[ { "URL": "https://arxiv.org/abs/2005.03776v2", "archive": "arXiv", "archive_location": "2005.03776", "author": [ { "literal": "Yang Li" }, { "literal": "Jiacong He" }, { "literal": "Xin Zhou" }, { "literal": "Yuan Zhang" }, { "literal": "Jason Baldridge" } ], "citation-key": "arxiv_2005_03776", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3af7b45455ffbd616e8cdf5612b19275ecb7bf07b1065af9f5b724ae19e96fb4", "submitted_at": "2020-05-07T21:41:40Z", "updated_at": "2020-06-05T02:11:56Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2005.03776v2" }, "canonical_source_url": "https://arxiv.org/abs/2005.03776", "catalog_id": "arxiv:2005.03776", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2020-05-07", "identifiers": { "arxiv": "2005.03776" }, "publication": { "authors": [ "Yang Li", "Jiacong He", "Xin Zhou", "Yuan Zhang", "Jason Baldridge" ], "date_basis": "Explicit publisher metadata: 2020/7; precision=month.", "date_parts": [ 2020, 7 ], "doi": "10.18653/v1/2020.acl-main.729", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2020.acl-main.729/" ], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "8198-8210", "pdf_url": "https://aclanthology.org/2020.acl-main.729.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Mapping Natural Language Instructions to Mobile UI Action Sequences", "type": "conference-paper", "url": "https://aclanthology.org/2020.acl-main.729/", "venue": "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", "volume": null }, "record_updated_at": "2020-06-05" }, "genre": "preprint", "id": "arxiv:2005.03776", "issued": { "date-parts": [ [ 2020, 5, 7 ] ] }, "note": "First published: 2020-05-07; Recorded arXiv version: v2; Recorded version updated: 2020-06-05T02:11:56Z.", "title": "Mapping Natural Language Instructions to Mobile UI Action Sequences", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2012.12350v2", "archive": "arXiv", "archive_location": "2012.12350", "author": [ { "literal": "Zecheng He" }, { "literal": "Srinivas Sunkara" }, { "literal": "Xiaoxue Zang" }, { "literal": "Ying Xu" }, { "literal": "Lijuan Liu" }, { "literal": "Nevan Wichers" }, { "literal": "Gabriel Schubiner" }, { "literal": "Ruby Lee" }, { "literal": "Jindong Chen" }, { "literal": "Blaise Agüera y Arcas" } ], "citation-key": "arxiv_2012_12350", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "51fdddb9a3d8a6090875719a51b22008b1f43bc38c6cfe1713a49a52f7e8434c", "submitted_at": "2020-12-22T20:49:52Z", "updated_at": "2021-01-25T20:37:39Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2012.12350v2" }, "canonical_source_url": "https://arxiv.org/abs/2012.12350", "catalog_id": "arxiv:2012.12350", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2020-12-22", "identifiers": { "arxiv": "2012.12350" }, "record_updated_at": "2021-01-25" }, "genre": "preprint", "id": "arxiv:2012.12350", "issued": { "date-parts": [ [ 2020, 12, 22 ] ] }, "note": "First published: 2020-12-22; Recorded arXiv version: v2; Recorded version updated: 2021-01-25T20:37:39Z.", "title": "ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2305.11854v4", "archive": "arXiv", "archive_location": "2305.11854", "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", "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": "record", "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" }, "genre": "preprint", "id": "arxiv:2305.11854", "issued": { "date-parts": [ [ 2023, 5, 19 ] ] }, "note": "First published: 2023-05-19; Recorded arXiv version: v4; Recorded version updated: 2024-02-25T16:21:00Z.", "title": "Multimodal Web Navigation with Instruction-Finetuned Foundation Models", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2306.00245v2", "archive": "arXiv", "archive_location": "2306.00245", "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", "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": "record", "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" }, "genre": "preprint", "id": "arxiv:2306.00245", "issued": { "date-parts": [ [ 2023, 5, 31 ] ] }, "note": "First published: 2023-05-31; Recorded arXiv version: v2; Recorded version updated: 2023-12-06T23:46:36Z.", "title": "From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2404.08755v1", "archive": "arXiv", "archive_location": "2404.08755", "author": [ { "literal": "Nicolai Dorka" }, { "literal": "Janusz Marecki" }, { "literal": "Ammar Anwar" } ], "citation-key": "arxiv_2404_08755", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a2f255b2c2870d9fbe5a543f2a0e09a30c3154fa0c13e9f46eedcefc11d2be43", "submitted_at": "2024-04-12T18:28:44Z", "updated_at": "2024-04-12T18:28:44Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2404.08755v1" }, "canonical_source_url": "https://arxiv.org/abs/2404.08755", "catalog_id": "arxiv:2404.08755", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-04-12", "identifiers": { "arxiv": "2404.08755" }, "record_updated_at": "2024-04-12" }, "genre": "preprint", "id": "arxiv:2404.08755", "issued": { "date-parts": [ [ 2024, 4, 12 ] ] }, "note": "First published: 2024-04-12; Recorded arXiv version: v1; Recorded version updated: 2024-04-12T18:28:44Z.", "title": "Training a Vision Language Model as Smartphone Assistant", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2405.15341v2", "archive": "arXiv", "archive_location": "2405.15341", "author": [ { "literal": "Abdur Rahman" }, { "literal": "Rajat Chawla" }, { "literal": "Muskaan Kumar" }, { "literal": "Arkajit Datta" }, { "literal": "Adarsh Jha" }, { "literal": "Mukunda NS" }, { "literal": "Ishaan Bhola" } ], "citation-key": "arxiv_2405_15341", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e7cb6087a48596442e1d191bf1313e9459ad62c02c3104ee481cb72cb00e56b1", "submitted_at": "2024-05-24T08:21:45Z", "updated_at": "2024-07-21T07:34:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2405.15341v2" }, "canonical_source_url": "https://arxiv.org/abs/2405.15341", "catalog_id": "arxiv:2405.15341", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-05-24", "identifiers": { "arxiv": "2405.15341" }, "record_updated_at": "2024-07-21" }, "genre": "preprint", "id": "arxiv:2405.15341", "issued": { "date-parts": [ [ 2024, 5, 24 ] ] }, "note": "First published: 2024-05-24; Recorded arXiv version: v2; Recorded version updated: 2024-07-21T07:34:44Z.", "title": "V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLM", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2409.14818v2", "archive": "arXiv", "archive_location": "2409.14818", "author": [ { "literal": "Qinzhuo Wu" }, { "literal": "Weikai Xu" }, { "literal": "Wei Liu" }, { "literal": "Tao Tan" }, { "literal": "Jianfeng Liu" }, { "literal": "Ang Li" }, { "literal": "Jian Luan" }, { "literal": "Bin Wang" }, { "literal": "Shuo Shang" } ], "citation-key": "arxiv_2409_14818", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cc22337ef29946dffcf7149df1008fd6cf02350c68d21ec0386e6485f5a14ebf", "submitted_at": "2024-09-23T08:47:54Z", "updated_at": "2024-10-03T05:23:22Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.14818v2" }, "canonical_source_url": "https://arxiv.org/abs/2409.14818", "catalog_id": "arxiv:2409.14818", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-09-23", "identifiers": { "arxiv": "2409.14818" }, "publication": { "authors": [ "Qinzhuo Wu", "Weikai Xu", "Wei Liu", "Tao Tan", "Jianfeng Liu", "Ang Li", "Jian Luan", "Bin Wang", "Shuo Shang" ], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 11 ], "doi": "10.18653/v1/2024.findings-emnlp.599", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2024.findings-emnlp.599/", "https://aclanthology.org/2024.findings-emnlp.599.pdf" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the publisher PDF, page 1. The landing page and its BibTeX list the fifth author as Liujian Liujianfeng; the PDF names Jianfeng Liu.", "pages": "10231-10251", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.599.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.599/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null }, "record_updated_at": "2024-10-03" }, "genre": "preprint", "id": "arxiv:2409.14818", "issued": { "date-parts": [ [ 2024, 9, 23 ] ] }, "note": "First published: 2024-09-23; Recorded arXiv version: v2; Recorded version updated: 2024-10-03T05:23:22Z.", "title": "MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2410.17883v2", "archive": "arXiv", "archive_location": "2410.17883", "author": [ { "literal": "Filippos Christianos" }, { "literal": "Georgios Papoudakis" }, { "literal": "Thomas Coste" }, { "literal": "Jianye Hao" }, { "literal": "Jun Wang" }, { "literal": "Kun Shao" } ], "citation-key": "arxiv_2410_17883", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9f6eb76587ef91a21942d34ba9ee7ba0ebc846277b12c69ecb179c2b2d1720df", "submitted_at": "2024-10-23T13:57:00Z", "updated_at": "2025-02-12T17:51:51Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.17883v2" }, "canonical_source_url": "https://arxiv.org/abs/2410.17883", "catalog_id": "arxiv:2410.17883", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-10-23", "identifiers": { "arxiv": "2410.17883" }, "record_updated_at": "2025-02-12" }, "genre": "preprint", "id": "arxiv:2410.17883", "issued": { "date-parts": [ [ 2024, 10, 23 ] ] }, "note": "First published: 2024-10-23; Recorded arXiv version: v2; Recorded version updated: 2025-02-12T17:51:51Z.", "title": "Lightweight Neural App Control", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2506.11127v3", "archive": "arXiv", "archive_location": "2506.11127", "author": [ { "literal": "Wenkang Han" }, { "literal": "Zhixiong Zeng" }, { "literal": "Jing Huang" }, { "literal": "Shu Jiang" }, { "literal": "Liming Zheng" }, { "literal": "Longrong Yang" }, { "literal": "Haibo Qiu" }, { "literal": "Chang Yao" }, { "literal": "Jingyuan Chen" }, { "literal": "Lin Ma" } ], "citation-key": "arxiv_2506_11127", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3cce7c2e1623ec841e8afed03c2e8e0c6f969f3dd05d53ddc4ef11e74310c21c", "submitted_at": "2025-06-10T12:16:27Z", "updated_at": "2025-11-26T07:48:14Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2506.11127v3" }, "canonical_source_url": "https://arxiv.org/abs/2506.11127", "catalog_id": "arxiv:2506.11127", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-10", "identifiers": { "arxiv": "2506.11127" }, "record_updated_at": "2025-11-26" }, "genre": "preprint", "id": "arxiv:2506.11127", "issued": { "date-parts": [ [ 2025, 6, 10 ] ] }, "note": "First published: 2025-06-10; Recorded arXiv version: v3; Recorded version updated: 2025-11-26T07:48:14Z.", "title": "UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2509.02322v1", "archive": "arXiv", "archive_location": "2509.02322", "author": [ { "literal": "Longrong Yang" }, { "literal": "Zhixiong Zeng" }, { "literal": "Yufeng Zhong" }, { "literal": "Jing Huang" }, { "literal": "Liming Zheng" }, { "literal": "Lei Chen" }, { "literal": "Haibo Qiu" }, { "literal": "Zequn Qin" }, { "literal": "Lin Ma" }, { "literal": "Xi Li" } ], "citation-key": "arxiv_2509_02322", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "227630b3a257557262ed25eb21906a129eb35c6c5d2de7c5754f919dd281c4bd", "submitted_at": "2025-09-02T13:47:54Z", "updated_at": "2025-09-02T13:47:54Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.02322v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.02322", "catalog_id": "arxiv:2509.02322", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-02", "identifiers": { "arxiv": "2509.02322" }, "record_updated_at": "2025-09-02" }, "genre": "preprint", "id": "arxiv:2509.02322", "issued": { "date-parts": [ [ 2025, 9, 2 ] ] }, "note": "First published: 2025-09-02; Recorded arXiv version: v1; Recorded version updated: 2025-09-02T13:47:54Z.", "title": "OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.17328v1", "archive": "arXiv", "archive_location": "2509.17328", "author": [ { "literal": "Hongxin Li" }, { "literal": "Jingran Su" }, { "literal": "Jingfan Chen" }, { "literal": "Zheng Ju" }, { "literal": "Yuntao Chen" }, { "literal": "Qing Li" }, { "literal": "Zhaoxiang Zhang" } ], "citation-key": "arxiv_2509_17328", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "97b7c0690ba7deb7dbbdac6ac94dd82e3864c440cb4325bf143ad735919bb08b", "submitted_at": "2025-09-22T03:04:53Z", "updated_at": "2025-09-22T03:04:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.17328v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.17328", "catalog_id": "arxiv:2509.17328", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-22", "identifiers": { "arxiv": "2509.17328" }, "record_updated_at": "2025-09-22" }, "genre": "preprint", "id": "arxiv:2509.17328", "issued": { "date-parts": [ [ 2025, 9, 22 ] ] }, "note": "First published: 2025-09-22; Recorded arXiv version: v1; Recorded version updated: 2025-09-22T03:04:53Z.", "title": "UIPro: Unleashing Superior Interaction Capability For GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.21552v2", "archive": "arXiv", "archive_location": "2509.21552", "author": [ { "literal": "Yu Zhao" }, { "literal": "Wei-Ning Chen" }, { "literal": "Huseyin Atahan Inan" }, { "literal": "Samuel Kessler" }, { "literal": "Lu Wang" }, { "literal": "Lukas Wutschitz" }, { "literal": "Fangkai Yang" }, { "literal": "Chaoyun Zhang" }, { "literal": "Pasquale Minervini" }, { "literal": "Saravan Rajmohan" }, { "literal": "Robert Sim" } ], "citation-key": "arxiv_2509_21552", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "83fa51d3642fa7786f7f6c44fcf5d5ab5876d7ae26e5f6184ddff4d5e2009181", "submitted_at": "2025-09-25T20:38:01Z", "updated_at": "2026-05-25T20:58:59Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.21552v2" }, "canonical_source_url": "https://arxiv.org/abs/2509.21552", "catalog_id": "arxiv:2509.21552", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-25", "identifiers": { "arxiv": "2509.21552" }, "record_updated_at": "2026-05-25" }, "genre": "preprint", "id": "arxiv:2509.21552", "issued": { "date-parts": [ [ 2025, 9, 25 ] ] }, "note": "First published: 2025-09-25; Recorded arXiv version: v2; Recorded version updated: 2026-05-25T20:58:59Z.", "title": "Learning GUI Grounding with Spatial Reasoning from Visual Feedback", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2601.18305v2", "archive": "arXiv", "archive_location": "2601.18305", "author": [ { "literal": "Xuan Wang" }, { "literal": "Siyuan Su" }, { "literal": "Quantong Fu" }, { "literal": "Yongxiang Hu" }, { "literal": "Yangfan Zhou" } ], "citation-key": "arxiv_2601_18305", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cb90eed33e989d38cd4058d54ba7d073f1b8e5c1453a9106dfe5e533da7b08a1", "submitted_at": "2026-01-26T09:35:10Z", "updated_at": "2026-08-20T07:50:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.18305v2" }, "canonical_source_url": "https://arxiv.org/abs/2601.18305", "catalog_id": "arxiv:2601.18305", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-26", "identifiers": { "arxiv": "2601.18305" }, "record_updated_at": "2026-08-20" }, "genre": "preprint", "id": "arxiv:2601.18305", "issued": { "date-parts": [ [ 2026, 1, 26 ] ] }, "note": "First published: 2026-01-26; Recorded arXiv version: v2; Recorded version updated: 2026-08-20T07:50:44Z.", "title": "SwipeGen: Bridging the Execution Gap in GUI Agents via Human-like Swipe Synthesis", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.17365v1", "archive": "arXiv", "archive_location": "2602.17365", "author": [ { "literal": "Yiming Guan" }, { "literal": "Rui Yu" }, { "literal": "John Zhang" }, { "literal": "Lu Wang" }, { "literal": "Chaoyun Zhang" }, { "literal": "Liqun Li" }, { "literal": "Bo Qiao" }, { "literal": "Si Qin" }, { "literal": "He Huang" }, { "literal": "Fangkai Yang" }, { "literal": "Pu Zhao" }, { "literal": "Lukas Wutschitz" }, { "literal": "Samuel Kessler" }, { "literal": "Huseyin A Inan" }, { "literal": "Robert Sim" }, { "literal": "Saravan Rajmohan" }, { "literal": "Qingwei Lin" }, { "literal": "Dongmei Zhang" } ], "citation-key": "arxiv_2602_17365", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3d2237dd43f4c876ba69b68c1871ca3efd3aa501e93c86655eb2de6d9f35d2e8", "submitted_at": "2026-02-19T13:48:29Z", "updated_at": "2026-02-19T13:48:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.17365v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.17365", "catalog_id": "arxiv:2602.17365", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-19", "identifiers": { "arxiv": "2602.17365" }, "record_updated_at": "2026-02-19" }, "genre": "preprint", "id": "arxiv:2602.17365", "issued": { "date-parts": [ [ 2026, 2, 19 ] ] }, "note": "First published: 2026-02-19; Recorded arXiv version: v1; Recorded version updated: 2026-02-19T13:48:29Z.", "title": "Computer-Using World Model", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.17588v4", "archive": "arXiv", "archive_location": "2602.17588", "author": [ { "literal": "Faria Huq" }, { "literal": "Zora Zhiruo Wang" }, { "literal": "Zhanqiu Guo" }, { "literal": "Venu Arvind Arangarajan" }, { "literal": "Tianyue Ou" }, { "literal": "Frank Xu" }, { "literal": "Shuyan Zhou" }, { "literal": "Graham Neubig" }, { "literal": "Jeffrey P. Bigham" } ], "citation-key": "arxiv_2602_17588", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fe83d38ece7cd8f39d932611abaf7a170e7cb9b7c9744bd1176eb42e73be85b5", "submitted_at": "2026-02-19T18:11:28Z", "updated_at": "2026-07-07T23:37:46Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2602.17588v4" }, "canonical_source_url": "https://arxiv.org/abs/2602.17588", "catalog_id": "arxiv:2602.17588", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-19", "identifiers": { "arxiv": "2602.17588" }, "record_updated_at": "2026-07-07" }, "genre": "preprint", "id": "arxiv:2602.17588", "issued": { "date-parts": [ [ 2026, 2, 19 ] ] }, "note": "First published: 2026-02-19; Recorded arXiv version: v4; Recorded version updated: 2026-07-07T23:37:46Z.", "title": "Modeling Distinct Human Interaction in Web Agents", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2603.12138v1", "archive": "arXiv", "archive_location": "2603.12138", "author": [ { "literal": "Rui Shao" }, { "literal": "Ruize Gao" }, { "literal": "Bin Xie" }, { "literal": "Yixing Li" }, { "literal": "Kaiwen Zhou" }, { "literal": "Shuai Wang" }, { "literal": "Weili Guan" }, { "literal": "Gongwei Chen" } ], "citation-key": "arxiv_2603_12138", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6421a7928b502cd431964e6f84a1a58d4cd16dbbf1d9b3d1ecc1c2b3dae863bf", "submitted_at": "2026-03-12T16:40:59Z", "updated_at": "2026-03-12T16:40:59Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.12138v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.12138", "catalog_id": "arxiv:2603.12138", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-12", "identifiers": { "arxiv": "2603.12138" }, "record_updated_at": "2026-03-12" }, "genre": "preprint", "id": "arxiv:2603.12138", "issued": { "date-parts": [ [ 2026, 3, 12 ] ] }, "note": "First published: 2026-03-12; Recorded arXiv version: v1; Recorded version updated: 2026-03-12T16:40:59Z.", "title": "HATS: Hardness-Aware Trajectory Synthesis for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.26211v1", "archive": "arXiv", "archive_location": "2603.26211", "author": [ { "literal": "Shrinidhi Kumbhar" }, { "literal": "Haofu Liao" }, { "literal": "Srikar Appalaraju" }, { "literal": "Kunwar Yashraj Singh" } ], "citation-key": "arxiv_2603_26211", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0838afd6777af3e3995fa3bf9645102f98962cccd81c1db438a007b4cd33c442", "submitted_at": "2026-03-27T09:34:07Z", "updated_at": "2026-03-27T09:34:07Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.26211v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.26211", "catalog_id": "arxiv:2603.26211", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-27", "identifiers": { "arxiv": "2603.26211" }, "record_updated_at": "2026-03-27" }, "genre": "preprint", "id": "arxiv:2603.26211", "issued": { "date-parts": [ [ 2026, 3, 27 ] ] }, "note": "First published: 2026-03-27; Recorded arXiv version: v1; Recorded version updated: 2026-03-27T09:34:07Z.", "title": "Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.12501v1", "archive": "arXiv", "archive_location": "2605.12501", "author": [ { "literal": "Miaosen Zhang" }, { "literal": "Xiaohan Zhao" }, { "literal": "Zhihong Tan" }, { "literal": "Zhou Huoshen" }, { "literal": "Yijia Fan" }, { "literal": "Yifan Yang" }, { "literal": "Kai Qiu" }, { "literal": "Bei Liu" }, { "literal": "Justin Wagle" }, { "literal": "Chenzhong Yin" }, { "literal": "Mingxi Cheng" }, { "literal": "Ji Li" }, { "literal": "Qi Dai" }, { "literal": "Chong Luo" }, { "literal": "Xu Yang" }, { "literal": "Xin Geng" }, { "literal": "Baining Guo" } ], "citation-key": "arxiv_2605_12501", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1fb57ba3cd858513d1da58d64a7c85388f12e331c9ea9f89204be5f43e6fec38", "submitted_at": "2026-05-12T17:59:58Z", "updated_at": "2026-05-12T17:59:58Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.12501v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.12501", "catalog_id": "arxiv:2605.12501", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-12", "identifiers": { "arxiv": "2605.12501" }, "record_updated_at": "2026-05-12" }, "genre": "preprint", "id": "arxiv:2605.12501", "issued": { "date-parts": [ [ 2026, 5, 12 ] ] }, "note": "First published: 2026-05-12; Recorded arXiv version: v1; Recorded version updated: 2026-05-12T17:59:58Z.", "title": "Covering Human Action Space for Computer Use: Data Synthesis and Benchmark", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.18758v2", "archive": "arXiv", "archive_location": "2605.18758", "author": [ { "literal": "Felix Henry" }, { "literal": "Lihan Lin" }, { "literal": "Jiangyou Zhu" }, { "literal": "Yangfan" }, { "literal": "Bingqian Zhang" }, { "literal": "Min Chen" }, { "literal": "Shiyu Huang" } ], "citation-key": "arxiv_2605_18758", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "99e8e0039ec99ef8f6a6ef3900cb74a62ddd5ae4f8df30629110969290028e6a", "submitted_at": "2026-04-03T08:57:06Z", "updated_at": "2026-09-28T02:42:06Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.18758v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.18758", "catalog_id": "arxiv:2605.18758", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-03", "identifiers": { "arxiv": "2605.18758" }, "record_updated_at": "2026-09-28" }, "genre": "preprint", "id": "arxiv:2605.18758", "issued": { "date-parts": [ [ 2026, 4, 3 ] ] }, "note": "First published: 2026-04-03; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T02:42:06Z.", "title": "OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2607.04425v2", "archive": "arXiv", "archive_location": "2607.04425", "author": [ { "literal": "Niu Lian" }, { "literal": "Tongbo Chen" }, { "literal": "Zhehao Yu" }, { "literal": "Chengzhen Duan" }, { "literal": "Fazhan Liu" }, { "literal": "Hui Liu" }, { "literal": "Pei Fu" }, { "literal": "Jian Luan" }, { "literal": "Heng Qu" }, { "literal": "Shu-Tao Xia" }, { "literal": "Jinpeng Wang" } ], "citation-key": "arxiv_2607_04425", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "32cb3020ccf25c31b805dc44218f5f9496cbc310e1df2906d8b15e5b60c31278", "submitted_at": "2026-07-05T17:37:12Z", "updated_at": "2026-08-10T13:11:37Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.04425v2" }, "canonical_source_url": "https://arxiv.org/abs/2607.04425", "catalog_id": "arxiv:2607.04425", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-05", "identifiers": { "arxiv": "2607.04425" }, "record_updated_at": "2026-08-10" }, "genre": "preprint", "id": "arxiv:2607.04425", "issued": { "date-parts": [ [ 2026, 7, 5 ] ] }, "note": "First published: 2026-07-05; Recorded arXiv version: v2; Recorded version updated: 2026-08-10T13:11:37Z.", "title": "UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2607.10079v3", "archive": "arXiv", "archive_location": "2607.10079", "author": [ { "literal": "Chengguang Gan" }, { "literal": "Hanjun Wei" }, { "literal": "Yunhao Liang" }, { "literal": "Zhixi Cai" }, { "literal": "Qinghao Zhang" }, { "literal": "Shiwen Ni" } ], "citation-key": "arxiv_2607_10079", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "37cfa436d182ed8fbc8823213b9173fbfcf9fb421e8d2ae89a093a5393c374ba", "submitted_at": "2026-07-11T02:08:46Z", "updated_at": "2026-07-16T03:28:43Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2607.10079v3" }, "canonical_source_url": "https://arxiv.org/abs/2607.10079", "catalog_id": "arxiv:2607.10079", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-11", "identifiers": { "arxiv": "2607.10079" }, "record_updated_at": "2026-07-16" }, "genre": "preprint", "id": "arxiv:2607.10079", "issued": { "date-parts": [ [ 2026, 7, 11 ] ] }, "note": "First published: 2026-07-11; Recorded arXiv version: v3; Recorded version updated: 2026-07-16T03:28:43Z.", "title": "MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2607.17050v1", "archive": "arXiv", "archive_location": "2607.17050", "author": [ { "literal": "Yaohan Yang" }, { "literal": "Minglei Shi" }, { "literal": "Borui Zhang" }, { "literal": "Jie Zhou" }, { "literal": "Jiwen Lu" } ], "citation-key": "arxiv_2607_17050", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6488798626abbec89ca739a0c5d188ae440484eb59b3be11f2b319ce742b22ec", "submitted_at": "2026-07-19T03:29:08Z", "updated_at": "2026-07-19T03:29:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.17050v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.17050", "catalog_id": "arxiv:2607.17050", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-19", "identifiers": { "arxiv": "2607.17050" }, "record_updated_at": "2026-07-19" }, "genre": "preprint", "id": "arxiv:2607.17050", "issued": { "date-parts": [ [ 2026, 7, 19 ] ] }, "note": "First published: 2026-07-19; Recorded arXiv version: v1; Recorded version updated: 2026-07-19T03:29:08Z.", "title": "EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.24112v1", "archive": "arXiv", "archive_location": "2607.24112", "author": [ { "literal": "Xiangyan Liu" }, { "literal": "Kaixin Li" }, { "literal": "Haonan Wang" }, { "literal": "Biao Wu" }, { "literal": "Meng Fang" }, { "literal": "Longxu Dou" }, { "literal": "Chao Du" }, { "literal": "Michael Qizhe Shieh" }, { "literal": "Tianyu Pang" } ], "citation-key": "arxiv_2607_24112", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4651964cbe45e4d740ed8f789753f82ae808e442d82c6598e7b3c997c09453c3", "submitted_at": "2026-07-27T07:54:08Z", "updated_at": "2026-07-27T07:54:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.24112v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.24112", "catalog_id": "arxiv:2607.24112", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-27", "identifiers": { "arxiv": "2607.24112" }, "record_updated_at": "2026-07-27" }, "genre": "preprint", "id": "arxiv:2607.24112", "issued": { "date-parts": [ [ 2026, 7, 27 ] ] }, "note": "First published: 2026-07-27; Recorded arXiv version: v1; Recorded version updated: 2026-07-27T07:54:08Z.", "title": "Scaling GUI Agents with Visual State Transitions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.21830v1", "archive": "arXiv", "archive_location": "2608.21830", "author": [ { "literal": "Chengyang Gu" }, { "literal": "Le Zhang" }, { "literal": "Jingbo Zhou" }, { "literal": "Yize Chen" }, { "literal": "Yu Shi" }, { "literal": "Siqi Bao" }, { "literal": "Zheng-Fan Wu" }, { "literal": "Hua Wu" }, { "literal": "Hui Xiong" } ], "citation-key": "arxiv_2608_21830", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9434f8da41679177f6978c039bd42fcacce543de2bd0e4ce05b62ab4d61ed761", "submitted_at": "2026-08-22T08:01:47Z", "updated_at": "2026-08-22T08:01:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.21830v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.21830", "catalog_id": "arxiv:2608.21830", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-22", "identifiers": { "arxiv": "2608.21830" }, "record_updated_at": "2026-08-22" }, "genre": "preprint", "id": "arxiv:2608.21830", "issued": { "date-parts": [ [ 2026, 8, 22 ] ] }, "note": "First published: 2026-08-22; Recorded arXiv version: v1; Recorded version updated: 2026-08-22T08:01:47Z.", "title": "Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.25769v1", "archive": "arXiv", "archive_location": "2609.25769", "author": [ { "literal": "Yan Zhang" }, { "literal": "Pei Fu" }, { "literal": "Daiqing Wu" }, { "literal": "Huawen Shen" }, { "literal": "Ruoceng Zhang" }, { "literal": "Shaojie Zhang" }, { "literal": "Jiahui Yang" }, { "literal": "Yu Zhou" }, { "literal": "Can Ma" }, { "literal": "Zhenbo Luo" }, { "literal": "Jian Luan" } ], "citation-key": "arxiv_2609_25769", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d184b111aa2a9ad65dd57391b72bcef369c2bcd01ceb8e4f00f7a2320db856d8", "submitted_at": "2026-09-22T07:02:35Z", "updated_at": "2026-09-22T07:02:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.25769v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.25769", "catalog_id": "arxiv:2609.25769", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-22", "identifiers": { "arxiv": "2609.25769" }, "record_updated_at": "2026-09-22" }, "genre": "preprint", "id": "arxiv:2609.25769", "issued": { "date-parts": [ [ 2026, 9, 22 ] ] }, "note": "First published: 2026-09-22; Recorded arXiv version: v1; Recorded version updated: 2026-09-22T07:02:35Z.", "title": "Towards Omni-dimensional GUI Agent Navigation with Masked Trajectory Prediction", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.27353v1", "archive": "arXiv", "archive_location": "2609.27353", "author": [ { "literal": "Chengguang Gan" }, { "literal": "Yunhao Liang" }, { "literal": "QingHao Zhang" }, { "literal": "Shiwen Ni" } ], "citation-key": "arxiv_2609_27353", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2b2bda1c50fd47fabbe77c40a2938979a6a16b407b40f11737fc6f1fc795d090", "submitted_at": "2026-09-23T04:49:07Z", "updated_at": "2026-09-23T04:49:07Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.27353v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.27353", "catalog_id": "arxiv:2609.27353", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-23", "identifiers": { "arxiv": "2609.27353" }, "record_updated_at": "2026-09-23" }, "genre": "preprint", "id": "arxiv:2609.27353", "issued": { "date-parts": [ [ 2026, 9, 23 ] ] }, "note": "First published: 2026-09-23; Recorded arXiv version: v1; Recorded version updated: 2026-09-23T04:49:07Z.", "title": "Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.32511v1", "archive": "arXiv", "archive_location": "2609.32511", "author": [ { "literal": "Jinming Hu" }, { "literal": "Haodong Zhao" }, { "literal": "Qi Jia" }, { "literal": "Die Chen" }, { "literal": "Tianhang Zhao" }, { "literal": "Sufeng Duan" }, { "literal": "Gongshen Liu" } ], "citation-key": "arxiv_2609_32511", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ff1c4eff95094ea8ecf37b7bc621eebbd5e4a677b0e11240e802a72b9b229c7f", "submitted_at": "2026-09-26T11:59:39Z", "updated_at": "2026-09-26T11:59:39Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.32511v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.32511", "catalog_id": "arxiv:2609.32511", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-26", "identifiers": { "arxiv": "2609.32511" }, "record_updated_at": "2026-09-26" }, "genre": "preprint", "id": "arxiv:2609.32511", "issued": { "date-parts": [ [ 2026, 9, 26 ] ] }, "note": "First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T11:59:39Z.", "title": "Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.13092v1", "archive": "arXiv", "archive_location": "2610.13092", "author": [ { "literal": "Yuchen Ling" }, { "literal": "Shengcheng Yu" }, { "literal": "Zhenyu Chen" }, { "literal": "Chunrong Fang" } ], "citation-key": "arxiv_2610_13092", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fb5f0220266a43b74e7a5f547abbe78a54a2ef993fee5d27f67827cb9715f5dc", "submitted_at": "2026-10-09T06:45:23Z", "updated_at": "2026-10-09T06:45:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.13092v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.13092", "catalog_id": "arxiv:2610.13092", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-09", "identifiers": { "arxiv": "2610.13092" }, "record_updated_at": "2026-10-09" }, "genre": "preprint", "id": "arxiv:2610.13092", "issued": { "date-parts": [ [ 2026, 10, 9 ] ] }, "note": "First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T06:45:23Z.", "title": "When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.24372v1", "archive": "arXiv", "archive_location": "2610.24372", "author": [ { "literal": "Sizhe Tang" }, { "literal": "Hanhan Zhou" }, { "literal": "Jeffrey Svajlenko" }, { "literal": "Rashmi Gangadharaiah" } ], "citation-key": "arxiv_2610_24372", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9d6808cf26a609b50b7835ae3ecece0a13580aafcd589823f0b1eeff54732f69", "submitted_at": "2026-10-17T02:03:20Z", "updated_at": "2026-10-17T02:03:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.24372v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.24372", "catalog_id": "arxiv:2610.24372", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-17", "identifiers": { "arxiv": "2610.24372" }, "record_updated_at": "2026-10-17" }, "genre": "preprint", "id": "arxiv:2610.24372", "issued": { "date-parts": [ [ 2026, 10, 17 ] ] }, "note": "First published: 2026-10-17; Recorded arXiv version: v1; Recorded version updated: 2026-10-17T02:03:20Z.", "title": "Beyond Next-Screen Prediction: The Decision Value of GUI World Models", "type": "article", "version": "1" } ]