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7fe857c9f7e7819a9c2f99448f77bbeae15ae4e2ac8ad308000f3d217b0177fc", "submitted_at": "2026-03-30T06:15:06Z", "updated_at": "2026-03-30T06:15:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.28069v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.28069", "catalog_id": "arxiv:2603.28069", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-03-30", "identifiers": { "arxiv": "2603.28069" }, "record_updated_at": "2026-03-30" }, "genre": "preprint", "id": "arxiv:2603.28069", "issued": { "date-parts": [ [ 2026, 3, 30 ] ] }, "note": "First published: 2026-03-30; Recorded arXiv version: v1; Recorded version updated: 2026-03-30T06:15:06Z.", "title": "MolmoPoint: Better Pointing for VLMs with Grounding Tokens", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.25380v2", "archive": "arXiv", "archive_location": "2604.25380", "author": [ { "literal": "Enqi Liu" }, { "literal": "Liyuan Pan" }, { "literal": "Zhi Gao" }, { "literal": "Yan Yang" }, { "literal": "Chenrui Shi" }, { "literal": "Yang Liu" }, { "literal": "Jingrong Wu" }, { "literal": "Qing Li" } ], "citation-key": "arxiv_2604_25380", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "54b49f54319922268ba880a1c1e8a27ffa7597e228b18be04caa1a6952a6456a", "submitted_at": "2026-04-28T08:43:58Z", "updated_at": "2026-05-08T04:29:20Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2604.25380v2" }, "canonical_source_url": "https://arxiv.org/abs/2604.25380", "catalog_id": "arxiv:2604.25380", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-28", "identifiers": { "arxiv": "2604.25380" }, "record_updated_at": "2026-05-08" }, "genre": "preprint", "id": "arxiv:2604.25380", "issued": { "date-parts": [ [ 2026, 4, 28 ] ] }, "note": "First published: 2026-04-28; Recorded arXiv version: v2; Recorded version updated: 2026-05-08T04:29:20Z.", "title": "Benchmarking and Improving GUI Agents in High-Dynamic Environments", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2604.26148v3", "archive": "arXiv", "archive_location": "2604.26148", "author": [ { "literal": "Chen Liang" }, { "literal": "Xirui Jiang" }, { "literal": "Naihao Deng" }, { "literal": "Eytan Adar" }, { "literal": "Anhong Guo" } ], "citation-key": "arxiv_2604_26148", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5b572e37eefab40a6a21fa4e4589324380ad9f66873a4da5746fc0f46aaeb1f6", "submitted_at": "2026-04-28T22:15:06Z", "updated_at": "2026-08-11T15:48:53Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2604.26148v3" }, "canonical_source_url": "https://arxiv.org/abs/2604.26148", "catalog_id": "arxiv:2604.26148", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-28", "identifiers": { "arxiv": "2604.26148" }, "record_updated_at": "2026-08-11" }, "genre": "preprint", "id": "arxiv:2604.26148", "issued": { "date-parts": [ [ 2026, 4, 28 ] ] }, "note": "First published: 2026-04-28; Recorded arXiv version: v3; Recorded version updated: 2026-08-11T15:48:53Z.", "title": "Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2605.10966v1", "archive": "arXiv", "archive_location": "2605.10966", "author": [ { "literal": "Chiyeong Heo" }, { "literal": "Jaechang Kim" }, { "literal": "Junhyuk Kwon" }, { "literal": "Hoyoung Kim" }, { "literal": "Dongmin Park" }, { "literal": "Jonghyun Lee" }, { "literal": "Jungseul Ok" } ], "citation-key": "arxiv_2605_10966", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0bd75e6bf9d5a8185a2204cdd99d42f9d96c102f7297abcadb9f8425e9246349", "submitted_at": "2026-05-08T10:57:19Z", "updated_at": "2026-05-08T10:57:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.10966v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.10966", "catalog_id": "arxiv:2605.10966", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-05-08", "identifiers": { "arxiv": "2605.10966" }, "record_updated_at": "2026-05-08" }, "genre": "preprint", "id": "arxiv:2605.10966", "issued": { "date-parts": [ [ 2026, 5, 8 ] ] }, "note": "First published: 2026-05-08; Recorded arXiv version: v1; Recorded version updated: 2026-05-08T10:57:19Z.", "title": "MMTB: Evaluating Terminal Agents on Multimedia-File Tasks", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.18758v2", "archive": "arXiv", "archive_location": "2605.18758", "author": [ { "literal": "Felix Henry" }, { "literal": "Lihan Lin" }, { "literal": "Jiangyou Zhu" }, { "literal": "Yangfan" }, { "literal": "Bingqian Zhang" }, { "literal": "Min Chen" }, { "literal": "Shiyu Huang" } ], "citation-key": "arxiv_2605_18758", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "99e8e0039ec99ef8f6a6ef3900cb74a62ddd5ae4f8df30629110969290028e6a", "submitted_at": "2026-04-03T08:57:06Z", "updated_at": "2026-09-28T02:42:06Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.18758v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.18758", "catalog_id": "arxiv:2605.18758", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-03", "identifiers": { "arxiv": "2605.18758" }, "record_updated_at": "2026-09-28" }, "genre": "preprint", "id": "arxiv:2605.18758", "issued": { "date-parts": [ [ 2026, 4, 3 ] ] }, "note": "First published: 2026-04-03; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T02:42:06Z.", "title": "OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2606.04701v1", "archive": "arXiv", "archive_location": "2606.04701", "author": [ { "literal": "Jiashu Yao" }, { "literal": "Heyan Huang" }, { "literal": "Daiqing Wu" }, { "literal": "Wangke Chen" }, { "literal": "Huaxi Ai" }, { "literal": "Haoyu Wen" }, { "literal": "Zeming Liu" }, { "literal": "Yuhang Guo" } ], "citation-key": "arxiv_2606_04701", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4d5a90333c4f6be0b8d203a2f5938f7e7eefcb09fbe7ea47b85eba8c7c1c422a", "submitted_at": "2026-06-03T10:25:46Z", "updated_at": "2026-06-03T10:25:46Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.04701v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.04701", "catalog_id": "arxiv:2606.04701", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-03", "identifiers": { "arxiv": "2606.04701" }, "record_updated_at": "2026-06-03" }, "genre": "preprint", "id": "arxiv:2606.04701", "issued": { "date-parts": [ [ 2026, 6, 3 ] ] }, "note": "First published: 2026-06-03; Recorded arXiv version: v1; Recorded version updated: 2026-06-03T10:25:46Z.", "title": "Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.29472v1", "archive": "arXiv", "archive_location": "2606.29472", "author": [ { "literal": "Bojie Li" }, { "literal": "Noah Shi" } ], "citation-key": "arxiv_2606_29472", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "54de4e93f4f3e39d904b4661a193765e02c29f8ec7787264aee5616579c32210", "submitted_at": "2026-06-28T15:59:31Z", "updated_at": "2026-06-28T15:59:31Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.29472v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.29472", "catalog_id": "arxiv:2606.29472", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-28", "identifiers": { "arxiv": "2606.29472" }, "record_updated_at": "2026-06-28" }, "genre": "preprint", "id": "arxiv:2606.29472", "issued": { "date-parts": [ [ 2026, 6, 28 ] ] }, "note": "First published: 2026-06-28; Recorded arXiv version: v1; Recorded version updated: 2026-06-28T15:59:31Z.", "title": "Agent-Computer Observation Interfaces Enable Dynamic Computer Use", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.31980v2", "archive": "arXiv", "archive_location": "2606.31980", "author": [ { "literal": "Meng Chen" }, { "literal": "Anya Ji" }, { "literal": "Tsung-Han Wu" }, { "literal": "Tobias Maringgele" }, { "literal": "David M. Chan" }, { "literal": "Alane Suhr" }, { "literal": "Amy Pavel" } ], "citation-key": "arxiv_2606_31980", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a0a3e641e0a71051f5fbd20f57af3db06f2b65c61025e78adcdd122f773d034b", "submitted_at": "2026-06-30T17:18:47Z", "updated_at": "2026-09-01T04:17:49Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.31980v2" }, "canonical_source_url": "https://arxiv.org/abs/2606.31980", "catalog_id": "arxiv:2606.31980", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-06-30", "identifiers": { "arxiv": "2606.31980" }, "record_updated_at": "2026-09-01" }, "genre": "preprint", "id": "arxiv:2606.31980", "issued": { "date-parts": [ [ 2026, 6, 30 ] ] }, "note": "First published: 2026-06-30; Recorded arXiv version: v2; Recorded version updated: 2026-09-01T04:17:49Z.", "title": "DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2609.27461v1", "archive": "arXiv", "archive_location": "2609.27461", "author": [ { "literal": "Zeyu Zhang" }, { "literal": "Dingyi Rong" }, { "literal": "Zijian Chen" }, { "literal": "Zicheng Zhang" }, { "literal": "Xiongkuo Min" }, { "literal": "Guangtao Zhai" } ], "citation-key": "arxiv_2609_27461", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3a89489bb1ff3001a1d806c3eefd8a6aa19503d1dfbe0265b916766119f96ec2", "submitted_at": "2026-09-23T07:27:23Z", "updated_at": "2026-09-23T07:27:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.27461v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.27461", "catalog_id": "arxiv:2609.27461", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-23", "identifiers": { "arxiv": "2609.27461" }, "record_updated_at": "2026-09-23" }, "genre": "preprint", "id": "arxiv:2609.27461", "issued": { "date-parts": [ [ 2026, 9, 23 ] ] }, "note": "First published: 2026-09-23; Recorded arXiv version: v1; Recorded version updated: 2026-09-23T07:27:23Z.", "title": "Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents", "type": "article", "version": "1" } ]