[ { "DOI": "10.18653/v1/2020.acl-main.729", "URL": "https://aclanthology.org/2020.acl-main.729/", "author": [ { "literal": "Yang Li" }, { "literal": "Jiacong He" }, { "literal": "Xin Zhou" }, { "literal": "Yuan Zhang" }, { "literal": "Jason Baldridge" } ], "citation-key": "arxiv_2005_03776_publication", "container-title": "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3af7b45455ffbd616e8cdf5612b19275ecb7bf07b1065af9f5b724ae19e96fb4", "submitted_at": "2020-05-07T21:41:40Z", "updated_at": "2020-06-05T02:11:56Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2005.03776v2" }, "canonical_source_url": "https://arxiv.org/abs/2005.03776", "catalog_id": "arxiv:2005.03776", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2020-05-07", "identifiers": { "arxiv": "2005.03776" }, "publication": { "authors": [ "Yang Li", "Jiacong He", "Xin Zhou", "Yuan Zhang", "Jason Baldridge" ], "date_basis": "Explicit publisher metadata: 2020/7; precision=month.", "date_parts": [ 2020, 7 ], "doi": "10.18653/v1/2020.acl-main.729", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2020.acl-main.729/" ], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "8198-8210", "pdf_url": "https://aclanthology.org/2020.acl-main.729.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Mapping Natural Language Instructions to Mobile UI Action Sequences", "type": "conference-paper", "url": "https://aclanthology.org/2020.acl-main.729/", "venue": "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", "volume": null }, "record_updated_at": "2020-06-05" }, "id": "arxiv:2005.03776:publication", "issued": { "date-parts": [ [ 2020, 7 ] ] }, "note": "Publication date: 2020-07.", "page": "8198-8210", "publisher": "Association for Computational Linguistics", "title": "Mapping Natural Language Instructions to Mobile UI Action Sequences", "type": "paper-conference" }, { "DOI": "10.18653/v1/2020.emnlp-main.443", "URL": "https://aclanthology.org/2020.emnlp-main.443/", "author": [ { "literal": "Yang Li" }, { "literal": "Gang Li" }, { "literal": "Luheng He" }, { "literal": "Jingjie Zheng" }, { "literal": "Hong Li" }, { "literal": "Zhiwei Guan" } ], "citation-key": "arxiv_2010_04295_publication", "container-title": "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "68af0a0a4b605d0c968e8913232fde16e3eadf6361099e8fc3d015dcdb26302b", "submitted_at": "2020-10-08T22:56:03Z", "updated_at": "2020-10-08T22:56:03Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2010.04295v1" }, "canonical_source_url": "https://arxiv.org/abs/2010.04295", "catalog_id": "arxiv:2010.04295", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2020-10-08", "identifiers": { "arxiv": "2010.04295" }, "publication": { "authors": [ "Yang Li", "Gang Li", "Luheng He", "Jingjie Zheng", "Hong Li", "Zhiwei Guan" ], "date_basis": "Explicit publisher metadata: 2020/11; precision=month.", "date_parts": [ 2020, 11 ], "doi": "10.18653/v1/2020.emnlp-main.443", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2020.emnlp-main.443/" ], "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 retained arXiv abstract reports 162,859 phrases; the ACL abstract reports 162,860. This publication proposal does not overwrite the arXiv annotation or assert a unified dataset count. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "5495-5510", "pdf_url": "https://aclanthology.org/2020.emnlp-main.443.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements", "type": "conference-paper", "url": "https://aclanthology.org/2020.emnlp-main.443/", "venue": "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)", "volume": null }, "record_updated_at": "2020-10-08" }, "id": "arxiv:2010.04295:publication", "issued": { "date-parts": [ [ 2020, 11 ] ] }, "note": "Publication date: 2020-11.", "page": "5495-5510", "publisher": "Association for Computational Linguistics", "title": "Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements", "type": "paper-conference" }, { "URL": "https://proceedings.mlr.press/v162/humphreys22a.html", "author": [ { "literal": "Peter Humphreys" }, { "literal": "David Raposo" }, { "literal": "Toby Pohlen" }, { "literal": "Gregory Thornton" }, { "literal": "Rachita Chhaparia" }, { "literal": "Alistair Muldal" }, { "literal": "Josh Abramson" }, { "literal": "Petko Georgiev" }, { "literal": "Adam Santoro" }, { "literal": "Timothy Lillicrap" } ], "citation-key": "arxiv_2202_08137_publication", "collection-title": "Proceedings of Machine Learning Research", "container-title": "Proceedings of the 39th International Conference on Machine Learning", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "94129847ac85f4a8aeab74907cc68a31c435b078ab950695d9328b6c3896b46d", "submitted_at": "2022-02-16T15:23:46Z", "updated_at": "2022-11-11T13:45:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2202.08137v2" }, "canonical_source_url": "https://arxiv.org/abs/2202.08137", "catalog_id": "arxiv:2202.08137", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2022-02-16", "identifiers": { "arxiv": "2202.08137" }, "publication": { "authors": [ "Peter Humphreys", "David Raposo", "Toby Pohlen", "Gregory Thornton", "Rachita Chhaparia", "Alistair Muldal", "Josh Abramson", "Petko Georgiev", "Adam Santoro", "Timothy Lillicrap" ], "date_basis": "Explicit publisher metadata: 2022/06/28; precision=day.", "date_parts": [ 2022, 6, 28 ], "doi": null, "event_dates": "17--23 Jul 2022", "evidence_urls": [ "https://proceedings.mlr.press/v162/humphreys22a.html", "https://proceedings.mlr.press/v162/humphreys22a/humphreys22a.pdf" ], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The formal ICML PDF lists 10 authors beginning Peter Humphreys and uses Toby Pohlen. The landing lists Peter C Humphreys and Tobias Pohlen. The retained arXiv snapshot lists 11 authors, including Alex Goldin. These are preserved as distinct version-specific author lists; the publication field uses only the formal PDF list. The publisher issue date comes from citation_publication_date; the conference date range is retained separately and does not replace it. Publisher issue date is 2022-06-28; the July 17–23 conference range is an event date, not a substitute publication day. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "9466-9482", "pdf_url": "https://proceedings.mlr.press/v162/humphreys22a/humphreys22a.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "A Data-Driven Approach for Learning to Control Computers", "type": "conference-paper", "url": "https://proceedings.mlr.press/v162/humphreys22a.html", "venue": "Proceedings of the 39th International Conference on Machine Learning", "volume": "162" }, "record_updated_at": "2022-11-11" }, "id": "arxiv:2202.08137:publication", "issued": { "date-parts": [ [ 2022, 6, 28 ] ] }, "note": "Publication date: 2022-06-28.", "page": "9466-9482", "publisher": "PMLR", "title": "A Data-Driven Approach for Learning to Control Computers", "type": "paper-conference", "volume": "162" }, { "URL": "https://proceedings.iclr.cc/paper_files/paper/2024/hash/7ef7d8359036afd8c2378d82c21058a4-Abstract-Conference.html", "author": [ { "literal": "Hiroki Furuta" }, { "literal": "Kuang-Huei Lee" }, { "literal": "Ofir Nachum" }, { "literal": "Yutaka Matsuo" }, { "literal": "Aleksandra Faust" }, { "literal": "Shixiang Shane Gu" }, { "literal": "Izzeddin Gur" } ], "citation-key": "arxiv_2305_11854_publication", "container-title": "International Conference on Learning Representations", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ac0ea5a462890317ea29ade32c879d016181afbe5962e2d28cc175e251df41e6", "submitted_at": "2023-05-19T17:44:34Z", "updated_at": "2024-02-25T16:21:00Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2305.11854v4" }, "canonical_source_url": "https://arxiv.org/abs/2305.11854", "catalog_id": "arxiv:2305.11854", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2023-05-19", "identifiers": { "arxiv": "2305.11854" }, "publication": { "authors": [ "Hiroki Furuta", "Kuang-Huei Lee", "Ofir Nachum", "Yutaka Matsuo", "Aleksandra Faust", "Shixiang Shane Gu", "Izzeddin Gur" ], "date_basis": "Explicit publisher metadata: 2024-05-31; precision=day.", "date_parts": [ 2024, 5, 31 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://proceedings.iclr.cc/paper_files/paper/2024/hash/7ef7d8359036afd8c2378d82c21058a4-Abstract-Conference.html", "https://proceedings.iclr.cc/paper_files/paper/2024/file/7ef7d8359036afd8c2378d82c21058a4-Paper-Conference.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 ICLR landing shortens Shixiang Shane Gu to Shixiang Gu. Publication authors use the full PDF title-page form. Volume 2024 and pages 29528–29558 are explicit publisher citation metadata, not values inferred from the event year or PDF page count. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "29528-29558", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2024/file/7ef7d8359036afd8c2378d82c21058a4-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Multimodal Web Navigation with Instruction-Finetuned Foundation Models", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2024/hash/7ef7d8359036afd8c2378d82c21058a4-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2024" }, "record_updated_at": "2024-02-25" }, "id": "arxiv:2305.11854:publication", "issued": { "date-parts": [ [ 2024, 5, 31 ] ] }, "note": "Publication date: 2024-05-31.", "page": "29528-29558", "title": "Multimodal Web Navigation with Instruction-Finetuned Foundation Models", "type": "paper-conference", "volume": "2024" }, { "DOI": "10.52202/075280-1490", "URL": "https://papers.nips.cc/paper_files/paper/2023/hash/6c52a8a4fadc9129c6e1d1745f2dfd0f-Abstract-Conference.html", "author": [ { "literal": "Peter Shaw" }, { "literal": "Mandar Joshi" }, { "literal": "James Cohan" }, { "literal": "Jonathan Berant" }, { "literal": "Panupong Pasupat" }, { "literal": "Hexiang Hu" }, { "literal": "Urvashi Khandelwal" }, { "literal": "Kenton Lee" }, { "literal": "Kristina Toutanova" } ], "citation-key": "arxiv_2306_00245_publication", "container-title": "Advances in Neural Information Processing Systems", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d06f7480695f45546b62b5b8c3d8c174ca52936e158d46e626689d0918711417", "submitted_at": "2023-05-31T23:39:18Z", "updated_at": "2023-12-06T23:46:36Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2306.00245v2" }, "canonical_source_url": "https://arxiv.org/abs/2306.00245", "catalog_id": "arxiv:2306.00245", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2023-05-31", "identifiers": { "arxiv": "2306.00245" }, "publication": { "authors": [ "Peter Shaw", "Mandar Joshi", "James Cohan", "Jonathan Berant", "Panupong Pasupat", "Hexiang Hu", "Urvashi Khandelwal", "Kenton Lee", "Kristina Toutanova" ], "date_basis": "Explicit publisher metadata: 2023-12-15; precision=day.", "date_parts": [ 2023, 12, 15 ], "doi": "10.52202/075280-1490", "event_dates": null, "evidence_urls": [ "https://papers.nips.cc/paper_files/paper/2023/hash/6c52a8a4fadc9129c6e1d1745f2dfd0f-Abstract-Conference.html", "https://proceedings.neurips.cc/paper_files/paper/2023/file/6c52a8a4fadc9129c6e1d1745f2dfd0f-Paper-Conference.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 NeurIPS landing metadata adds the initial N to Kristina Toutanova; the formal paper title page does not. Publication authors use the PDF. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "34354-34370", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2023/file/6c52a8a4fadc9129c6e1d1745f2dfd0f-Paper-Conference.pdf", "publisher": null, "series": null, "title": "From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces", "type": "conference-paper", "url": "https://papers.nips.cc/paper_files/paper/2023/hash/6c52a8a4fadc9129c6e1d1745f2dfd0f-Abstract-Conference.html", "venue": "Advances in Neural Information Processing Systems", "volume": "36" }, "record_updated_at": "2023-12-06" }, "id": "arxiv:2306.00245:publication", "issued": { "date-parts": [ [ 2023, 12, 15 ] ] }, "note": "Publication date: 2023-12-15.", "page": "34354-34370", "title": "From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces", "type": "paper-conference", "volume": "36" }, { "DOI": "10.52202/075280-2609", "URL": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html", "author": [ { "literal": "Christopher Rawles" }, { "literal": "Alice Li" }, { "literal": "Daniel Rodriguez" }, { "literal": "Oriana Riva" }, { "literal": "Timothy Lillicrap" } ], "citation-key": "arxiv_2307_10088_publication", "container-title": "Advances in Neural Information Processing Systems", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "def4616f7cb13fe839e500c4b3171eafbe37b155b5d14301137806d6a5cde939", "submitted_at": "2023-07-19T15:57:24Z", "updated_at": "2023-10-27T14:24:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2307.10088v2" }, "canonical_source_url": "https://arxiv.org/abs/2307.10088", "catalog_id": "arxiv:2307.10088", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2023-07-19", "identifiers": { "arxiv": "2307.10088" }, "publication": { "authors": [ "Christopher Rawles", "Alice Li", "Daniel Rodriguez", "Oriana Riva", "Timothy Lillicrap" ], "date_basis": "Explicit publisher citation_publication_date: 2023-12-15. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2023, 12, 15 ], "doi": "10.52202/075280-2609", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "59708-59728", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2023/file/bbbb6308b402fe909c39dd29950c32e0-Paper-Datasets_and_Benchmarks.pdf", "publisher": null, "series": null, "title": "AndroidInTheWild: A Large-Scale Dataset For Android Device Control", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html", "venue": "Advances in Neural Information Processing Systems", "volume": "36" }, "record_updated_at": "2023-10-27" }, "id": "arxiv:2307.10088:publication", "issued": { "date-parts": [ [ 2023, 12, 15 ] ] }, "note": "Publication date: 2023-12-15.", "page": "59708-59728", "title": "AndroidInTheWild: A Large-Scale Dataset For Android Device Control", "type": "paper-conference", "volume": "36" }, { "DOI": "10.18653/v1/2024.findings-acl.186", "URL": "https://aclanthology.org/2024.findings-acl.186/", "author": [ { "literal": "Zhuosheng Zhang" }, { "literal": "Aston Zhang" } ], "citation-key": "arxiv_2309_11436_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2024", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6d9cff1ece6115e87b7a9032f5720deb49694fbf570bea1f152018c4fa80d981", "submitted_at": "2023-09-20T16:12:32Z", "updated_at": "2024-06-07T04:52:29Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2309.11436v4" }, "canonical_source_url": "https://arxiv.org/abs/2309.11436", "catalog_id": "arxiv:2309.11436", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2023-09-20", "identifiers": { "arxiv": "2309.11436" }, "publication": { "authors": [ "Zhuosheng Zhang", "Aston Zhang" ], "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 8 ], "doi": "10.18653/v1/2024.findings-acl.186", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.findings-acl.186/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "3132-3149", "pdf_url": "https://aclanthology.org/2024.findings-acl.186.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "You Only Look at Screens: Multimodal Chain-of-Action Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-acl.186/", "venue": "Findings of the Association for Computational Linguistics: ACL 2024", "volume": null }, "record_updated_at": "2024-06-07" }, "id": "arxiv:2309.11436:publication", "issued": { "date-parts": [ [ 2024, 8 ] ] }, "note": "Publication date: 2024-08.", "page": "3132-3149", "publisher": "Association for Computational Linguistics", "title": "You Only Look at Screens: Multimodal Chain-of-Action Agents", "type": "paper-conference" }, { "URL": "https://openaccess.thecvf.com/content/CVPR2024/html/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.html", "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": "Yuxiao Dong" }, { "literal": "Ming Ding" }, { "literal": "Jie Tang" } ], "citation-key": "arxiv_2312_08914_publication", "container-title": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2312.08914", "catalog_id": "arxiv:2312.08914", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2023-12-14", "identifiers": { "arxiv": "2312.08914" }, "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 }, "record_updated_at": "2024-12-27" }, "id": "arxiv:2312.08914:publication", "issued": { "date-parts": [ [ 2024, 6 ] ] }, "note": "Publication date: 2024-06.", "page": "14281-14290", "title": "CogAgent: A Visual Language Model for GUI Agents", "type": "paper-conference" }, { "URL": "https://proceedings.mlr.press/v235/zheng24e.html", "author": [ { "literal": "Boyuan Zheng" }, { "literal": "Boyu Gou" }, { "literal": "Jihyung Kil" }, { "literal": "Huan Sun" }, { "literal": "Yu Su" } ], "citation-key": "arxiv_2401_01614_publication", "collection-title": "Proceedings of Machine Learning Research", "container-title": "Proceedings of the 41st International Conference on Machine Learning", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2401.01614", "catalog_id": "arxiv:2401.01614", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-01-03", "identifiers": { "arxiv": "2401.01614" }, "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" }, "record_updated_at": "2024-03-12" }, "id": "arxiv:2401.01614:publication", "issued": { "date-parts": [ [ 2024, 7, 8 ] ] }, "note": "Publication date: 2024-07-08.", "page": "61349-61385", "publisher": "PMLR", "title": "GPT-4V(ision) is a Generalist Web Agent, if Grounded", "type": "paper-conference", "volume": "235" }, { "DOI": "10.18653/v1/2024.acl-long.505", "URL": "https://aclanthology.org/2024.acl-long.505/", "author": [ { "literal": "Kanzhi Cheng" }, { "literal": "Qiushi Sun" }, { "literal": "Yougang Chu" }, { "literal": "Fangzhi Xu" }, { "literal": "Yantao Li" }, { "literal": "Jianbing Zhang" }, { "literal": "Zhiyong Wu" } ], "citation-key": "arxiv_2401_10935_publication", "container-title": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c92ec9323eec9362aa07984f9fb1cbfbe98ecae426a9f8adc9d436328a87aed3", "submitted_at": "2024-01-17T08:10:35Z", "updated_at": "2024-02-23T04:36:51Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2401.10935v2" }, "canonical_source_url": "https://arxiv.org/abs/2401.10935", "catalog_id": "arxiv:2401.10935", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-01-17", "identifiers": { "arxiv": "2401.10935" }, "publication": { "authors": [ "Kanzhi Cheng", "Qiushi Sun", "Yougang Chu", "Fangzhi Xu", "Yantao Li", "Jianbing Zhang", "Zhiyong Wu" ], "date_basis": "Explicit publisher metadata: 2024/8; precision=month.", "date_parts": [ 2024, 8 ], "doi": "10.18653/v1/2024.acl-long.505", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.acl-long.505/", "https://aclanthology.org/2024.acl-long.505.pdf" ], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The ACL landing metadata spells the fifth author Li YanTao. The formal PDF title page spells Yantao Li; the publication author field uses the PDF. The retained arXiv author list is untouched. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "9313-9332", "pdf_url": "https://aclanthology.org/2024.acl-long.505.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.acl-long.505/", "venue": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2024-02-23" }, "id": "arxiv:2401.10935:publication", "issued": { "date-parts": [ [ 2024, 8 ] ] }, "note": "Publication date: 2024-08.", "page": "9313-9332", "publisher": "Association for Computational Linguistics", "title": "SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents", "type": "paper-conference" }, { "DOI": "10.18653/v1/2024.acl-long.50", "URL": "https://aclanthology.org/2024.acl-long.50/", "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" } ], "citation-key": "arxiv_2401_13649_publication", "container-title": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2401.13649", "catalog_id": "arxiv:2401.13649", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-01-24", "identifiers": { "arxiv": "2401.13649" }, "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 }, "record_updated_at": "2024-06-06" }, "id": "arxiv:2401.13649:publication", "issued": { "date-parts": [ [ 2024, 8 ] ] }, "note": "Publication date: 2024-08.", "page": "881-905", "publisher": "Association for Computational Linguistics", "title": "VisualWebArena: Evaluating Multimodal Agents on Realistic Visually Grounded Web Tasks", "type": "paper-conference" }, { "DOI": "10.18653/v1/2024.acl-long.371", "URL": "https://aclanthology.org/2024.acl-long.371/", "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" } ], "citation-key": "arxiv_2401_13919_publication", "container-title": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2401.13919", "catalog_id": "arxiv:2401.13919", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-01-25", "identifiers": { "arxiv": "2401.13919" }, "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 }, "record_updated_at": "2024-06-06" }, "id": "arxiv:2401.13919:publication", "issued": { "date-parts": [ [ 2024, 8 ] ] }, "note": "Publication date: 2024-08.", "page": "6864-6890", "publisher": "Association for Computational Linguistics", "title": "WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models", "type": "paper-conference" }, { "URL": "https://proceedings.mlr.press/v235/lu24e.html", "author": [ { "literal": "Xing Han Lù" }, { "literal": "Zdeněk Kasner" }, { "literal": "Siva Reddy" } ], "citation-key": "arxiv_2402_05930_publication", "collection-title": "Proceedings of Machine Learning Research", "container-title": "Proceedings of the 41st International Conference on Machine Learning", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6a7c1a1f260f9287e8999525e1adc5534a70f7b96271d469973fceee1ac23609", "submitted_at": "2024-02-08T18:58:02Z", "updated_at": "2024-09-10T22:22:43Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2402.05930v2" }, "canonical_source_url": "https://arxiv.org/abs/2402.05930", "catalog_id": "arxiv:2402.05930", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-02-08", "identifiers": { "arxiv": "2402.05930" }, "publication": { "authors": [ "Xing Han Lù", "Zdeněk Kasner", "Siva Reddy" ], "date_basis": "Explicit publisher metadata: 2024/07/08; precision=day.", "date_parts": [ 2024, 7, 8 ], "doi": null, "event_dates": "21--27 Jul 2024", "evidence_urls": [ "https://proceedings.mlr.press/v235/lu24e.html", "https://raw.githubusercontent.com/mlresearch/v235/main/assets/lu24e/lu24e.pdf" ], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The PMLR landing renders Xing Han Lu; the paper title page has Xing Han Lù. Publication authors use the PDF. The publisher issue date comes from citation_publication_date; the conference date range is retained separately and does not replace it. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "33007-33056", "pdf_url": "https://raw.githubusercontent.com/mlresearch/v235/main/assets/lu24e/lu24e.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "WebLINX: Real-World Website Navigation with Multi-Turn Dialogue", "type": "conference-paper", "url": "https://proceedings.mlr.press/v235/lu24e.html", "venue": "Proceedings of the 41st International Conference on Machine Learning", "volume": "235" }, "record_updated_at": "2024-09-10" }, "id": "arxiv:2402.05930:publication", "issued": { "date-parts": [ [ 2024, 7, 8 ] ] }, "note": "Publication date: 2024-07-08.", "page": "33007-33056", "publisher": "PMLR", "title": "WebLINX: Real-World Website Navigation with Multi-Turn Dialogue", "type": "paper-conference", "volume": "235" }, { "DOI": "10.18653/v1/2025.naacl-long.26", "URL": "https://aclanthology.org/2025.naacl-long.26/", "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" } ], "citation-key": "arxiv_2402_07939_publication", "container-title": "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)", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2402.07939", "catalog_id": "arxiv:2402.07939", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-02-08", "identifiers": { "arxiv": "2402.07939" }, "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 }, "record_updated_at": "2024-05-23" }, "id": "arxiv:2402.07939:publication", "issued": { "date-parts": [ [ 2025, 4 ] ] }, "note": "Publication date: 2025-04.", "page": "597-622", "publisher": "Association for Computational Linguistics", "title": "UFO: A UI-Focused Agent for Windows OS Interaction", "type": "paper-conference" }, { "DOI": "10.18653/v1/2024.findings-acl.539", "URL": "https://aclanthology.org/2024.findings-acl.539", "author": [ { "literal": "Xinbei Ma" }, { "literal": "Zhuosheng Zhang" }, { "literal": "Hai Zhao (赵海)" } ], "citation-key": "arxiv_2402_11941_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2024", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "98930b10832d8169bdc60620f882b4b8f753440979c8e9a8de167b12d38d7060", "submitted_at": "2024-02-19T08:29:03Z", "updated_at": "2024-06-02T13:25:05Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2402.11941v3" }, "canonical_source_url": "https://arxiv.org/abs/2402.11941", "catalog_id": "arxiv:2402.11941", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-02-19", "identifiers": { "arxiv": "2402.11941" }, "publication": { "authors": [ "Xinbei Ma", "Zhuosheng Zhang", "Hai Zhao (赵海)" ], "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 8 ], "doi": "10.18653/v1/2024.findings-acl.539", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.findings-acl.539" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "9097-9110", "pdf_url": "https://aclanthology.org/2024.findings-acl.539.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-acl.539", "venue": "Findings of the Association for Computational Linguistics: ACL 2024", "volume": null }, "record_updated_at": "2024-06-02" }, "id": "arxiv:2402.11941:publication", "issued": { "date-parts": [ [ 2024, 8 ] ] }, "note": "Publication date: 2024-08.", "page": "9097-9110", "publisher": "Association for Computational Linguistics", "title": "CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation", "type": "paper-conference" }, { "DOI": "10.18653/v1/2024.acl-long.477", "URL": "https://aclanthology.org/2024.acl-long.477/", "author": [ { "literal": "Yang Deng" }, { "literal": "Xuan Zhang" }, { "literal": "Wenxuan Zhang" }, { "literal": "Yifei Yuan" }, { "literal": "See Kiong Ng" }, { "literal": "Tat-Seng Chua" } ], "citation-key": "arxiv_2402_15057_publication", "container-title": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5e4b233e423e9043b6d615c7b185a1eb0d47f646590e4fb9fd43ca156a1a1b16", "submitted_at": "2024-02-23T02:18:12Z", "updated_at": "2024-02-23T02:18:12Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2402.15057v1" }, "canonical_source_url": "https://arxiv.org/abs/2402.15057", "catalog_id": "arxiv:2402.15057", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-02-23", "identifiers": { "arxiv": "2402.15057" }, "publication": { "authors": [ "Yang Deng", "Xuan Zhang", "Wenxuan Zhang", "Yifei Yuan", "See Kiong Ng", "Tat-Seng Chua" ], "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.477", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.acl-long.477/" ], "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": "8795-8812", "pdf_url": "https://aclanthology.org/2024.acl-long.477.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "On the Multi-turn Instruction Following for Conversational Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.acl-long.477/", "venue": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2024-02-23" }, "id": "arxiv:2402.15057:publication", "issued": { "date-parts": [ [ 2024, 8 ] ] }, "note": "Publication date: 2024-08.", "page": "8795-8812", "publisher": "Association for Computational Linguistics", "title": "On the Multi-turn Instruction Following for Conversational Web Agents", "type": "paper-conference" }, { "DOI": "10.18653/v1/2024.findings-emnlp.702", "URL": "https://aclanthology.org/2024.findings-emnlp.702/", "author": [ { "literal": "Jiwen Zhang (张霁雯)" }, { "literal": "Jihao Wu" }, { "literal": "Teng Yihua" }, { "literal": "Minghui Liao" }, { "literal": "Nuo Xu" }, { "literal": "Xiao Xiao" }, { "literal": "Zhongyu Wei (魏忠钰)" }, { "literal": "Duyu Tang" } ], "citation-key": "arxiv_2403_02713_publication", "container-title": "Findings of the Association for Computational Linguistics: EMNLP 2024", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4de9e7d68aa8450cab65ecb300524e85b1d2b2a91d58fecef370deceaba64b1e", "submitted_at": "2024-03-05T07:09:35Z", "updated_at": "2024-07-13T02:12:30Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2403.02713v2" }, "canonical_source_url": "https://arxiv.org/abs/2403.02713", "catalog_id": "arxiv:2403.02713", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-03-05", "identifiers": { "arxiv": "2403.02713" }, "publication": { "authors": [ "Jiwen Zhang (张霁雯)", "Jihao Wu", "Teng Yihua", "Minghui Liao", "Nuo Xu", "Xiao Xiao", "Zhongyu Wei (魏忠钰)", "Duyu Tang" ], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 11 ], "doi": "10.18653/v1/2024.findings-emnlp.702", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.findings-emnlp.702/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "12016-12031", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.702.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Android in the Zoo: Chain-of-Action-Thought for GUI Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.702/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null }, "record_updated_at": "2024-07-13" }, "id": "arxiv:2403.02713:publication", "issued": { "date-parts": [ [ 2024, 11 ] ] }, "note": "Publication date: 2024-11.", "page": "12016-12031", "publisher": "Association for Computational Linguistics", "title": "Android in the Zoo: Chain-of-Action-Thought for GUI Agents", "type": "paper-conference" }, { "URL": "https://proceedings.mlr.press/v267/tan25h.html", "author": [ { "literal": "Weihao Tan" }, { "literal": "Wentao Zhang" }, { "literal": "Xinrun Xu" }, { "literal": "Haochong Xia" }, { "literal": "Ziluo Ding" }, { "literal": "Boyu Li" }, { "literal": "Bohan Zhou" }, { "literal": "Junpeng Yue" }, { "literal": "Jiechuan Jiang" }, { "literal": "Yewen Li" }, { "literal": "Ruyi An" }, { "literal": "Molei Qin" }, { "literal": "Chuqiao Zong" }, { "literal": "Longtao Zheng" }, { "literal": "Yujie Wu" }, { "literal": "Xiaoqiang Chai" }, { "literal": "Yifei Bi" }, { "literal": "Tianbao Xie" }, { "literal": "Pengjie Gu" }, { "literal": "Xiyun Li" }, { "literal": "Ceyao Zhang" }, { "literal": "Long Tian" }, { "literal": "Chaojie Wang" }, { "literal": "Xinrun Wang" }, { "literal": "Börje F. Karlsson" }, { "literal": "Bo An" }, { "literal": "Shuicheng Yan" }, { "literal": "Zongqing Lu" } ], "citation-key": "arxiv_2403_03186_publication", "collection-title": "Proceedings of Machine Learning Research", "container-title": "Proceedings of the 42nd International Conference on Machine Learning", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "63c68c596f1c81485e77f98beae696deca9785a5d8725ab4456ee35870e64a99", "submitted_at": "2024-03-05T18:22:29Z", "updated_at": "2024-07-02T17:23:13Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2403.03186v3" }, "canonical_source_url": "https://arxiv.org/abs/2403.03186", "catalog_id": "arxiv:2403.03186", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-03-05", "identifiers": { "arxiv": "2403.03186" }, "publication": { "authors": [ "Weihao Tan", "Wentao Zhang", "Xinrun Xu", "Haochong Xia", "Ziluo Ding", "Boyu Li", "Bohan Zhou", "Junpeng Yue", "Jiechuan Jiang", "Yewen Li", "Ruyi An", "Molei Qin", "Chuqiao Zong", "Longtao Zheng", "Yujie Wu", "Xiaoqiang Chai", "Yifei Bi", "Tianbao Xie", "Pengjie Gu", "Xiyun Li", "Ceyao Zhang", "Long Tian", "Chaojie Wang", "Xinrun Wang", "Börje F. Karlsson", "Bo An", "Shuicheng Yan", "Zongqing Lu" ], "date_basis": "Explicit publisher metadata: 2025/10/06; precision=day.", "date_parts": [ 2025, 10, 6 ], "doi": null, "event_dates": "13--19 Jul 2025", "evidence_urls": [ "https://proceedings.mlr.press/v267/tan25h.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": "58658-58725", "pdf_url": "https://raw.githubusercontent.com/mlresearch/v267/main/assets/tan25h/tan25h.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "Cradle: Empowering Foundation Agents towards General Computer Control", "type": "conference-paper", "url": "https://proceedings.mlr.press/v267/tan25h.html", "venue": "Proceedings of the 42nd International Conference on Machine Learning", "volume": "267" }, "record_updated_at": "2024-07-02" }, "id": "arxiv:2403.03186:publication", "issued": { "date-parts": [ [ 2025, 10, 6 ] ] }, "note": "Publication date: 2025-10-06.", "page": "58658-58725", "publisher": "PMLR", "title": "Cradle: Empowering Foundation Agents towards General Computer Control", "type": "paper-conference", "volume": "267" }, { "DOI": "10.18653/v1/2025.naacl-long.188", "URL": "https://aclanthology.org/2025.naacl-long.188/", "author": [ { "literal": "Kevin Xu" }, { "literal": "Yeganeh Kordi" }, { "literal": "Tanay Nayak" }, { "literal": "Adi Asija" }, { "literal": "Yizhong Wang" }, { "literal": "Kate Sanders" }, { "literal": "Adam Byerly" }, { "literal": "Jingyu Zhang" }, { "literal": "Benjamin Van Durme" }, { "literal": "Daniel Khashabi" } ], "citation-key": "arxiv_2403_11905_publication", "container-title": "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)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d82424b84ebddfeb005ffae38c130c6a9c7dae7adcdc59e2b7d001284b785573", "submitted_at": "2024-03-18T16:06:30Z", "updated_at": "2025-02-22T01:33:54Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2403.11905v4" }, "canonical_source_url": "https://arxiv.org/abs/2403.11905", "catalog_id": "arxiv:2403.11905", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-03-18", "identifiers": { "arxiv": "2403.11905" }, "publication": { "authors": [ "Kevin Xu", "Yeganeh Kordi", "Tanay Nayak", "Adi Asija", "Yizhong Wang", "Kate Sanders", "Adam Byerly", "Jingyu Zhang", "Benjamin Van Durme", "Daniel Khashabi" ], "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.188", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.naacl-long.188/" ], "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": "3694-3710", "pdf_url": "https://aclanthology.org/2025.naacl-long.188.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "TurkingBench: A Challenge Benchmark for Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-long.188/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-02-22" }, "id": "arxiv:2403.11905:publication", "issued": { "date-parts": [ [ 2025, 4 ] ] }, "note": "Publication date: 2025-04.", "page": "3694-3710", "publisher": "Association for Computational Linguistics", "title": "TurkingBench: A Challenge Benchmark for Web Agents", "type": "paper-conference" }, { "DOI": "10.52202/079017-1650", "URL": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/5d413e48f84dc61244b6be550f1cd8f5-Abstract-Datasets_and_Benchmarks_Track.html", "author": [ { "literal": "Tianbao Xie" }, { "literal": "Danyang Zhang" }, { "literal": "Jixuan Chen" }, { "literal": "Xiaochuan Li" }, { "literal": "Siheng Zhao" }, { "literal": "Ruisheng Cao" }, { "literal": "Toh J. 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" } ], "citation-key": "arxiv_2404_07972_publication", "container-title": "Advances in Neural Information Processing Systems", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2404.07972", "catalog_id": "arxiv:2404.07972", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-04-11", "identifiers": { "arxiv": "2404.07972" }, "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" }, "record_updated_at": "2024-05-30" }, "id": "arxiv:2404.07972:publication", "issued": { "date-parts": [ [ 2024, 12, 16 ] ] }, "note": "Publication date: 2024-12-16.", "page": "52040-52094", "title": "OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments", "type": "paper-conference", "volume": "37" }, { "DOI": "10.18653/v1/2025.findings-acl.703", "URL": "https://aclanthology.org/2025.findings-acl.703/", "author": [ { "literal": "Shulin Tian" }, { "literal": "Ziniu Zhang" }, { "literal": "Liang-Yu Chen" }, { "literal": "Ziwei Liu" } ], "citation-key": "arxiv_2404_09992_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2025", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "667b1f5053f3ae6ea712999932d5e9ee2f42e402cc72e713048d0790f5931976", "submitted_at": "2024-04-15T17:59:50Z", "updated_at": "2025-06-29T05:24:54Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2404.09992v2" }, "canonical_source_url": "https://arxiv.org/abs/2404.09992", "catalog_id": "arxiv:2404.09992", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-04-15", "identifiers": { "arxiv": "2404.09992" }, "publication": { "authors": [ "Shulin Tian", "Ziniu Zhang", "Liang-Yu Chen", "Ziwei Liu" ], "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.703", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.703/" ], "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": "13682-13697", "pdf_url": "https://aclanthology.org/2025.findings-acl.703.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "MMInA: Benchmarking Multihop Multimodal Internet Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.703/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2025-06-29" }, "id": "arxiv:2404.09992:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "13682-13697", "publisher": "Association for Computational Linguistics", "title": "MMInA: Benchmarking Multihop Multimodal Internet Agents", "type": "paper-conference" }, { "URL": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/01a83bc2f2732a58e6aa731e659e7101-Abstract-Conference.html", "author": [ { "literal": "Chris 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" } ], "citation-key": "arxiv_2405_14573_publication", "container-title": "International Conference on Learning Representations", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2405.14573", "catalog_id": "arxiv:2405.14573", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-05-23", "identifiers": { "arxiv": "2405.14573" }, "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" }, "record_updated_at": "2025-04-06" }, "id": "arxiv:2405.14573:publication", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "Publication date: 2025-05-01.", "page": "406-441", "title": "AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents", "type": "paper-conference", "volume": "2025" }, { "DOI": "10.52202/079017-2925", "URL": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html", "author": [ { "literal": "Wei Li" }, { "literal": "William Bishop" }, { "literal": "Alice Li" }, { "literal": "Chris Rawles" }, { "literal": "Folawiyo Campbell-Ajala" }, { "literal": "Divya Tyamagundlu" }, { "literal": "Oriana Riva" } ], "citation-key": "arxiv_2406_03679_publication", "container-title": "Advances in Neural Information Processing Systems", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6eb3209d8e2a431987fe19f01cd0818f9fb490e684d7369e7d3002dc388ff271", "submitted_at": "2024-06-06T01:49:29Z", "updated_at": "2024-11-13T16:42:22Z", "version": 6, "versioned_url": "https://arxiv.org/abs/2406.03679v6" }, "canonical_source_url": "https://arxiv.org/abs/2406.03679", "catalog_id": "arxiv:2406.03679", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-06-06", "identifiers": { "arxiv": "2406.03679" }, "publication": { "authors": [ "Wei Li", "William Bishop", "Alice Li", "Chris Rawles", "Folawiyo Campbell-Ajala", "Divya Tyamagundlu", "Oriana Riva" ], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 12, 16 ], "doi": "10.52202/079017-2925", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "92130-92154", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/a79f3ef3b445fd4659f44648f7ea8ffd-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "On the Effects of Data Scale on UI Control Agents", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "record_updated_at": "2024-11-13" }, "id": "arxiv:2406.03679:publication", "issued": { "date-parts": [ [ 2024, 12, 16 ] ] }, "note": "Publication date: 2024-12-16.", "page": "92130-92154", "title": "On the Effects of Data Scale on UI Control Agents", "type": "paper-conference", "volume": "37" }, { "DOI": "10.52202/079017-2214", "URL": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/804e757b7d7043c26701c3a313032101-Abstract-Datasets_and_Benchmarks_Track.html", "author": [ { "literal": "Kevin Q. Lin" }, { "literal": "Linjie Li" }, { "literal": "Difei Gao" }, { "literal": "Qinchen Wu" }, { "literal": "Mingyi Yan" }, { "literal": "Zhengyuan Yang" }, { "literal": "Lijuan Wang" }, { "literal": "Mike Z. Shou" } ], "citation-key": "arxiv_2406_10227_publication", "container-title": "Advances in Neural Information Processing Systems", "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": "publication", "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" }, "id": "arxiv:2406.10227:publication", "issued": { "date-parts": [ [ 2024, 12, 16 ] ] }, "note": "Publication date: 2024-12-16.", "page": "69329-69360", "title": "VideoGUI: A Benchmark for GUI Automation from Instructional Videos", "type": "paper-conference", "volume": "37" }, { "DOI": "10.52202/079017-0397", "URL": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html", "author": [ { "literal": "Hao Bai" }, { "literal": "Yifei Zhou" }, { "literal": "Mert Cemri" }, { "literal": "Jiayi Pan" }, { "literal": "Alane Suhr" }, { "literal": "Sergey Levine" }, { "literal": "Aviral Kumar" } ], "citation-key": "arxiv_2406_11896_publication", "container-title": "Advances in Neural Information Processing Systems", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2c5d4e75d6ba88574f6f033bb2c1cf44cf04149e94e017cd8a1a227e7a1c8238", "submitted_at": "2024-06-14T17:49:55Z", "updated_at": "2024-06-14T17:49:55Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2406.11896v1" }, "canonical_source_url": "https://arxiv.org/abs/2406.11896", "catalog_id": "arxiv:2406.11896", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-06-14", "identifiers": { "arxiv": "2406.11896" }, "publication": { "authors": [ "Hao Bai", "Yifei Zhou", "Mert Cemri", "Jiayi Pan", "Alane Suhr", "Sergey Levine", "Aviral Kumar" ], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 12, 16 ], "doi": "10.52202/079017-0397", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "12461-12495", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/1704ddd0bb89f159dfe609b32c889995-Paper-Conference.pdf", "publisher": null, "series": null, "title": "DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "record_updated_at": "2024-06-14" }, "id": "arxiv:2406.11896:publication", "issued": { "date-parts": [ [ 2024, 12, 16 ] ] }, "note": "Publication date: 2024-12-16.", "page": "12461-12495", "title": "DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning", "type": "paper-conference", "volume": "37" }, { "URL": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/460a1d8eac34125dad453b28d6d64446-Abstract-Conference.html", "author": [ { "literal": "Chen Wu" }, { "literal": "Rishi Shah" }, { "literal": "Jing Yu Koh" }, { "literal": "Russ Salakhutdinov" }, { "literal": "Daniel Fried" }, { "literal": "Aditi Raghunathan" } ], "citation-key": "arxiv_2406_12814_publication", "container-title": "International Conference on Learning Representations", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2406.12814", "catalog_id": "arxiv:2406.12814", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-06-18", "identifiers": { "arxiv": "2406.12814" }, "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" }, "record_updated_at": "2025-02-04" }, "id": "arxiv:2406.12814:publication", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "Publication date: 2025-05-01.", "page": "28362-28383", "title": "Dissecting Adversarial Robustness of Multimodal LM Agents", "type": "paper-conference", "volume": "2025" }, { "DOI": "10.18653/v1/2024.findings-emnlp.68", "URL": "https://aclanthology.org/2024.findings-emnlp.68/", "author": [ { "literal": "Meng Ziyang" }, { "literal": "Yu Dai" }, { "literal": "Zezheng Gong" }, { "literal": "Shaoxiong Guo" }, { "literal": "Minglong Tang" }, { "literal": "Tongquan Wei" } ], "citation-key": "arxiv_2406_14056_publication", "container-title": "Findings of the Association for Computational Linguistics: EMNLP 2024", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ea674b3aec3aee51c6f7fd4e99ad2b88394e7df43a4f3a02654d805e9a60343a", "submitted_at": "2024-06-20T07:24:43Z", "updated_at": "2024-11-04T09:31:06Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2406.14056v3" }, "canonical_source_url": "https://arxiv.org/abs/2406.14056", "catalog_id": "arxiv:2406.14056", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-06-20", "identifiers": { "arxiv": "2406.14056" }, "publication": { "authors": [ "Meng Ziyang", "Yu Dai", "Zezheng Gong", "Shaoxiong Guo", "Minglong Tang", "Tongquan Wei" ], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 11 ], "doi": "10.18653/v1/2024.findings-emnlp.68", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.findings-emnlp.68/" ], "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": "1261-1279", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.68.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "VGA: Vision GUI Assistant - Minimizing Hallucinations through Image-Centric Fine-Tuning", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.68/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null }, "record_updated_at": "2024-11-04" }, "id": "arxiv:2406.14056:publication", "issued": { "date-parts": [ [ 2024, 11 ] ] }, "note": "Publication date: 2024-11.", "page": "1261-1279", "publisher": "Association for Computational Linguistics", "title": "VGA: Vision GUI Assistant - Minimizing Hallucinations through Image-Centric Fine-Tuning", "type": "paper-conference" }, { "DOI": "10.18653/v1/2024.emnlp-main.533", "URL": "https://aclanthology.org/2024.emnlp-main.533/", "author": [ { "literal": "Yue Fan" }, { "literal": "Lei Ding" }, { "literal": "Ching-Chen Kuo" }, { "literal": "Shan Jiang" }, { "literal": "Yang Zhao" }, { "literal": "Xinze Guan" }, { "literal": "Jie Yang" }, { "literal": "Yi Zhang" }, { "literal": "Xin Eric Wang" } ], "citation-key": "arxiv_2406_19263_publication", "container-title": "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0c86d68b5c3486b099f64792d5d3290d79e25b7c82c6eb2402869b893bb22fea", "submitted_at": "2024-06-27T15:34:16Z", "updated_at": "2024-10-25T18:16:21Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2406.19263v2" }, "canonical_source_url": "https://arxiv.org/abs/2406.19263", "catalog_id": "arxiv:2406.19263", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-06-27", "identifiers": { "arxiv": "2406.19263" }, "publication": { "authors": [ "Yue Fan", "Lei Ding", "Ching-Chen Kuo", "Shan Jiang", "Yang Zhao", "Xinze Guan", "Jie Yang", "Yi Zhang", "Xin Eric Wang" ], "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.533", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.emnlp-main.533/" ], "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": "9503-9522", "pdf_url": "https://aclanthology.org/2024.emnlp-main.533.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding", "type": "conference-paper", "url": "https://aclanthology.org/2024.emnlp-main.533/", "venue": "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", "volume": null }, "record_updated_at": "2024-10-25" }, "id": "arxiv:2406.19263:publication", "issued": { "date-parts": [ [ 2024, 11 ] ] }, "note": "Publication date: 2024-11.", "page": "9503-9522", "publisher": "Association for Computational Linguistics", "title": "Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.findings-acl.1113", "URL": "https://aclanthology.org/2025.findings-acl.1113/", "author": [ { "literal": "Tianqi Xu" }, { "literal": "Linyao Chen" }, { "literal": "Dai-Jie Wu" }, { "literal": "Yanjun Chen" }, { "literal": "Zecheng Zhang" }, { "literal": "Xiang Yao" }, { "literal": "Zhiqiang Xie (谢志强)" }, { "literal": "Yongchao Chen" }, { "literal": "Shilong Liu" }, { "literal": "Bochen Qian" }, { "literal": "Anjie Yang" }, { "literal": "Zhaoxuan Jin" }, { "literal": "Jianbo Deng" }, { "literal": "Philip Torr" }, { "literal": "Bernard Ghanem" }, { "literal": "Guohao Li" } ], "citation-key": "arxiv_2407_01511_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2025", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "12e5464ea0fc62bd566f19d301b887826b7ff317cfc27c86fa0cda8d3de271d9", "submitted_at": "2024-07-01T17:55:04Z", "updated_at": "2025-07-20T13:42:07Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2407.01511v4" }, "canonical_source_url": "https://arxiv.org/abs/2407.01511", "catalog_id": "arxiv:2407.01511", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-07-01", "identifiers": { "arxiv": "2407.01511" }, "publication": { "authors": [ "Tianqi Xu", "Linyao Chen", "Dai-Jie Wu", "Yanjun Chen", "Zecheng Zhang", "Xiang Yao", "Zhiqiang Xie (谢志强)", "Yongchao Chen", "Shilong Liu", "Bochen Qian", "Anjie Yang", "Zhaoxuan Jin", "Jianbo Deng", "Philip Torr", "Bernard Ghanem", "Guohao 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.1113", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.1113/" ], "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": "21607-21647", "pdf_url": "https://aclanthology.org/2025.findings-acl.1113.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.1113/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2025-07-20" }, "id": "arxiv:2407.01511:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "21607-21647", "publisher": "Association for Computational Linguistics", "title": "CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents", "type": "paper-conference" }, { "DOI": "10.52202/079017-0195", "URL": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/0b82662b6c32e887bb252a74d8cb2d5e-Abstract-Datasets_and_Benchmarks_Track.html", "author": [ { "literal": "Léo Boisvert" }, { "literal": "Megh Thakkar" }, { "literal": "Maxime Gasse" }, { "literal": "Massimo Caccia" }, { "literal": "Thibault L. De Chezelles" }, { "literal": "Quentin Cappart" }, { "literal": "Nicolas Chapados" }, { "literal": "Alexandre Lacoste" }, { "literal": "Alexandre Drouin" } ], "citation-key": "arxiv_2407_05291_publication", "container-title": "Advances in Neural Information Processing Systems", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2407.05291", "catalog_id": "arxiv:2407.05291", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-07-07", "identifiers": { "arxiv": "2407.05291" }, "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" }, "record_updated_at": "2025-02-05" }, "id": "arxiv:2407.05291:publication", "issued": { "date-parts": [ [ 2024, 12, 16 ] ] }, "note": "Publication date: 2024-12-16.", "page": "5996-6051", "title": "WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks", "type": "paper-conference", "volume": "37" }, { "DOI": "10.52202/079017-3421", "URL": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/c2f71567cd53464161cab3336e8fc865-Abstract-Datasets_and_Benchmarks_Track.html", "author": [ { "literal": "Ruisheng Cao" }, { "literal": "Fangyu Lei" }, { "literal": "Haoyuan Wu" }, { "literal": "Jixuan Chen" }, { "literal": "Yeqiao Fu" }, { "literal": "Hongcheng Gao" }, { "literal": "Xinzhuang Xiong" }, { "literal": "Hanchong Zhang" }, { "literal": "Yuchen Mao" }, { "literal": "Wenjing Hu" }, { "literal": "Tianbao Xie" }, { "literal": "Hongshen Xu" }, { "literal": "Danyang Zhang" }, { "literal": "Sida Wang" }, { "literal": "Ruoxi Sun" }, { "literal": "Pengcheng Yin" }, { "literal": "Caiming Xiong" }, { "literal": "Ansong Ni" }, { "literal": "Qian Liu" }, { "literal": "Victor Zhong" }, { "literal": "Lu Chen" }, { "literal": "Kai Yu" }, { "literal": "Tao Yu" } ], "citation-key": "arxiv_2407_10956_publication", "container-title": "Advances in Neural Information Processing Systems", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7922a723142ac62018064fe5fc9357fb77c08e316ac4d6d6ba728f1b337df690", "submitted_at": "2024-07-15T17:54:37Z", "updated_at": "2024-07-15T17:54:37Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2407.10956v1" }, "canonical_source_url": "https://arxiv.org/abs/2407.10956", "catalog_id": "arxiv:2407.10956", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-07-15", "identifiers": { "arxiv": "2407.10956" }, "publication": { "authors": [ "Ruisheng Cao", "Fangyu Lei", "Haoyuan Wu", "Jixuan Chen", "Yeqiao Fu", "Hongcheng Gao", "Xinzhuang Xiong", "Hanchong Zhang", "Yuchen Mao", "Wenjing Hu", "Tianbao Xie", "Hongshen Xu", "Danyang Zhang", "Sida Wang", "Ruoxi Sun", "Pengcheng Yin", "Caiming Xiong", "Ansong Ni", "Qian Liu", "Victor Zhong", "Lu Chen", "Kai Yu", "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": "10.52202/079017-3421", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/c2f71567cd53464161cab3336e8fc865-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. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "107703-107744", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/c2f71567cd53464161cab3336e8fc865-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/c2f71567cd53464161cab3336e8fc865-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "record_updated_at": "2024-07-15" }, "id": "arxiv:2407.10956:publication", "issued": { "date-parts": [ [ 2024, 12, 16 ] ] }, "note": "Publication date: 2024-12-16.", "page": "107703-107744", "title": "Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?", "type": "paper-conference", "volume": "37" }, { "DOI": "10.18653/v1/2024.emnlp-main.505", "URL": "https://aclanthology.org/2024.emnlp-main.505/", "author": [ { "literal": "Ori Yoran" }, { "literal": "Samuel Joseph Amouyal" }, { "literal": "Chaitanya Malaviya" }, { "literal": "Ben Bogin" }, { "literal": "Ofir Press" }, { "literal": "Jonathan Berant" } ], "citation-key": "arxiv_2407_15711_publication", "container-title": "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2407.15711", "catalog_id": "arxiv:2407.15711", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-07-22", "identifiers": { "arxiv": "2407.15711" }, "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 }, "record_updated_at": "2024-10-21" }, "id": "arxiv:2407.15711:publication", "issued": { "date-parts": [ [ 2024, 11 ] ] }, "note": "Publication date: 2024-11.", "page": "8938-8968", "publisher": "Association for Computational Linguistics", "title": "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.findings-acl.110", "URL": "https://aclanthology.org/2025.findings-acl.110/", "author": [ { "literal": "Yuxiang Chai" }, { "literal": "Siyuan Huang" }, { "literal": "Yazhe Niu" }, { "literal": "Han Xiao" }, { "literal": "Liang Liu" }, { "literal": "Guozhi Wang" }, { "literal": "Dingyu Zhang" }, { "literal": "Shuai Ren" }, { "literal": "Hongsheng Li" } ], "citation-key": "arxiv_2407_17490_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2025", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9c80665716bf665fe4688a27a4c7dcf26fcfe93cb7f79a6f28784a795e0bd3cb", "submitted_at": "2024-07-03T17:59:58Z", "updated_at": "2025-05-29T02:43:50Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2407.17490v2" }, "canonical_source_url": "https://arxiv.org/abs/2407.17490", "catalog_id": "arxiv:2407.17490", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-07-03", "identifiers": { "arxiv": "2407.17490" }, "publication": { "authors": [ "Yuxiang Chai", "Siyuan Huang", "Yazhe Niu", "Han Xiao", "Liang Liu", "Guozhi Wang", "Dingyu Zhang", "Shuai Ren", "Hongsheng Li" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.findings-acl.110", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.110/", "https://aclanthology.org/2025.findings-acl.110.pdf" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. The publisher PDF, page 1, lists nine authors including Guozhi Wang; the retained arXiv snapshot lists eight. Each edition retains its own authors.", "pages": "2138-2156", "pdf_url": "https://aclanthology.org/2025.findings-acl.110.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.110/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2025-05-29" }, "id": "arxiv:2407.17490:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "2138-2156", "publisher": "Association for Computational Linguistics", "title": "AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents", "type": "paper-conference" }, { "DOI": "10.18653/v1/2024.findings-emnlp.599", "URL": "https://aclanthology.org/2024.findings-emnlp.599/", "author": [ { "literal": "Qinzhuo Wu" }, { "literal": "Weikai Xu" }, { "literal": "Wei Liu" }, { "literal": "Tao Tan" }, { "literal": "Jianfeng Liu" }, { "literal": "Ang Li" }, { "literal": "Jian Luan" }, { "literal": "Bin Wang" }, { "literal": "Shuo Shang" } ], "citation-key": "arxiv_2409_14818_publication", "container-title": "Findings of the Association for Computational Linguistics: EMNLP 2024", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cc22337ef29946dffcf7149df1008fd6cf02350c68d21ec0386e6485f5a14ebf", "submitted_at": "2024-09-23T08:47:54Z", "updated_at": "2024-10-03T05:23:22Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.14818v2" }, "canonical_source_url": "https://arxiv.org/abs/2409.14818", "catalog_id": "arxiv:2409.14818", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-09-23", "identifiers": { "arxiv": "2409.14818" }, "publication": { "authors": [ "Qinzhuo Wu", "Weikai Xu", "Wei Liu", "Tao Tan", "Jianfeng Liu", "Ang Li", "Jian Luan", "Bin Wang", "Shuo Shang" ], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 11 ], "doi": "10.18653/v1/2024.findings-emnlp.599", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.findings-emnlp.599/", "https://aclanthology.org/2024.findings-emnlp.599.pdf" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the publisher PDF, page 1. The landing page and its BibTeX list the fifth author as Liujian Liujianfeng; the PDF names Jianfeng Liu.", "pages": "10231-10251", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.599.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.599/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null }, "record_updated_at": "2024-10-03" }, "id": "arxiv:2409.14818:publication", "issued": { "date-parts": [ [ 2024, 11 ] ] }, "note": "Publication date: 2024-11.", "page": "10231-10251", "publisher": "Association for Computational Linguistics", "title": "MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding", "type": "paper-conference" }, { "DOI": "10.52202/079017-2908", "URL": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a6a6891cf1dfc64d664f086cf5976e93-Abstract-Conference.html", "author": [ { "literal": "Tianyue Ou" }, { "literal": "Frank F. Xu" }, { "literal": "Aman Madaan" }, { "literal": "Jiarui Liu" }, { "literal": "Robert Lo" }, { "literal": "Abishek Sridhar" }, { "literal": "Sudipta Sengupta" }, { "literal": "Dan Roth" }, { "literal": "Graham Neubig" }, { "literal": "Shuyan Zhou" } ], "citation-key": "arxiv_2409_15637_publication", "container-title": "Advances in Neural Information Processing Systems", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6c19b869b10f0b4c985b88b032f78e0e72f83e7ca8d9f346417054cd2a9002e3", "submitted_at": "2024-09-24T00:51:45Z", "updated_at": "2024-11-27T16:34:52Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.15637v2" }, "canonical_source_url": "https://arxiv.org/abs/2409.15637", "catalog_id": "arxiv:2409.15637", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-09-24", "identifiers": { "arxiv": "2409.15637" }, "publication": { "authors": [ "Tianyue Ou", "Frank F. Xu", "Aman Madaan", "Jiarui Liu", "Robert Lo", "Abishek Sridhar", "Sudipta Sengupta", "Dan Roth", "Graham Neubig", "Shuyan Zhou" ], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 12, 16 ], "doi": "10.52202/079017-2908", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a6a6891cf1dfc64d664f086cf5976e93-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "91618-91652", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/a6a6891cf1dfc64d664f086cf5976e93-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a6a6891cf1dfc64d664f086cf5976e93-Abstract-Conference.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "record_updated_at": "2024-11-27" }, "id": "arxiv:2409.15637:publication", "issued": { "date-parts": [ [ 2024, 12, 16 ] ] }, "note": "Publication date: 2024-12-16.", "page": "91618-91652", "title": "Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale", "type": "paper-conference", "volume": "37" }, { "DOI": "10.18653/v1/2025.acl-long.381", "URL": "https://aclanthology.org/2025.acl-long.381/", "author": [ { "literal": "Junting Lu" }, { "literal": "Zhiyang Zhang" }, { "literal": "Fangkai Yang" }, { "literal": "Jue Zhang" }, { "literal": "Lu Wang" }, { "literal": "Chao Du" }, { "literal": "Qingwei Lin" }, { "literal": "Saravan Rajmohan" }, { "literal": "Dongmei Zhang" }, { "literal": "Qi Zhang" } ], "citation-key": "arxiv_2409_17140_publication", "container-title": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "618f41c2253a532780766b38396f241a48b587c580d6b4d7065d1519e6149751", "submitted_at": "2024-09-25T17:58:08Z", "updated_at": "2025-05-19T16:12:40Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.17140v2" }, "canonical_source_url": "https://arxiv.org/abs/2409.17140", "catalog_id": "arxiv:2409.17140", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-09-25", "identifiers": { "arxiv": "2409.17140" }, "publication": { "authors": [ "Junting Lu", "Zhiyang Zhang", "Fangkai Yang", "Jue Zhang", "Lu Wang", "Chao Du", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.acl-long.381", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.381/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "7711-7743", "pdf_url": "https://aclanthology.org/2025.acl-long.381.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.381/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-05-19" }, "id": "arxiv:2409.17140:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "7711-7743", "publisher": "Association for Computational Linguistics", "title": "AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents", "type": "paper-conference" }, { "DOI": "10.18653/v1/2024.findings-emnlp.70", "URL": "https://aclanthology.org/2024.findings-emnlp.70/", "author": [ { "literal": "Shaoqing Zhang" }, { "literal": "Zhuosheng Zhang" }, { "literal": "Kehai Chen (陈科海)" }, { "literal": "Xinbei Ma" }, { "literal": "Muyun Yang (杨沐昀)" }, { "literal": "Tiejun Zhao (赵铁军)" }, { "literal": "Min Zhang" } ], "citation-key": "arxiv_2410_00467_publication", "container-title": "Findings of the Association for Computational Linguistics: EMNLP 2024", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f370d105dc1fc1a377fd1b1fd5d1fc3d0f035694cc7c364e6326c587607c98c6", "submitted_at": "2024-10-01T07:49:24Z", "updated_at": "2024-12-19T14:29:31Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.00467v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.00467", "catalog_id": "arxiv:2410.00467", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-01", "identifiers": { "arxiv": "2410.00467" }, "publication": { "authors": [ "Shaoqing Zhang", "Zhuosheng Zhang", "Kehai Chen (陈科海)", "Xinbei Ma", "Muyun Yang (杨沐昀)", "Tiejun Zhao (赵铁军)", "Min Zhang" ], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 11 ], "doi": "10.18653/v1/2024.findings-emnlp.70", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.findings-emnlp.70/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "1304-1320", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.70.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Dynamic Planning for LLM-based Graphical User Interface Automation", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.70/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null }, "record_updated_at": "2024-12-19" }, "id": "arxiv:2410.00467:publication", "issued": { "date-parts": [ [ 2024, 11 ] ] }, "note": "Publication date: 2024-11.", "page": "1304-1320", "publisher": "Association for Computational Linguistics", "title": "Dynamic Planning for LLM-based Graphical User Interface Automation", "type": "paper-conference" }, { "URL": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/4ca0e369689dadb25a5345ba9755ad6f-Abstract-Conference.html", "author": [ { "literal": "Boyu Gou" }, { "literal": "Demi Ruohan Wang" }, { "literal": "Boyuan Zheng" }, { "literal": "Yanan Xie" }, { "literal": "Cheng Chang" }, { "literal": "Yiheng Shu" }, { "literal": "Huan Sun" }, { "literal": "Yu Su" } ], "citation-key": "arxiv_2410_05243_publication", "container-title": "International Conference on Learning Representations", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "08ece826d135b9ab9dfed2a3baf9deeab99489120da749cd67517b636649c5a6", "submitted_at": "2024-10-07T17:47:50Z", "updated_at": "2025-06-17T15:06:02Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.05243v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.05243", "catalog_id": "arxiv:2410.05243", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-07", "identifiers": { "arxiv": "2410.05243" }, "publication": { "authors": [ "Boyu Gou", "Demi Ruohan Wang", "Boyuan Zheng", "Yanan Xie", "Cheng Chang", "Yiheng Shu", "Huan Sun", "Yu Su" ], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 5, 1 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://proceedings.iclr.cc/paper_files/paper/2025/hash/4ca0e369689dadb25a5345ba9755ad6f-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "30851-30883", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/4ca0e369689dadb25a5345ba9755ad6f-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/4ca0e369689dadb25a5345ba9755ad6f-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "record_updated_at": "2025-06-17" }, "id": "arxiv:2410.05243:publication", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "Publication date: 2025-05-01.", "page": "30851-30883", "title": "Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents", "type": "paper-conference", "volume": "2025" }, { "URL": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/394c7c30ea87b5c3521b4d9e9d419071-Abstract-Conference.html", "author": [ { "literal": "Saaket Agashe" }, { "literal": "Jiuzhou Han" }, { "literal": "Shuyu Gan" }, { "literal": "Jiachen Yang" }, { "literal": "Ang Li" }, { "literal": "Xin Wang" } ], "citation-key": "arxiv_2410_08164_publication", "container-title": "International Conference on Learning Representations", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2410.08164", "catalog_id": "arxiv:2410.08164", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-10", "identifiers": { "arxiv": "2410.08164" }, "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" }, "record_updated_at": "2024-10-10" }, "id": "arxiv:2410.08164:publication", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "Publication date: 2025-05-01.", "page": "22924-22946", "title": "Agent S: An Open Agentic Framework that Uses Computers Like a Human", "type": "paper-conference", "volume": "2025" }, { "DOI": "10.18653/v1/2025.sigdial-1.38", "URL": "https://aclanthology.org/2025.sigdial-1.38/", "author": [ { "literal": "Jakub Hoscilowicz" }, { "literal": "Bartosz Maj" }, { "literal": "Bartosz Kozakiewicz" }, { "literal": "Oleksii Tymoshchuk" }, { "literal": "Artur Janicki" } ], "citation-key": "arxiv_2410_11872_publication", "container-title": "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e804944da205076ac6cf88c7966c471697e526f657bda339e09df240257f7217", "submitted_at": "2024-10-09T14:49:02Z", "updated_at": "2024-10-17T07:12:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.11872v2" }, "canonical_source_url": "https://arxiv.org/abs/2410.11872", "catalog_id": "arxiv:2410.11872", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-09", "identifiers": { "arxiv": "2410.11872" }, "publication": { "authors": [ "Jakub Hoscilowicz", "Bartosz Maj", "Bartosz Kozakiewicz", "Oleksii Tymoshchuk", "Artur Janicki" ], "date_basis": "Explicit publisher citation_publication_date: 2025/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 8 ], "doi": "10.18653/v1/2025.sigdial-1.38", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.sigdial-1.38/", "https://aclanthology.org/2025.sigdial-1.38.pdf" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the five-author list on page 1 of the publisher PDF. Landing-page citation metadata lists only Jakub Hoscilowicz and Artur Janicki.", "pages": "471-476", "pdf_url": "https://aclanthology.org/2025.sigdial-1.38.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.sigdial-1.38/", "venue": "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue", "volume": null }, "record_updated_at": "2024-10-17" }, "id": "arxiv:2410.11872:publication", "issued": { "date-parts": [ [ 2025, 8 ] ] }, "note": "Publication date: 2025-08.", "page": "471-476", "publisher": "Association for Computational Linguistics", "title": "ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.naacl-demo.43", "URL": "https://aclanthology.org/2025.naacl-demo.43/", "author": [ { "literal": "Zichen Zhu" }, { "literal": "Hao Tang" }, { "literal": "Yansi Li" }, { "literal": "Dingye Liu" }, { "literal": "Hongshen Xu" }, { "literal": "Kunyao Lan" }, { "literal": "Danyang Zhang" }, { "literal": "Yixuan Jiang" }, { "literal": "Hao Zhou" }, { "literal": "Chenrun Wang" }, { "literal": "Situo Zhang" }, { "literal": "Liangtai Sun" }, { "literal": "Yixiao Wang" }, { "literal": "Yuheng Sun" }, { "literal": "Lu Chen" }, { "literal": "Kai Yu" } ], "citation-key": "arxiv_2410_13757_publication", "container-title": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c0ef02f9c31bf2f095330cf018e7525aecc7644eb1552fb6b511ffced3889122", "submitted_at": "2024-10-17T16:53:50Z", "updated_at": "2025-05-13T06:25:09Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.13757v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.13757", "catalog_id": "arxiv:2410.13757", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-17", "identifiers": { "arxiv": "2410.13757" }, "publication": { "authors": [ "Zichen Zhu", "Hao Tang", "Yansi Li", "Dingye Liu", "Hongshen Xu", "Kunyao Lan", "Danyang Zhang", "Yixuan Jiang", "Hao Zhou", "Chenrun Wang", "Situo Zhang", "Liangtai Sun", "Yixiao Wang", "Yuheng Sun", "Lu Chen", "Kai Yu" ], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 4 ], "doi": "10.18653/v1/2025.naacl-demo.43", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.naacl-demo.43/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "535-549", "pdf_url": "https://aclanthology.org/2025.naacl-demo.43.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-demo.43/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "volume": null }, "record_updated_at": "2025-05-13" }, "id": "arxiv:2410.13757:publication", "issued": { "date-parts": [ [ 2025, 4 ] ] }, "note": "Publication date: 2025-04.", "page": "535-549", "publisher": "Association for Computational Linguistics", "title": "MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation", "type": "paper-conference" }, { "URL": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/2da53cd1abdae59150e35f4693834f32-Abstract-Conference.html", "author": [ { "literal": "Junpeng Liu" }, { "literal": "Tianyue Ou" }, { "literal": "Yifan Song" }, { "literal": "Yuxiao Qu" }, { "literal": "Wai Lam" }, { "literal": "Chenyan Xiong" }, { "literal": "Wenhu Chen" }, { "literal": "Graham Neubig" }, { "literal": "Xiang Yue" } ], "citation-key": "arxiv_2410_13824_publication", "container-title": "International Conference on Learning Representations", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2a3bcd26dff4f1d21a8a2772929c0c97cd1cc180a7606b0744e630dabae94609", "submitted_at": "2024-10-17T17:48:54Z", "updated_at": "2024-11-06T08:29:22Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.13824v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.13824", "catalog_id": "arxiv:2410.13824", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-17", "identifiers": { "arxiv": "2410.13824" }, "publication": { "authors": [ "Junpeng Liu", "Tianyue Ou", "Yifan Song", "Yuxiao Qu", "Wai Lam", "Chenyan Xiong", "Wenhu Chen", "Graham Neubig", "Xiang Yue" ], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 5, 1 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://proceedings.iclr.cc/paper_files/paper/2025/hash/2da53cd1abdae59150e35f4693834f32-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "17971-18005", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/2da53cd1abdae59150e35f4693834f32-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Harnessing Webpage UIs for Text-Rich Visual Understanding", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/2da53cd1abdae59150e35f4693834f32-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "record_updated_at": "2024-11-06" }, "id": "arxiv:2410.13824:publication", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "Publication date: 2025-05-01.", "page": "17971-18005", "title": "Harnessing Webpage UIs for Text-Rich Visual Understanding", "type": "paper-conference", "volume": "2025" }, { "URL": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/b9e472cd579c83e2f6aa3459f46aac28-Abstract-Conference.html", "author": [ { "literal": "Taiyi Wang" }, { "literal": "Zhihao Wu" }, { "literal": "Jianheng Liu" }, { "literal": "Jianye HAO" }, { "literal": "Jun Wang" }, { "literal": "Kun Shao" } ], "citation-key": "arxiv_2410_14803_publication", "container-title": "International Conference on Learning Representations", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a9e3d8350cd0be5d4f3e82b3b35a15fe89403cd602e8bb20b7cd783c7a7067a0", "submitted_at": "2024-10-18T18:19:56Z", "updated_at": "2025-02-21T16:23:59Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2410.14803v5" }, "canonical_source_url": "https://arxiv.org/abs/2410.14803", "catalog_id": "arxiv:2410.14803", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-18", "identifiers": { "arxiv": "2410.14803" }, "publication": { "authors": [ "Taiyi Wang", "Zhihao Wu", "Jianheng Liu", "Jianye HAO", "Jun Wang", "Kun Shao" ], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 5, 1 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://proceedings.iclr.cc/paper_files/paper/2025/hash/b9e472cd579c83e2f6aa3459f46aac28-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 publisher title uses singular Agent; the preprint uses Agents. The authors and DistRL contribution agree.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "74757-74782", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/b9e472cd579c83e2f6aa3459f46aac28-Paper-Conference.pdf", "publisher": null, "series": null, "title": "DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/b9e472cd579c83e2f6aa3459f46aac28-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "record_updated_at": "2025-02-21" }, "id": "arxiv:2410.14803:publication", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "Publication date: 2025-05-01.", "page": "74757-74782", "title": "DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent", "type": "paper-conference", "volume": "2025" }, { "URL": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/9a75f4dd9679aa4ff80a4e6f0a1dc700-Abstract-Conference.html", "author": [ { "literal": "Jingxuan Chen" }, { "literal": "Derek Yuen" }, { "literal": "Bin Xie" }, { "literal": "Yuhao Yang" }, { "literal": "Gongwei Chen" }, { "literal": "Zhihao Wu" }, { "literal": "Li Yixing" }, { "literal": "Xurui Zhou" }, { "literal": "Weiwen Liu" }, { "literal": "Shuai Wang" }, { "literal": "Kaiwen Zhou" }, { "literal": "Rui Shao" }, { "literal": "Liqiang Nie" }, { "literal": "Yasheng Wang" }, { "literal": "Jianye HAO" }, { "literal": "Jun Wang" }, { "literal": "Kun Shao" } ], "citation-key": "arxiv_2410_15164_publication", "container-title": "International Conference on Learning Representations", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "206059754652205f1e036fac8ee117f71dd356bfe2d35fd84aff8d2935ea242d", "submitted_at": "2024-10-19T17:28:48Z", "updated_at": "2025-03-31T20:39:17Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.15164v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.15164", "catalog_id": "arxiv:2410.15164", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-19", "identifiers": { "arxiv": "2410.15164" }, "publication": { "authors": [ "Jingxuan Chen", "Derek Yuen", "Bin Xie", "Yuhao Yang", "Gongwei Chen", "Zhihao Wu", "Li Yixing", "Xurui Zhou", "Weiwen Liu", "Shuai Wang", "Kaiwen Zhou", "Rui Shao", "Liqiang Nie", "Yasheng Wang", "Jianye HAO", "Jun Wang", "Kun Shao" ], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 5, 1 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://proceedings.iclr.cc/paper_files/paper/2025/hash/9a75f4dd9679aa4ff80a4e6f0a1dc700-Abstract-Conference.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "61769-61806", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/9a75f4dd9679aa4ff80a4e6f0a1dc700-Paper-Conference.pdf", "publisher": null, "series": null, "title": "SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/9a75f4dd9679aa4ff80a4e6f0a1dc700-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025" }, "record_updated_at": "2025-03-31" }, "id": "arxiv:2410.15164:publication", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "Publication date: 2025-05-01.", "page": "61769-61806", "title": "SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION", "type": "paper-conference", "volume": "2025" }, { "DOI": "10.18653/v1/2025.findings-acl.577", "URL": "https://aclanthology.org/2025.findings-acl.577/", "author": [ { "literal": "Yueqi Song" }, { "literal": "Frank F. Xu" }, { "literal": "Shuyan Zhou" }, { "literal": "Graham Neubig" } ], "citation-key": "arxiv_2410_16464_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2025", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0944387dd3c65ea7b2f5ca52721496cf10b3c9860b303063201e7811318f4950", "submitted_at": "2024-10-21T19:46:06Z", "updated_at": "2025-06-16T22:23:37Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.16464v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.16464", "catalog_id": "arxiv:2410.16464", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-21", "identifiers": { "arxiv": "2410.16464" }, "publication": { "authors": [ "Yueqi Song", "Frank F. Xu", "Shuyan Zhou", "Graham Neubig" ], "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.577", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.577/" ], "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": "11066-11085", "pdf_url": "https://aclanthology.org/2025.findings-acl.577.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Beyond Browsing: API-Based Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.577/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2025-06-16" }, "id": "arxiv:2410.16464:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "11066-11085", "publisher": "Association for Computational Linguistics", "title": "Beyond Browsing: API-Based Web Agents", "type": "paper-conference" }, { "URL": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/5b555804d495321df2e3208cc27f4fbc-Abstract-Conference.html", "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_publication", "container-title": "International Conference on Learning Representations", "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": "publication", "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" }, "id": "arxiv:2410.19100:publication", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "Publication date: 2025-05-01.", "page": "36934-36958", "title": "VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks", "type": "paper-conference", "volume": "2025" }, { "DOI": "10.18653/v1/2025.acl-long.1336", "URL": "https://aclanthology.org/2025.acl-long.1336/", "author": [ { "literal": "Hongliang He" }, { "literal": "Wenlin Yao" }, { "literal": "Kaixin Ma" }, { "literal": "Wenhao Yu" }, { "literal": "Hongming Zhang" }, { "literal": "Tianqing Fang" }, { "literal": "Zhenzhong Lan" }, { "literal": "Dong Yu" } ], "citation-key": "arxiv_2410_19609_publication", "container-title": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "db2a115281f831ea9333a03fc2a9ebb2f09528eb082060f00a33b125f9ef7762", "submitted_at": "2024-10-25T15:01:27Z", "updated_at": "2024-10-25T15:01:27Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2410.19609v1" }, "canonical_source_url": "https://arxiv.org/abs/2410.19609", "catalog_id": "arxiv:2410.19609", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-25", "identifiers": { "arxiv": "2410.19609" }, "publication": { "authors": [ "Hongliang He", "Wenlin Yao", "Kaixin Ma", "Wenhao Yu", "Hongming Zhang", "Tianqing Fang", "Zhenzhong Lan", "Dong Yu" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.acl-long.1336", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.1336/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "27545-27564", "pdf_url": "https://aclanthology.org/2025.acl-long.1336.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.1336/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2024-10-25" }, "id": "arxiv:2410.19609:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "27545-27564", "publisher": "Association for Computational Linguistics", "title": "OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.findings-naacl.222", "URL": "https://aclanthology.org/2025.findings-naacl.222/", "author": [ { "literal": "Haoyi Qiu" }, { "literal": "Alexander Richard Fabbri" }, { "literal": "Divyansh Agarwal" }, { "literal": "Kung-Hsiang Huang" }, { "literal": "Sarah Tan" }, { "literal": "Nanyun Peng" }, { "literal": "Chien-Sheng Wu" } ], "citation-key": "arxiv_2410_23252_publication", "container-title": "Findings of the Association for Computational Linguistics: NAACL 2025", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "26fac89c78ab03fcbaf25bbfe93ebce090dec9adbf5c6dd5440641f154cffac9", "submitted_at": "2024-10-30T17:35:44Z", "updated_at": "2025-03-08T23:37:49Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.23252v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.23252", "catalog_id": "arxiv:2410.23252", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-30", "identifiers": { "arxiv": "2410.23252" }, "publication": { "authors": [ "Haoyi Qiu", "Alexander Richard Fabbri", "Divyansh Agarwal", "Kung-Hsiang Huang", "Sarah Tan", "Nanyun Peng", "Chien-Sheng Wu" ], "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.findings-naacl.222", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-naacl.222/" ], "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": "3978-4005", "pdf_url": "https://aclanthology.org/2025.findings-naacl.222.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Evaluating Cultural and Social Awareness of LLM Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-naacl.222/", "venue": "Findings of the Association for Computational Linguistics: NAACL 2025", "volume": null }, "record_updated_at": "2025-03-08" }, "id": "arxiv:2410.23252:publication", "issued": { "date-parts": [ [ 2025, 4 ] ] }, "note": "Publication date: 2025-04.", "page": "3978-4005", "publisher": "Association for Computational Linguistics", "title": "Evaluating Cultural and Social Awareness of LLM Web Agents", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.acl-long.107", "URL": "https://aclanthology.org/2025.acl-long.107/", "author": [ { "literal": "Yifan Xu" }, { "literal": "Xiao Liu" }, { "literal": "Xueqiao Sun" }, { "literal": "Siyi Cheng" }, { "literal": "Hao Yu (余浩)" }, { "literal": "Hanyu Lai" }, { "literal": "Shudan Zhang" }, { "literal": "Dan Zhang" }, { "literal": "Jie Tang" }, { "literal": "Yuxiao Dong" } ], "citation-key": "arxiv_2410_24024_publication", "container-title": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d29fe5262adf8677bbd5fead628c5fc28707af263aa7e800d1dee1f7e499784c", "submitted_at": "2024-10-31T15:25:20Z", "updated_at": "2024-11-04T05:57:31Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.24024v2" }, "canonical_source_url": "https://arxiv.org/abs/2410.24024", "catalog_id": "arxiv:2410.24024", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-10-31", "identifiers": { "arxiv": "2410.24024" }, "publication": { "authors": [ "Yifan Xu", "Xiao Liu", "Xueqiao Sun", "Siyi Cheng", "Hao Yu (余浩)", "Hanyu Lai", "Shudan Zhang", "Dan Zhang", "Jie Tang", "Yuxiao Dong" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.acl-long.107", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.107/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "2144-2166", "pdf_url": "https://aclanthology.org/2025.acl-long.107.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.107/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2024-11-04" }, "id": "arxiv:2410.24024:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "2144-2166", "publisher": "Association for Computational Linguistics", "title": "AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.acl-long.411", "URL": "https://aclanthology.org/2025.acl-long.411/", "author": [ { "literal": "Yanzhe Zhang" }, { "literal": "Tao Yu" }, { "literal": "Diyi Yang" } ], "citation-key": "arxiv_2411_02391_publication", "container-title": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "085c64595365cc6439c8c5fa8a479259a3d59b7e9740e0f9d43e48d00e1439c0", "submitted_at": "2024-11-04T18:56:42Z", "updated_at": "2025-05-24T16:15:46Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2411.02391v2" }, "canonical_source_url": "https://arxiv.org/abs/2411.02391", "catalog_id": "arxiv:2411.02391", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-11-04", "identifiers": { "arxiv": "2411.02391" }, "publication": { "authors": [ "Yanzhe Zhang", "Tao Yu", "Diyi Yang" ], "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.411", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.411/" ], "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": "8387-8401", "pdf_url": "https://aclanthology.org/2025.acl-long.411.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Attacking Vision-Language Computer Agents via Pop-ups", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.411/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-05-24" }, "id": "arxiv:2411.02391:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "8387-8401", "publisher": "Association for Computational Linguistics", "title": "Attacking Vision-Language Computer Agents via Pop-ups", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.acl-long.1008", "URL": "https://aclanthology.org/2025.acl-long.1008/", "author": [ { "literal": "Gaurav Verma" }, { "literal": "Rachneet Kaur" }, { "literal": "Nishan Srishankar" }, { "literal": "Zhen Zeng" }, { "literal": "Tucker Balch" }, { "literal": "Manuela Veloso" } ], "citation-key": "arxiv_2411_13451_publication", "container-title": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "94d908dd89ff27434805fe7915c5a93d5c2b1d873449babc1c566c5582cca734", "submitted_at": "2024-11-20T16:54:15Z", "updated_at": "2024-11-20T16:54:15Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2411.13451v1" }, "canonical_source_url": "https://arxiv.org/abs/2411.13451", "catalog_id": "arxiv:2411.13451", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-11-20", "identifiers": { "arxiv": "2411.13451" }, "publication": { "authors": [ "Gaurav Verma", "Rachneet Kaur", "Nishan Srishankar", "Zhen Zeng", "Tucker Balch", "Manuela Veloso" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.acl-long.1008", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.1008/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "20635-20651", "pdf_url": "https://aclanthology.org/2025.acl-long.1008.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.1008/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2024-11-20" }, "id": "arxiv:2411.13451:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "20635-20651", "publisher": "Association for Computational Linguistics", "title": "AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations", "type": "paper-conference" }, { "URL": "https://openaccess.thecvf.com/content/CVPR2025/html/Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper.html", "author": [ { "literal": "Kevin Qinghong Lin" }, { "literal": "Linjie Li" }, { "literal": "Difei Gao" }, { "literal": "Zhengyuan Yang" }, { "literal": "Shiwei Wu" }, { "literal": "Zechen Bai" }, { "literal": "Stan Weixian Lei" }, { "literal": "Lijuan Wang" }, { "literal": "Mike Zheng Shou" } ], "citation-key": "arxiv_2411_17465_publication", "container-title": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2411.17465", "catalog_id": "arxiv:2411.17465", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-11-26", "identifiers": { "arxiv": "2411.17465" }, "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 }, "record_updated_at": "2024-11-26" }, "id": "arxiv:2411.17465:publication", "issued": { "date-parts": [ [ 2025, 6 ] ] }, "note": "Publication date: 2025-06.", "page": "19498-19508", "title": "ShowUI: One Vision-Language-Action Model for GUI Visual Agent", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.findings-acl.76", "URL": "https://aclanthology.org/2025.findings-acl.76/", "author": [ { "literal": "Yiqin Wang" }, { "literal": "Haoji Zhang" }, { "literal": "Jingqi Tian" }, { "literal": "Yansong Tang" } ], "citation-key": "arxiv_2412_01268_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2025", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6a4c750017de421d3ca9bf119834dfb96d2fe8a0610f12b30d2fae603e26c66b", "submitted_at": "2024-12-02T08:35:31Z", "updated_at": "2024-12-02T08:35:31Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2412.01268v1" }, "canonical_source_url": "https://arxiv.org/abs/2412.01268", "catalog_id": "arxiv:2412.01268", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-12-02", "identifiers": { "arxiv": "2412.01268" }, "publication": { "authors": [ "Yiqin Wang", "Haoji Zhang", "Jingqi Tian", "Yansong Tang" ], "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.76", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.76/" ], "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": "1461-1473", "pdf_url": "https://aclanthology.org/2025.findings-acl.76.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Ponder & Press: Advancing Visual GUI Agent towards General Computer Control", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.76/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2024-12-02" }, "id": "arxiv:2412.01268:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "1461-1473", "publisher": "Association for Computational Linguistics", "title": "Ponder & Press: Advancing Visual GUI Agent towards General Computer Control", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.findings-acl.1152", "URL": "https://aclanthology.org/2025.findings-acl.1152/", "author": [ { "literal": "Yuhao Yang" }, { "literal": "Yue Wang" }, { "literal": "Dongxu Li" }, { "literal": "Ziyang Luo" }, { "literal": "Bei Chen" }, { "literal": "Chao Huang" }, { "literal": "Junnan Li" } ], "citation-key": "arxiv_2412_16256_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2025", "custom": { "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" }, "canonical_source_url": "https://arxiv.org/abs/2412.16256", "catalog_id": "arxiv:2412.16256", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-12-20", "identifiers": { "arxiv": "2412.16256" }, "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 }, "record_updated_at": "2025-07-08" }, "id": "arxiv:2412.16256:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "22418-22433", "publisher": "Association for Computational Linguistics", "title": "Aria-UI: Visual Grounding for GUI Instructions", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.acl-long.277", "URL": "https://aclanthology.org/2025.acl-long.277/", "author": [ { "literal": "Qiushi Sun" }, { "literal": "Kanzhi Cheng" }, { "literal": "Zichen Ding" }, { "literal": "Chuanyang Jin" }, { "literal": "Yian Wang" }, { "literal": "Fangzhi Xu" }, { "literal": "Zhenyu Wu" }, { "literal": "Chengyou Jia" }, { "literal": "Liheng Chen" }, { "literal": "Zhoumianze Liu" }, { "literal": "Ben Kao" }, { "literal": "Guohao Li" }, { "literal": "Junxian He" }, { "literal": "Yu Qiao" }, { "literal": "Zhiyong Wu" } ], "citation-key": "arxiv_2412_19723_publication", "container-title": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "40b5e3090c25f80d8d786f623812459b329acc2772f945419a585ffb27c54db3", "submitted_at": "2024-12-27T16:21:58Z", "updated_at": "2025-06-27T08:25:48Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2412.19723v3" }, "canonical_source_url": "https://arxiv.org/abs/2412.19723", "catalog_id": "arxiv:2412.19723", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2024-12-27", "identifiers": { "arxiv": "2412.19723" }, "publication": { "authors": [ "Qiushi Sun", "Kanzhi Cheng", "Zichen Ding", "Chuanyang Jin", "Yian Wang", "Fangzhi Xu", "Zhenyu Wu", "Chengyou Jia", "Liheng Chen", "Zhoumianze Liu", "Ben Kao", "Guohao Li", "Junxian He", "Yu Qiao", "Zhiyong Wu" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.acl-long.277", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.277/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "5555-5579", "pdf_url": "https://aclanthology.org/2025.acl-long.277.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.277/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-06-27" }, "id": "arxiv:2412.19723:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "5555-5579", "publisher": "Association for Computational Linguistics", "title": "OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.naacl-demo.17", "URL": "https://aclanthology.org/2025.naacl-demo.17/", "author": [ { "literal": "Faria Huq" }, { "literal": "Zora Zhiruo Wang" }, { "literal": "Frank F. Xu" }, { "literal": "Tianyue Ou" }, { "literal": "Shuyan Zhou" }, { "literal": "Jeffrey P. Bigham" }, { "literal": "Graham Neubig" } ], "citation-key": "arxiv_2501_16609_publication", "container-title": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9b14b88273749ac54ebbe3694cbe4196640da8f81ba2faf77b0e6bbd79a060f6", "submitted_at": "2025-01-28T00:56:53Z", "updated_at": "2026-02-27T05:35:06Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2501.16609v4" }, "canonical_source_url": "https://arxiv.org/abs/2501.16609", "catalog_id": "arxiv:2501.16609", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2025-01-28", "identifiers": { "arxiv": "2501.16609" }, "publication": { "authors": [ "Faria Huq", "Zora Zhiruo Wang", "Frank F. Xu", "Tianyue Ou", "Shuyan Zhou", "Jeffrey P. Bigham", "Graham Neubig" ], "date_basis": "The ACL Anthology citation_publication_date is 2025/4, and its visible Month/Year fields state April 2025. Only month precision is supplied; no day is inferred from conference dates.", "date_parts": [ 2025, 4 ], "doi": "10.18653/v1/2025.naacl-demo.17", "event_dates": null, "evidence_urls": [ "https://arxiv.org/abs/2501.16609v4", "https://aclanthology.org/2025.naacl-demo.17/" ], "identity_basis": "The retained arXiv v4 abstract page explicitly links this DOI. The ACL publication has the same complete title and the same seven authors in the same order, and describes the same CowPilot human-agent navigation framework. This attaches the proceedings edition to the existing arXiv identity.", "issue": null, "notes": "The April 2025 proceedings edition is distinct from the retained arXiv v4, last revised on 2026-02-27. The publisher abstract has minor wording and typesetting differences from the retained arXiv abstract; neither its text nor its date replaces the original arXiv snapshot or annotation. Exact publication day, numeric volume, issue and series are not established.", "pages": "163-172", "pdf_url": "https://aclanthology.org/2025.naacl-demo.17.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-demo.17/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "volume": null }, "record_updated_at": "2026-02-27" }, "id": "arxiv:2501.16609:publication", "issued": { "date-parts": [ [ 2025, 4 ] ] }, "note": "Publication date: 2025-04.", "page": "163-172", "publisher": "Association for Computational Linguistics", "title": "CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.naacl-long.244", "URL": "https://aclanthology.org/2025.naacl-long.244/", "author": [ { "literal": "Qinzhuo Wu" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Bin Wang" } ], "citation-key": "arxiv_2502_02955_publication", "container-title": "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)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d3e0b19f259bcdb57b0dea92578d0ee1c7c229ea11e622c56e808f17ca2568cc", "submitted_at": "2025-02-05T07:35:23Z", "updated_at": "2025-02-05T07:35:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2502.02955v1" }, "canonical_source_url": "https://arxiv.org/abs/2502.02955", "catalog_id": "arxiv:2502.02955", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2025-02-05", "identifiers": { "arxiv": "2502.02955" }, "publication": { "authors": [ "Qinzhuo Wu", "Wei Liu", "Jian Luan", "Bin Wang" ], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 4 ], "doi": "10.18653/v1/2025.naacl-long.244", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.naacl-long.244/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "4760-4775", "pdf_url": "https://aclanthology.org/2025.naacl-long.244.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-long.244/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-02-05" }, "id": "arxiv:2502.02955:publication", "issued": { "date-parts": [ [ 2025, 4 ] ] }, "note": "Publication date: 2025-04.", "page": "4760-4775", "publisher": "Association for Computational Linguistics", "title": "ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.findings-acl.326", "URL": "https://aclanthology.org/2025.findings-acl.326/", "author": [ { "literal": "Vardaan Pahuja" }, { "literal": "Yadong Lu" }, { "literal": "Corby Rosset" }, { "literal": "Boyu Gou" }, { "literal": "Arindam Mitra" }, { "literal": "Spencer Whitehead" }, { "literal": "Yu Su" }, { "literal": "Ahmed Awadallah" } ], "citation-key": "arxiv_2502_11357_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2025", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d9f459a02b7a464d9e1e49579943d1b93d46308c1b00e795c903d2fa1502a2b2", "submitted_at": "2025-02-17T02:13:48Z", "updated_at": "2025-05-30T02:30:57Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2502.11357v4" }, "canonical_source_url": "https://arxiv.org/abs/2502.11357", "catalog_id": "arxiv:2502.11357", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2025-02-17", "identifiers": { "arxiv": "2502.11357" }, "publication": { "authors": [ "Vardaan Pahuja", "Yadong Lu", "Corby Rosset", "Boyu Gou", "Arindam Mitra", "Spencer Whitehead", "Yu Su", "Ahmed Awadallah" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.findings-acl.326", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.326/", "https://aclanthology.org/2025.findings-acl.326.pdf" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the publisher PDF, page 1. Landing-page citation metadata gives Ahmed Hassan for the final author, while the supplied BibTeX expands the name to Ahmed Hassan Awadallah; the PDF uses Ahmed Awadallah.", "pages": "6300-6323", "pdf_url": "https://aclanthology.org/2025.findings-acl.326.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.326/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2025-05-30" }, "id": "arxiv:2502.11357:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "6300-6323", "publisher": "Association for Computational Linguistics", "title": "Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.naacl-demo.36", "URL": "https://aclanthology.org/2025.naacl-demo.36/", "author": [ { "literal": "Danqing Zhang" }, { "literal": "Balaji Rama" }, { "literal": "Jingyi Ni" }, { "literal": "Shiying He" }, { "literal": "Fu Zhao" }, { "literal": "Kunyu Chen" }, { "literal": "Arnold Chen" }, { "literal": "Junyu Cao" } ], "citation-key": "arxiv_2503_02950_publication", "container-title": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "df682f883bed5e0e9917074dfa130839fabaa318c55714f26943d944774854fe", "submitted_at": "2025-03-04T19:13:10Z", "updated_at": "2025-05-06T06:42:34Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.02950v2" }, "canonical_source_url": "https://arxiv.org/abs/2503.02950", "catalog_id": "arxiv:2503.02950", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2025-03-04", "identifiers": { "arxiv": "2503.02950" }, "publication": { "authors": [ "Danqing Zhang", "Balaji Rama", "Jingyi Ni", "Shiying He", "Fu Zhao", "Kunyu Chen", "Arnold Chen", "Junyu Cao" ], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 4 ], "doi": "10.18653/v1/2025.naacl-demo.36", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.naacl-demo.36/" ], "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": "449-455", "pdf_url": "https://aclanthology.org/2025.naacl-demo.36.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-demo.36/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "volume": null }, "record_updated_at": "2025-05-06" }, "id": "arxiv:2503.02950:publication", "issued": { "date-parts": [ [ 2025, 4 ] ] }, "note": "Publication date: 2025-04.", "page": "449-455", "publisher": "Association for Computational Linguistics", "title": "LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.findings-acl.809", "URL": "https://aclanthology.org/2025.findings-acl.809/", "author": [ { "literal": "Xinyi Liu" }, { "literal": "Xiaoyi Zhang" }, { "literal": "Ziyun Zhang" }, { "literal": "Yan Lu" } ], "citation-key": "arxiv_2504_11257_publication", "container-title": "Findings of the Association for Computational Linguistics: ACL 2025", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "363e3c3e882fa93a19df74bbf77aa98525cf4639c8f62100c3ddc3e0a438997f", "submitted_at": "2025-04-15T14:56:21Z", "updated_at": "2025-07-30T13:57:49Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2504.11257v4" }, "canonical_source_url": "https://arxiv.org/abs/2504.11257", "catalog_id": "arxiv:2504.11257", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2025-04-15", "identifiers": { "arxiv": "2504.11257" }, "publication": { "authors": [ "Xinyi Liu", "Xiaoyi Zhang", "Ziyun Zhang", "Yan Lu" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.findings-acl.809", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.809/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "15668-15684", "pdf_url": "https://aclanthology.org/2025.findings-acl.809.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.809/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2025-07-30" }, "id": "arxiv:2504.11257:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "15668-15684", "publisher": "Association for Computational Linguistics", "title": "UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.acl-long.282", "URL": "https://aclanthology.org/2025.acl-long.282/", "author": [ { "literal": "Bin Xie" }, { "literal": "Rui Shao" }, { "literal": "Gongwei Chen" }, { "literal": "Kaiwen Zhou" }, { "literal": "Yinchuan Li" }, { "literal": "Jie Liu" }, { "literal": "Min Zhang" }, { "literal": "Liqiang Nie" } ], "citation-key": "arxiv_2505_16827_publication", "container-title": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "641001c49fccac1e1c0659fe765eba5a30cefd2a7ff5d00c821f79092c45a1df", "submitted_at": "2025-05-22T16:01:06Z", "updated_at": "2025-05-22T16:01:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.16827v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.16827", "catalog_id": "arxiv:2505.16827", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2025-05-22", "identifiers": { "arxiv": "2505.16827" }, "publication": { "authors": [ "Bin Xie", "Rui Shao", "Gongwei Chen", "Kaiwen Zhou", "Yinchuan Li", "Jie Liu", "Min Zhang", "Liqiang Nie" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.acl-long.282", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.282/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "5650-5667", "pdf_url": "https://aclanthology.org/2025.acl-long.282.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.282/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-05-22" }, "id": "arxiv:2505.16827:publication", "issued": { "date-parts": [ [ 2025, 7 ] ] }, "note": "Publication date: 2025-07.", "page": "5650-5667", "publisher": "Association for Computational Linguistics", "title": "GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent", "type": "paper-conference" }, { "DOI": "10.18653/v1/2025.emnlp-demos.12", "URL": "https://aclanthology.org/2025.emnlp-demos.12/", "author": [ { "literal": "Zhong Zhang" }, { "literal": "Yaxi Lu" }, { "literal": "Yikun Fu" }, { "literal": "Yupeng Huo" }, { "literal": "Shenzhi Yang" }, { "literal": "Yesai Wu" }, { "literal": "Han Si (司函)" }, { "literal": "Xin Cong" }, { "literal": "Haotian Chen" }, { "literal": "Yankai Lin (林衍凯)" }, { "literal": "Jie Xie" }, { "literal": "Wei Zhou" }, { "literal": "Wang Xu" }, { "literal": "Yuanheng Zhang" }, { "literal": "Zhou Su" }, { "literal": "Zhongwu Zhai" }, { "literal": "Xiaoming Liu" }, { "literal": "Yudong Mei" }, { "literal": "Jianming Xu" }, { "literal": "Hongyan Tian" }, { "literal": "Chongyi Wang" }, { "literal": "Chi Chen" }, { "literal": "Yuan Yao" }, { "literal": "Zhiyuan Liu" }, { "literal": "Maosong Sun (孙茂松)" } ], "citation-key": "arxiv_2506_01391_publication", "container-title": "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3c0b2a065898ba4f73fcb5e5b2e92d723b0b55ac6caa46d5bf02d44eb7a2cdd9", "submitted_at": "2025-06-02T07:30:29Z", "updated_at": "2025-06-17T02:57:04Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2506.01391v2" }, "canonical_source_url": "https://arxiv.org/abs/2506.01391", "catalog_id": "arxiv:2506.01391", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2025-06-02", "identifiers": { "arxiv": "2506.01391" }, "publication": { "authors": [ "Zhong Zhang", "Yaxi Lu", "Yikun Fu", "Yupeng Huo", "Shenzhi Yang", "Yesai Wu", "Han Si (司函)", "Xin Cong", "Haotian Chen", "Yankai Lin (林衍凯)", "Jie Xie", "Wei Zhou", "Wang Xu", "Yuanheng Zhang", "Zhou Su", "Zhongwu Zhai", "Xiaoming Liu", "Yudong Mei", "Jianming Xu", "Hongyan Tian", "Chongyi Wang", "Chi Chen", "Yuan Yao", "Zhiyuan Liu", "Maosong Sun (孙茂松)" ], "date_basis": "Explicit publisher citation_publication_date: 2025/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 11 ], "doi": "10.18653/v1/2025.emnlp-demos.12", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.emnlp-demos.12/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "155-180", "pdf_url": "https://aclanthology.org/2025.emnlp-demos.12.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning", "type": "conference-paper", "url": "https://aclanthology.org/2025.emnlp-demos.12/", "venue": "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", "volume": null }, "record_updated_at": "2025-06-17" }, "id": "arxiv:2506.01391:publication", "issued": { "date-parts": [ [ 2025, 11 ] ] }, "note": "Publication date: 2025-11.", "page": "155-180", "publisher": "Association for Computational Linguistics", "title": "AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning", "type": "paper-conference" }, { "DOI": "10.1145/2983990.2984020", "URL": "https://doi.org/10.1145/2983990.2984020", "author": [ { "literal": "Shaon Barman" }, { "literal": "Sarah Chasins" }, { "literal": "Ras Bodik" }, { "literal": "Sumit Gulwani" } ], "citation-key": "cua_07942b5af1a8c0ffa9c7322a", "container-title": "OOPSLA 2016", "custom": { "canonical_source_url": "https://doi.org/10.1145/2983990.2984020", "catalog_id": "url:347925d0f440d6396080", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": { "doi": "10.1145/2983990.2984020" }, "publication": { "authors": [ "Shaon Barman", "Sarah Chasins", "Ras Bodik", "Sumit Gulwani" ], "date_basis": "Supplied month precision: 2016-11. year=2016, month=November", "date_parts": [ 2016, 11 ], "doi": "10.1145/2983990.2984020", "event_dates": null, "evidence_urls": [ "https://www.microsoft.com/en-us/research/publication/ringer-web-automation-demonstration/bibtex/", "https://2016.splashcon.org/track/splash-2016-oopsla", "https://www.microsoft.com/en-us/research/publication/ringer-web-automation-demonstration/", "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/12/oopsla16-web.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": "The original manuscript and MSR BibTeX print Sarah Chasins and Ras Bodik. The official conference profiles expand these to Sarah E. Chasins and Rastislav Bodík; the printed publication names are preserved. Page range, volume and exact publication day are not established by the retained citation sources.", "pages": null, "pdf_url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/12/oopsla16-web.pdf", "publisher": null, "series": null, "title": "Ringer: Web Automation by Demonstration", "type": "conference-paper", "url": "https://doi.org/10.1145/2983990.2984020", "venue": "OOPSLA 2016", "volume": null }, "record_updated_at": null }, "id": "url:347925d0f440d6396080", "issued": { "date-parts": [ [ 2016, 11 ] ] }, "note": "Publication date: 2016-11.", "title": "Ringer: Web Automation by Demonstration", "type": "paper-conference" }, { "DOI": "10.1145/3025453.3025483", "URL": "https://doi.org/10.1145/3025453.3025483", "author": [ { "literal": "Toby Jia-Jun Li" }, { "literal": "Amos Azaria" }, { "literal": "Brad A. Myers" } ], "citation-key": "cua_6b7f9d608ed89d1625610eb1", "container-title": "Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems", "custom": { "canonical_source_url": "https://doi.org/10.1145/3025453.3025483", "catalog_id": "url:392a602c660ffa91be46", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": { "doi": "10.1145/3025453.3025483" }, "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 }, "record_updated_at": null }, "id": "url:392a602c660ffa91be46", "issued": { "date-parts": [ [ 2017 ] ] }, "note": "Publication date: 2017.", "page": "6038-6049", "title": "SUGILITE: Creating Multimodal Smartphone Automation by Demonstration", "type": "paper-conference" }, { "URL": "https://proceedings.mlr.press/v70/shi17a.html", "author": [ { "literal": "Tianlin Shi" }, { "literal": "Andrej Karpathy" }, { "literal": "Linxi Fan" }, { "literal": "Jonathan Hernandez" }, { "literal": "Percy Liang" } ], "citation-key": "cua_ba263493b78b0263c7933138", "collection-title": "Proceedings of Machine Learning Research", "container-title": "Proceedings of the 34th International Conference on Machine Learning", "custom": { "canonical_source_url": "https://proceedings.mlr.press/v70/shi17a.html", "catalog_id": "url:52a3261eb6a19b402e88", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2017-07-17", "identifiers": {}, "publication": { "authors": [ "Tianlin Shi", "Andrej Karpathy", "Linxi Fan", "Jonathan Hernandez", "Percy Liang" ], "date_basis": "Publisher citation_publication_date metadata explicitly states 2017/07/17; this is separate from the conference interval.", "date_parts": [ 2017, 7, 17 ], "doi": null, "event_dates": "06--11 Aug (conference interval reported in the publisher BibTeX month field)", "evidence_urls": [ "https://proceedings.mlr.press/v70/shi17a.html", "https://proceedings.mlr.press/v70/shi17a/shi17a.pdf" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Publisher citation uses Tianlin Shi and Linxi Fan; the PDF also prints the nicknames Tim and Jim. The ordered publisher author names are retained. DOI not supplied in the retained publisher citation. Publisher metadata supplies the publication date separately from the conference interval.", "pages": "3135-3144", "pdf_url": "https://proceedings.mlr.press/v70/shi17a/shi17a.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "World of Bits: An Open-Domain Platform for Web-Based Agents", "type": "conference-paper", "url": "https://proceedings.mlr.press/v70/shi17a.html", "venue": "Proceedings of the 34th International Conference on Machine Learning", "volume": "70" }, "record_updated_at": null }, "id": "url:52a3261eb6a19b402e88", "issued": { "date-parts": [ [ 2017, 7, 17 ] ] }, "note": "Publication date: 2017-07-17.", "page": "3135-3144", "publisher": "PMLR", "title": "World of Bits: An Open-Domain Platform for Web-Based Agents", "type": "paper-conference", "volume": "70" }, { "DOI": "10.1145/1753326.1753555", "URL": "https://doi.org/10.1145/1753326.1753555", "author": [ { "literal": "Tsung-Hsiang Chang" }, { "literal": "Tom Yeh" }, { "literal": "Robert C. Miller" } ], "citation-key": "cua_08a6c6d3e0e8b509ecb90301", "container-title": "Proceedings of the 28th International Conference on Human Factors in Computing Systems (CHI '10)", "custom": { "canonical_source_url": "https://doi.org/10.1145/1753326.1753555", "catalog_id": "url:6262c757080f8838e62c", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": { "doi": "10.1145/1753326.1753555" }, "publication": { "authors": [ "Tsung-Hsiang Chang", "Tom Yeh", "Robert C. Miller" ], "date_basis": "Supplied month precision: 2010-04. Date Issued: April 2010", "date_parts": [ 2010, 4 ], "doi": "10.1145/1753326.1753555", "event_dates": null, "evidence_urls": [ "https://dspace.mit.edu/entities/publication/6a6097ba-1d97-43cf-bc70-04b5af02efd5" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Distinct visual-testing contribution from the 2009 Sikuli paper. The institutional abstract and published-version citation supply the retained evidence. Exact publication day and operating-system coverage are not established in the accessible institutional abstract.", "pages": "1535-1544", "pdf_url": null, "publisher": null, "series": null, "title": "GUI Testing Using Computer Vision", "type": "conference-paper", "url": "https://doi.org/10.1145/1753326.1753555", "venue": "Proceedings of the 28th International Conference on Human Factors in Computing Systems (CHI '10)", "volume": null }, "record_updated_at": null }, "id": "url:6262c757080f8838e62c", "issued": { "date-parts": [ [ 2010, 4 ] ] }, "note": "Publication date: 2010-04.", "page": "1535-1544", "title": "GUI Testing Using Computer Vision", "type": "paper-conference" }, { "URL": "https://aaai.org/Papers/AAAI/2007/AAAI07-240.pdf", "author": [ { "literal": "James Allen" }, { "literal": "Nathanael Chambers" }, { "literal": "George Ferguson" }, { "literal": "Lucian Galescu" }, { "literal": "Hyuckchul Jung" }, { "literal": "Mary Swift" }, { "literal": "William Taysom" } ], "citation-key": "cua_4e2f12a215bd1cadd864f498", "container-title": "Twenty-Second AAAI National Conference on Artificial Intelligence", "custom": { "canonical_source_url": "https://aaai.org/Papers/AAAI/2007/AAAI07-240.pdf", "catalog_id": "url:628b5251757bb3888e89", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": {}, "publication": { "authors": [ "James Allen", "Nathanael Chambers", "George Ferguson", "Lucian Galescu", "Hyuckchul Jung", "Mary Swift", "William Taysom" ], "date_basis": "Supplied year precision: 2007. Papers section: AAAI-2007", "date_parts": [ 2007 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://aaai.org/Papers/AAAI/2007/AAAI07-240.pdf", "https://www.cs.rochester.edu/research/cisd/projects/plow/" ], "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 ordered names follow the original published paper, without expanding initials or replacing names from secondary indexes. DOI and volume number are not supplied in the retained primary sources. No exact publication month/day is established.", "pages": "1514-1519", "pdf_url": "https://cdn.aaai.org/AAAI/2007/AAAI07-240.pdf", "publisher": null, "series": null, "title": "PLOW: A Collaborative Task Learning Agent", "type": "conference-paper", "url": "https://aaai.org/Papers/AAAI/2007/AAAI07-240.pdf", "venue": "Twenty-Second AAAI National Conference on Artificial Intelligence", "volume": null }, "record_updated_at": null }, "id": "url:628b5251757bb3888e89", "issued": { "date-parts": [ [ 2007 ] ] }, "note": "Publication date: 2007.", "page": "1514-1519", "title": "PLOW: A Collaborative Task Learning Agent", "type": "paper-conference" }, { "DOI": "10.1145/3210240.3210339", "URL": "https://doi.org/10.1145/3210240.3210339", "author": [ { "literal": "Toby Jia-Jun Li" }, { "literal": "Oriana Riva" } ], "citation-key": "cua_93605b13ec414a1e08029b6d", "container-title": "The 16th Annual International Conference on Mobile Systems, Applications, and Services", "custom": { "canonical_source_url": "https://doi.org/10.1145/3210240.3210339", "catalog_id": "url:901ca855640457dfe2f1", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": { "doi": "10.1145/3210240.3210339" }, "publication": { "authors": [ "Toby Jia-Jun Li", "Oriana Riva" ], "date_basis": "Supplied month precision: 2018-06. Publication line: MobiSys 2018, June 2018", "date_parts": [ 2018, 6 ], "doi": "10.1145/3210240.3210339", "event_dates": null, "evidence_urls": [ "https://www.microsoft.com/en-us/research/publication/kite-building-conversational-bots-mobile-apps/", "https://www.microsoft.com/en-us/research/wp-content/uploads/2018/05/kite_mobisys18.pdf" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Final proceedings page range and volume are not established in the retained first-party citation. The paper states a 14-page extent, not a page range. Exact publication day is unknown.", "pages": null, "pdf_url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2018/05/kite_mobisys18.pdf", "publisher": null, "series": null, "title": "Kite: Building Conversational Bots from Mobile Apps", "type": "conference-paper", "url": "https://doi.org/10.1145/3210240.3210339", "venue": "The 16th Annual International Conference on Mobile Systems, Applications, and Services", "volume": null }, "record_updated_at": null }, "id": "url:901ca855640457dfe2f1", "issued": { "date-parts": [ [ 2018, 6 ] ] }, "note": "Publication date: 2018-06.", "title": "Kite: Building Conversational Bots from Mobile Apps", "type": "paper-conference" }, { "DOI": "10.1145/3242587.3242661", "URL": "https://doi.org/10.1145/3242587.3242661", "author": [ { "literal": "Sarah E. Chasins" }, { "literal": "Maria Mueller" }, { "literal": "Rastislav Bodik" } ], "citation-key": "cua_b85f11762562177944b6898f", "container-title": "Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology", "custom": { "canonical_source_url": "https://doi.org/10.1145/3242587.3242661", "catalog_id": "url:97c0b1896525632434e2", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": { "doi": "10.1145/3242587.3242661" }, "publication": { "authors": [ "Sarah E. Chasins", "Maria Mueller", "Rastislav Bodik" ], "date_basis": "Supplied year precision: 2018. Rousillon entry: UIST 2018", "date_parts": [ 2018 ], "doi": "10.1145/3242587.3242661", "event_dates": null, "evidence_urls": [ "https://schasins.com/papers/", "https://schasins.com/assets/papers/rousillon.pdf" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "This is browser interaction learned from demonstrations, rather than a generic server-side crawling library. Final proceedings page range and volume are not established. Manuscript pages 1-13 are not substituted for publisher pagination. Exact publication month/day is not inferred from conference dates.", "pages": null, "pdf_url": "https://schasins.com/assets/papers/rousillon.pdf", "publisher": null, "series": null, "title": "Rousillon: Scraping Distributed Hierarchical Web Data", "type": "conference-paper", "url": "https://doi.org/10.1145/3242587.3242661", "venue": "Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology", "volume": null }, "record_updated_at": null }, "id": "url:97c0b1896525632434e2", "issued": { "date-parts": [ [ 2018 ] ] }, "note": "Publication date: 2018.", "title": "Rousillon: Scraping Distributed Hierarchical Web Data", "type": "paper-conference" }, { "DOI": "10.1145/1622176.1622213", "URL": "https://doi.org/10.1145/1622176.1622213", "author": [ { "literal": "Tom Yeh" }, { "literal": "Tsung-Hsiang Chang" }, { "literal": "Robert C. Miller" } ], "citation-key": "cua_510831381c08385eb74fb95e", "container-title": "Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology (UIST '09)", "custom": { "canonical_source_url": "https://doi.org/10.1145/1622176.1622213", "catalog_id": "url:a4cdb2ee0d07d3980651", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": { "doi": "10.1145/1622176.1622213" }, "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 }, "record_updated_at": null }, "id": "url:a4cdb2ee0d07d3980651", "issued": { "date-parts": [ [ 2009, 10 ] ] }, "note": "Publication date: 2009-10.", "page": "183-192", "title": "Sikuli: Using GUI screenshots for search and automation", "type": "paper-conference" }, { "DOI": "10.1145/3126594.3126651", "URL": "https://doi.org/10.1145/3126594.3126651", "author": [ { "literal": "Biplab Deka" }, { "literal": "Zifeng Huang" }, { "literal": "Chad Franzen" }, { "literal": "Joshua Hibschman" }, { "literal": "Daniel Afergan" }, { "literal": "Yang Li" }, { "literal": "Jeffrey Nichols" }, { "literal": "Ranjitha Kumar" } ], "citation-key": "cua_402ed654426712089390317c", "container-title": "UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology", "custom": { "canonical_source_url": "https://doi.org/10.1145/3126594.3126651", "catalog_id": "url:b560b5d6abaab98483f6", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": "2017-10-20", "identifiers": { "doi": "10.1145/3126594.3126651" }, "publication": { "authors": [ "Biplab Deka", "Zifeng Huang", "Chad Franzen", "Joshua Hibschman", "Daniel Afergan", "Yang Li", "Jeffrey Nichols", "Ranjitha Kumar" ], "date_basis": "Supplied day precision: 2017-10-20. PDF cover, Published: 20 October 2017 The 18 January 2026 download date and October 22-25 conference dates are not publication dates.", "date_parts": [ 2017, 10, 20 ], "doi": "10.1145/3126594.3126651", "event_dates": null, "evidence_urls": [ "https://danafergan.com/publications/deka2017rico.pdf", "https://dev.interactionmining.org/archive/rico" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The paper is a distinct resource from the already cataloged Rico dataset (url:0b134b082a7bd507fc6a). The publisher PDF describes 9.7k apps and 72k screens; the project page describes 9.3k apps and 66k screens. The annotation intentionally supplies no merged size claim. No volume number is supplied for this proceedings article.", "pages": "845-854", "pdf_url": "https://danafergan.com/publications/deka2017rico.pdf", "publisher": null, "series": null, "title": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications", "type": "conference-paper", "url": "https://doi.org/10.1145/3126594.3126651", "venue": "UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology", "volume": null }, "record_updated_at": null }, "id": "url:b560b5d6abaab98483f6", "issued": { "date-parts": [ [ 2017, 10, 20 ] ] }, "note": "Publication date: 2017-10-20.", "page": "845-854", "title": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications", "type": "paper-conference" }, { "URL": "https://ieeexplore.ieee.org/document/8506506", "author": [ { "literal": "Toby Jia-Jun Li" }, { "literal": "Igor Labutov" }, { "literal": "Xiaohan Nancy Li" }, { "literal": "Xiaoyi Zhang" }, { "literal": "Wenze Shi" }, { "literal": "Wanling Ding" }, { "literal": "Tom M. Mitchell" }, { "literal": "Brad A. Myers" } ], "citation-key": "cua_753e73012e6a2483f242138b", "container-title": "Proceedings of the 2018 IEEE Symposium on Visual Languages and Human-Centric Computing", "custom": { "canonical_source_url": "https://ieeexplore.ieee.org/document/8506506", "catalog_id": "url:ba2c664c1b3c6f1b172f", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": {}, "publication": { "authors": [ "Toby Jia-Jun Li", "Igor Labutov", "Xiaohan Nancy Li", "Xiaoyi Zhang", "Wenze Shi", "Wanling Ding", "Tom M. Mitchell", "Brad A. Myers" ], "date_basis": "Supplied year precision: 2018. APPINITE publication citation: VL/HCC 2018", "date_parts": [ 2018 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://toby.li/files/TobyLi-VLHCC18-APPINITE.pdf", "https://www.cs.cmu.edu/~NatProg/sugilite.html", "https://toby.li/publications/" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The base SUGILITE framework and later PUMICE work are distinct publications; this paper focuses on resolving data-description ambiguity in demonstrations. Author-hosted manuscript and institutional publication lists supply the retained evidence. DOI, final page range, and exact publication day remain unknown.", "pages": null, "pdf_url": "https://toby.li/files/TobyLi-VLHCC18-APPINITE.pdf", "publisher": null, "series": null, "title": "APPINITE: A Multi-Modal Interface for Specifying Data Descriptions in Programming by Demonstration Using Natural Language Instructions", "type": "conference-paper", "url": "https://ieeexplore.ieee.org/document/8506506", "venue": "Proceedings of the 2018 IEEE Symposium on Visual Languages and Human-Centric Computing", "volume": null }, "record_updated_at": null }, "id": "url:ba2c664c1b3c6f1b172f", "issued": { "date-parts": [ [ 2018 ] ] }, "note": "Publication date: 2018.", "title": "APPINITE: A Multi-Modal Interface for Specifying Data Descriptions in Programming by Demonstration Using Natural Language Instructions", "type": "paper-conference" }, { "URL": "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "author": [ { "literal": "Fei Tang" }, { "literal": "Zhangxuan Gu" }, { "literal": "Zhengxi Lu" }, { "literal": "Shangzhan Zhang" }, { "literal": "Zhengwen Zeng" }, { "literal": "Shuheng Shen" }, { "literal": "Changhua Meng" }, { "literal": "Yuchen Yan" }, { "literal": "Wenqi Zhang" }, { "literal": "Yongliang Shen" }, { "literal": "Weiming Lu" }, { "literal": "Yueting Zhuang" } ], "citation-key": "cua_a6fbf231c6d3a11f67403503", "container-title": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "custom": { "canonical_source_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "catalog_id": "url:beb8f1fd6b945ffc9d93", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": {}, "publication": { "authors": [ "Fei Tang", "Zhangxuan Gu", "Zhengxi Lu", "Shangzhan Zhang", "Zhengwen Zeng", "Shuheng Shen", "Changhua Meng", "Yuchen Yan", "Wenqi Zhang", "Yongliang Shen", "Weiming Lu", "Yueting Zhuang" ], "date_basis": "Explicit publisher metadata: month = {June}, year = {2026}; precision=month.", "date_parts": [ 2026, 6 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "https://openaccess.thecvf.com/content/CVPR2026/papers/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.pdf" ], "identity_basis": "No title/DOI/canonical URL match in the current paper catalog or raw archive; closest substantive same-team works were reread and have different contributions.", "issue": null, "notes": "CVF open-access accepted version; PDF states that the final proceedings version is on IEEE Xplore.", "pages": "13007-13016", "pdf_url": "https://openaccess.thecvf.com/content/CVPR2026/papers/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.pdf", "publisher": null, "series": null, "title": "GUI-SAGE: Enhancing GUI Automation with Self-Explanatory Learning", "type": "conference-paper", "url": "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "volume": null }, "record_updated_at": null }, "id": "url:beb8f1fd6b945ffc9d93", "issued": { "date-parts": [ [ 2026, 6 ] ] }, "note": "Publication date: 2026-06.", "page": "13007-13016", "title": "GUI-SAGE: Enhancing GUI Automation with Self-Explanatory Learning", "type": "paper-conference" }, { "URL": "https://acypher.com/Publications/CHI91/EagerCHI.html", "author": [ { "literal": "Allen Cypher" } ], "citation-key": "cua_79e3af204750d438f5d43781", "container-title": "Proceedings of CHI '91", "custom": { "canonical_source_url": "https://acypher.com/Publications/CHI91/EagerCHI.html", "catalog_id": "url:bf0c11018e49dff6aeec", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": {}, "publication": { "authors": [ "Allen Cypher" ], "date_basis": "Supplied year precision: 1991. Opening CHI 1991 citation and copyright", "date_parts": [ 1991 ], "doi": null, "event_dates": null, "evidence_urls": [ "https://acypher.com/Eager/", "https://acypher.com/Publications/CHI91/EagerCHI.html" ], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The 1991 conference paper is kept distinct from the 1991 video and 1993/1995 reprints listed on the author project page. Macintosh/HyperCard is tagged desktop; it is not represented as support for contemporary macOS. DOI not verified in a retained first-party source. Exact publication month/day is not inferred from conference dates.", "pages": "33-39", "pdf_url": null, "publisher": null, "series": null, "title": "Eager: Programming Repetitive Tasks by Example", "type": "conference-paper", "url": "https://acypher.com/Publications/CHI91/EagerCHI.html", "venue": "Proceedings of CHI '91", "volume": null }, "record_updated_at": null }, "id": "url:bf0c11018e49dff6aeec", "issued": { "date-parts": [ [ 1991 ] ] }, "note": "Publication date: 1991.", "page": "33-39", "title": "Eager: Programming Repetitive Tasks by Example", "type": "paper-conference" }, { "DOI": "10.1145/1240624.1240767", "URL": "https://doi.org/10.1145/1240624.1240767", "author": [ { "literal": "Greg Little" }, { "literal": "Tessa A. Lau" }, { "literal": "Allen Cypher" }, { "literal": "James Lin" }, { "literal": "Eben M. Haber" }, { "literal": "Eser Kandogan" } ], "citation-key": "cua_1b4a3a269ca9f1884a566476", "container-title": "CHI 2007 Proceedings", "custom": { "canonical_source_url": "https://doi.org/10.1145/1240624.1240767", "catalog_id": "url:cccd967aa993404d74d0", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "first_published_at": null, "identifiers": { "doi": "10.1145/1240624.1240767" }, "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 }, "record_updated_at": null }, "id": "url:cccd967aa993404d74d0", "issued": { "date-parts": [ [ 2007 ] ] }, "note": "Publication date: 2007.", "page": "943-946", "title": "Koala: Capture, Share, Automate, Personalize Business Processes on the Web", "type": "paper-conference" } ]