[ { "URL": "https://arxiv.org/abs/2310.18331v2", "archive": "arXiv", "archive_location": "2310.18331", "author": [ { "literal": "Jiarun Liu" }, { "literal": "Wentao Hu" }, { "literal": "Chunhong Zhang" } ], "citation-key": "arxiv_2310_18331", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c72eab40cdc28981cf83a753d88f5181b5441d82cd568265457fef96d75b36b6", "submitted_at": "2023-10-20T11:10:14Z", "updated_at": "2023-10-31T06:25:59Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2310.18331v2" }, "canonical_source_url": "https://arxiv.org/abs/2310.18331", "catalog_id": "arxiv:2310.18331", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2023-10-20", "identifiers": { "arxiv": "2310.18331" }, "record_updated_at": "2023-10-31" }, "genre": "preprint", "id": "arxiv:2310.18331", "issued": { "date-parts": [ [ 2023, 10, 20 ] ] }, "note": "First published: 2023-10-20; Recorded arXiv version: v2; Recorded version updated: 2023-10-31T06:25:59Z.", "title": "AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models", "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/2406.14314v3", "archive": "arXiv", "archive_location": "2406.14314", "author": [ { "literal": "Omri Berkovitch" }, { "literal": "Sapir Caduri" }, { "literal": "Noam Kahlon" }, { "literal": "Anatoly Efros" }, { "literal": "Avi Caciularu" }, { "literal": "Ido Dagan" } ], "citation-key": "arxiv_2406_14314", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a0bc798b69e59d1ec0ca8ecb0fab7a7ee6594f4d656ca4212b19be7e3085c0c5", "submitted_at": "2024-06-20T13:46:10Z", "updated_at": "2025-03-03T15:47:10Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2406.14314v3" }, "canonical_source_url": "https://arxiv.org/abs/2406.14314", "catalog_id": "arxiv:2406.14314", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-06-20", "identifiers": { "arxiv": "2406.14314" }, "record_updated_at": "2025-03-03" }, "genre": "preprint", "id": "arxiv:2406.14314", "issued": { "date-parts": [ [ 2024, 6, 20 ] ] }, "note": "First published: 2024-06-20; Recorded arXiv version: v3; Recorded version updated: 2025-03-03T15:47:10Z.", "title": "Identifying User Goals from UI Trajectories", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2410.00467v3", "archive": "arXiv", "archive_location": "2410.00467", "author": [ { "literal": "Shaoqing Zhang" }, { "literal": "Zhuosheng Zhang" }, { "literal": "Kehai Chen" }, { "literal": "Xinbei Ma" }, { "literal": "Muyun Yang" }, { "literal": "Tiejun Zhao" }, { "literal": "Min Zhang" } ], "citation-key": "arxiv_2410_00467", "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": "record", "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" }, "genre": "preprint", "id": "arxiv:2410.00467", "issued": { "date-parts": [ [ 2024, 10, 1 ] ] }, "note": "First published: 2024-10-01; Recorded arXiv version: v3; Recorded version updated: 2024-12-19T14:29:31Z.", "title": "Dynamic Planning for LLM-based Graphical User Interface Automation", "type": "article", "version": "3" }, { "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/2410.23555v1", "archive": "arXiv", "archive_location": "2410.23555", "author": [ { "literal": "Nalin Tiwary" }, { "literal": "Vardhan Dongre" }, { "literal": "Sanil Arun Chawla" }, { "literal": "Ashwin Lamani" }, { "literal": "Dilek Hakkani-Tür" } ], "citation-key": "arxiv_2410_23555", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1c67b1559410152607fc9d54abf25c37ef939c9f755f089bdf87d4f39393c085", "submitted_at": "2024-10-31T01:51:41Z", "updated_at": "2024-10-31T01:51:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2410.23555v1" }, "canonical_source_url": "https://arxiv.org/abs/2410.23555", "catalog_id": "arxiv:2410.23555", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-10-31", "identifiers": { "arxiv": "2410.23555" }, "record_updated_at": "2024-10-31" }, "genre": "preprint", "id": "arxiv:2410.23555", "issued": { "date-parts": [ [ 2024, 10, 31 ] ] }, "note": "First published: 2024-10-31; Recorded arXiv version: v1; Recorded version updated: 2024-10-31T01:51:41Z.", "title": "From Context to Action: Analysis of the Impact of State Representation and Context on the Generalization of Multi-Turn Web Navigation Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.00416v1", "archive": "arXiv", "archive_location": "2505.00416", "author": [ { "literal": "Jing Huang" }, { "literal": "Zhixiong Zeng" }, { "literal": "Wenkang Han" }, { "literal": "Yufeng Zhong" }, { "literal": "Liming Zheng" }, { "literal": "Shuai Fu" }, { "literal": "Jingyuan Chen" }, { "literal": "Lin Ma" } ], "citation-key": "arxiv_2505_00416", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e582c92521ec41a0a3daa0ca72b8c00250621289352b28400ee6d311c4a106eb", "submitted_at": "2025-05-01T09:27:13Z", "updated_at": "2025-05-01T09:27:13Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.00416v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.00416", "catalog_id": "arxiv:2505.00416", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-01", "identifiers": { "arxiv": "2505.00416" }, "record_updated_at": "2025-05-01" }, "genre": "preprint", "id": "arxiv:2505.00416", "issued": { "date-parts": [ [ 2025, 5, 1 ] ] }, "note": "First published: 2025-05-01; Recorded arXiv version: v1; Recorded version updated: 2025-05-01T09:27:13Z.", "title": "ScaleTrack: Scaling and back-tracking Automated GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.14418v3", "archive": "arXiv", "archive_location": "2505.14418", "author": [ { "literal": "Pengzhou Cheng" }, { "literal": "Haowen Hu" }, { "literal": "Zheng Wu" }, { "literal": "Zongru Wu" }, { "literal": "Tianjie Ju" }, { "literal": "Zhuosheng Zhang" }, { "literal": "Gongshen Liu" } ], "citation-key": "arxiv_2505_14418", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "815345ed44d70f40ce9784c212d269ffaaa476e5c2ea5cdbbaaeb98d22eba3cb", "submitted_at": "2025-05-20T14:29:18Z", "updated_at": "2026-06-15T06:42:51Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.14418v3" }, "canonical_source_url": "https://arxiv.org/abs/2505.14418", "catalog_id": "arxiv:2505.14418", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-20", "identifiers": { "arxiv": "2505.14418" }, "record_updated_at": "2026-06-15" }, "genre": "preprint", "id": "arxiv:2505.14418", "issued": { "date-parts": [ [ 2025, 5, 20 ] ] }, "note": "First published: 2025-05-20; Recorded arXiv version: v3; Recorded version updated: 2026-06-15T06:42:51Z.", "title": "Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2505.21496v1", "archive": "arXiv", "archive_location": "2505.21496", "author": [ { "literal": "Han Xiao" }, { "literal": "Guozhi Wang" }, { "literal": "Yuxiang Chai" }, { "literal": "Zimu Lu" }, { "literal": "Weifeng Lin" }, { "literal": "Hao He" }, { "literal": "Lue Fan" }, { "literal": "Liuyang Bian" }, { "literal": "Rui Hu" }, { "literal": "Liang Liu" }, { "literal": "Shuai Ren" }, { "literal": "Yafei Wen" }, { "literal": "Xiaoxin Chen" }, { "literal": "Aojun Zhou" }, { "literal": "Hongsheng Li" } ], "citation-key": "arxiv_2505_21496", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f19671a527de76b702e68311656e42feea88249716f68911a41ec80be205e4c", "submitted_at": "2025-05-27T17:58:06Z", "updated_at": "2025-05-27T17:58:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.21496v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.21496", "catalog_id": "arxiv:2505.21496", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-27", "identifiers": { "arxiv": "2505.21496" }, "record_updated_at": "2025-05-27" }, "genre": "preprint", "id": "arxiv:2505.21496", "issued": { "date-parts": [ [ 2025, 5, 27 ] ] }, "note": "First published: 2025-05-27; Recorded arXiv version: v1; Recorded version updated: 2025-05-27T17:58:06Z.", "title": "UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2507.03730v1", "archive": "arXiv", "archive_location": "2507.03730", "author": [ { "literal": "Gongwei Chen" }, { "literal": "Xurui Zhou" }, { "literal": "Rui Shao" }, { "literal": "Yibo Lyu" }, { "literal": "Kaiwen Zhou" }, { "literal": "Shuai Wang" }, { "literal": "Wentao Li" }, { "literal": "Yinchuan Li" }, { "literal": "Zhongang Qi" }, { "literal": "Liqiang Nie" } ], "citation-key": "arxiv_2507_03730", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "774e2515b563f75d4561daaa6a4b672423d917a3f50e98308ab448e2ae0731e5", "submitted_at": "2025-07-04T17:37:15Z", "updated_at": "2025-07-04T17:37:15Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2507.03730v1" }, "canonical_source_url": "https://arxiv.org/abs/2507.03730", "catalog_id": "arxiv:2507.03730", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-07-04", "identifiers": { "arxiv": "2507.03730" }, "record_updated_at": "2025-07-04" }, "genre": "preprint", "id": "arxiv:2507.03730", "issued": { "date-parts": [ [ 2025, 7, 4 ] ] }, "note": "First published: 2025-07-04; Recorded arXiv version: v1; Recorded version updated: 2025-07-04T17:37:15Z.", "title": "Less is More: Empowering GUI Agent with Context-Aware Simplification", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2507.21071v2", "archive": "arXiv", "archive_location": "2507.21071", "author": [ { "literal": "Qinglong Yang" }, { "literal": "Haoming Li" }, { "literal": "Haotian Zhao" }, { "literal": "Xiaokai Yan" }, { "literal": "Jingtao Ding" }, { "literal": "Fengli Xu" }, { "literal": "Yong Li" } ], "citation-key": "arxiv_2507_21071", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "947c85efc189635a118b823b8ca0787ff6b1c922d1af8b21a8686b7df9a27cf8", "submitted_at": "2025-06-09T06:38:41Z", "updated_at": "2026-03-16T09:14:01Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2507.21071v2" }, "canonical_source_url": "https://arxiv.org/abs/2507.21071", "catalog_id": "arxiv:2507.21071", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-09", "identifiers": { "arxiv": "2507.21071" }, "record_updated_at": "2026-03-16" }, "genre": "preprint", "id": "arxiv:2507.21071", "issued": { "date-parts": [ [ 2025, 6, 9 ] ] }, "note": "First published: 2025-06-09; Recorded arXiv version: v2; Recorded version updated: 2026-03-16T09:14:01Z.", "title": "FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2510.00413v2", "archive": "arXiv", "archive_location": "2510.00413", "author": [ { "literal": "Zikang Liu" }, { "literal": "Junyi Li" }, { "literal": "Wayne Xin Zhao" }, { "literal": "Dawei Gao" }, { "literal": "Yaliang Li" }, { "literal": "Ji-rong Wen" } ], "citation-key": "arxiv_2510_00413", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "277315ecc1a341c0a511bce84b87190fc0aeeb2306666ea8d4746aa8e9b39984", "submitted_at": "2025-10-01T01:48:39Z", "updated_at": "2025-10-04T15:23:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.00413v2" }, "canonical_source_url": "https://arxiv.org/abs/2510.00413", "catalog_id": "arxiv:2510.00413", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-01", "identifiers": { "arxiv": "2510.00413" }, "record_updated_at": "2025-10-04" }, "genre": "preprint", "id": "arxiv:2510.00413", "issued": { "date-parts": [ [ 2025, 10, 1 ] ] }, "note": "First published: 2025-10-01; Recorded arXiv version: v2; Recorded version updated: 2025-10-04T15:23:55Z.", "title": "PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2510.00536v2", "archive": "arXiv", "archive_location": "2510.00536", "author": [ { "literal": "Kung-Hsiang Huang" }, { "literal": "Haoyi Qiu" }, { "literal": "Yutong Dai" }, { "literal": "Caiming Xiong" }, { "literal": "Chien-Sheng Wu" } ], "citation-key": "arxiv_2510_00536", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e07a5a8f9c0aa39643bb919c2d637435669318420223d7d72b0ef3d733308852", "submitted_at": "2025-10-01T05:37:54Z", "updated_at": "2026-10-07T23:23:10Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.00536v2" }, "canonical_source_url": "https://arxiv.org/abs/2510.00536", "catalog_id": "arxiv:2510.00536", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-01", "identifiers": { "arxiv": "2510.00536" }, "record_updated_at": "2026-10-07" }, "genre": "preprint", "id": "arxiv:2510.00536", "issued": { "date-parts": [ [ 2025, 10, 1 ] ] }, "note": "First published: 2025-10-01; Recorded arXiv version: v2; Recorded version updated: 2026-10-07T23:23:10Z.", "title": "GUI-KV: Efficient GUI Agents via KV Cache with Spatio-Temporal Awareness", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2510.04373v2", "archive": "arXiv", "archive_location": "2510.04373", "author": [ { "literal": "Hadi Nekoei" }, { "literal": "Aman Jaiswal" }, { "literal": "Patrice Bechard" }, { "literal": "Oleh Shliazhko" }, { "literal": "Orlando Marquez Ayala" }, { "literal": "Mathieu Reymond" }, { "literal": "Massimo Caccia" }, { "literal": "Alexandre Drouin" }, { "literal": "Sarath Chandar" }, { "literal": "Alexandre Lacoste" } ], "citation-key": "arxiv_2510_04373", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0d4bd517ada9303e765827b3badfa2ee432bc5511ff4ee0cc42d937735e1c8de", "submitted_at": "2025-10-05T21:34:42Z", "updated_at": "2026-02-20T19:34:32Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.04373v2" }, "canonical_source_url": "https://arxiv.org/abs/2510.04373", "catalog_id": "arxiv:2510.04373", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-05", "identifiers": { "arxiv": "2510.04373" }, "record_updated_at": "2026-02-20" }, "genre": "preprint", "id": "arxiv:2510.04373", "issued": { "date-parts": [ [ 2025, 10, 5 ] ] }, "note": "First published: 2025-10-05; Recorded arXiv version: v2; Recorded version updated: 2026-02-20T19:34:32Z.", "title": "JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2510.09038v1", "archive": "arXiv", "archive_location": "2510.09038", "author": [ { "literal": "Wenyi Wu" }, { "literal": "Kun Zhou" }, { "literal": "Ruoxin Yuan" }, { "literal": "Vivian Yu" }, { "literal": "Stephen Wang" }, { "literal": "Zhiting Hu" }, { "literal": "Biwei Huang" } ], "citation-key": "arxiv_2510_09038", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "43c41dfbef8b76bbdccd7c435694cee8788b116db278122f64a22e7498bd5a5a", "submitted_at": "2025-10-10T06:16:45Z", "updated_at": "2025-10-10T06:16:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.09038v1" }, "canonical_source_url": "https://arxiv.org/abs/2510.09038", "catalog_id": "arxiv:2510.09038", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-10", "identifiers": { "arxiv": "2510.09038" }, "record_updated_at": "2025-10-10" }, "genre": "preprint", "id": "arxiv:2510.09038", "issued": { "date-parts": [ [ 2025, 10, 10 ] ] }, "note": "First published: 2025-10-10; Recorded arXiv version: v1; Recorded version updated: 2025-10-10T06:16:45Z.", "title": "Auto-scaling Continuous Memory for GUI Agent", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2510.19205v1", "archive": "arXiv", "archive_location": "2510.19205", "author": [ { "literal": "Yaoyao Qian" }, { "literal": "Yuanli Wang" }, { "literal": "Jinda Zhang" }, { "literal": "Yun Zong" }, { "literal": "Meixu Chen" }, { "literal": "Hanhan Zhou" }, { "literal": "Jindan Huang" }, { "literal": "Yifan Zeng" }, { "literal": "Xinyu Hu" }, { "literal": "Chan Hee Song" }, { "literal": "Danqing Zhang" } ], "citation-key": "arxiv_2510_19205", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d404ff922ef38e57481c01a5e3108bd38457d88f83d7adf6d3c3c7b5ddf124e2", "submitted_at": "2025-10-22T03:29:25Z", "updated_at": "2025-10-22T03:29:25Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.19205v1" }, "canonical_source_url": "https://arxiv.org/abs/2510.19205", "catalog_id": "arxiv:2510.19205", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-22", "identifiers": { "arxiv": "2510.19205" }, "record_updated_at": "2025-10-22" }, "genre": "preprint", "id": "arxiv:2510.19205", "issued": { "date-parts": [ [ 2025, 10, 22 ] ] }, "note": "First published: 2025-10-22; Recorded arXiv version: v1; Recorded version updated: 2025-10-22T03:29:25Z.", "title": "WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph Representation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2510.27210v1", "archive": "arXiv", "archive_location": "2510.27210", "author": [ { "literal": "Tao Liu" }, { "literal": "Chongyu Wang" }, { "literal": "Rongjie Li" }, { "literal": "Yingchen Yu" }, { "literal": "Xuming He" }, { "literal": "Bai Song" } ], "citation-key": "arxiv_2510_27210", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "283b1a1de2a4e1d4ec8175f0c15af66c10097a7f5ad9fd2793e93b888526ff7e", "submitted_at": "2025-10-31T06:10:57Z", "updated_at": "2025-10-31T06:10:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.27210v1" }, "canonical_source_url": "https://arxiv.org/abs/2510.27210", "catalog_id": "arxiv:2510.27210", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-31", "identifiers": { "arxiv": "2510.27210" }, "record_updated_at": "2025-10-31" }, "genre": "preprint", "id": "arxiv:2510.27210", "issued": { "date-parts": [ [ 2025, 10, 31 ] ] }, "note": "First published: 2025-10-31; Recorded arXiv version: v1; Recorded version updated: 2025-10-31T06:10:57Z.", "title": "GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2511.09127v1", "archive": "arXiv", "archive_location": "2511.09127", "author": [ { "literal": "Ziwei Wang" }, { "literal": "Leyang Yang" }, { "literal": "Xiaoxuan Tang" }, { "literal": "Sheng Zhou" }, { "literal": "Dajun Chen" }, { "literal": "Wei Jiang" }, { "literal": "Yong Li" } ], "citation-key": "arxiv_2511_09127", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d0f61f09ce52b1e66fa81479483ea419aaa16e6b27ce331d3c1039927075fd91", "submitted_at": "2025-11-12T09:06:25Z", "updated_at": "2025-11-12T09:06:25Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.09127v1" }, "canonical_source_url": "https://arxiv.org/abs/2511.09127", "catalog_id": "arxiv:2511.09127", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-12", "identifiers": { "arxiv": "2511.09127" }, "record_updated_at": "2025-11-12" }, "genre": "preprint", "id": "arxiv:2511.09127", "issued": { "date-parts": [ [ 2025, 11, 12 ] ] }, "note": "First published: 2025-11-12; Recorded arXiv version: v1; Recorded version updated: 2025-11-12T09:06:25Z.", "title": "History-Aware Reasoning for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2511.12997v2", "archive": "arXiv", "archive_location": "2511.12997", "author": [ { "literal": "Genglin Liu" }, { "literal": "Shijie Geng" }, { "literal": "Sha Li" }, { "literal": "Hejie Cui" }, { "literal": "Sarah Zhang" }, { "literal": "Xin Liu" }, { "literal": "Tianyi Liu" } ], "citation-key": "arxiv_2511_12997", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8a105701d9265bacd3971f71f34a0e7ed315b6e54e9a7e675588c50713fcc4de", "submitted_at": "2025-11-17T05:38:50Z", "updated_at": "2026-07-22T21:19:00Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2511.12997v2" }, "canonical_source_url": "https://arxiv.org/abs/2511.12997", "catalog_id": "arxiv:2511.12997", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-17", "identifiers": { "arxiv": "2511.12997" }, "record_updated_at": "2026-07-22" }, "genre": "preprint", "id": "arxiv:2511.12997", "issued": { "date-parts": [ [ 2025, 11, 17 ] ] }, "note": "First published: 2025-11-17; Recorded arXiv version: v2; Recorded version updated: 2026-07-22T21:19:00Z.", "title": "WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2512.01763v2", "archive": "arXiv", "archive_location": "2512.01763", "author": [ { "literal": "Xurui Zhou" }, { "literal": "Gongwei Chen" }, { "literal": "Yuquan Xie" }, { "literal": "Zaijing Li" }, { "literal": "Kaiwen Zhou" }, { "literal": "Shuai Wang" }, { "literal": "Shuo Yang" }, { "literal": "Zhuotao Tian" }, { "literal": "Rui Shao" } ], "citation-key": "arxiv_2512_01763", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3a6eb58f9b6349ab9cc33444d8ea82c8f17653cc4a7f4b19ffc94e3b4fb894b3", "submitted_at": "2025-12-01T15:06:45Z", "updated_at": "2026-03-08T10:18:14Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2512.01763v2" }, "canonical_source_url": "https://arxiv.org/abs/2512.01763", "catalog_id": "arxiv:2512.01763", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-01", "identifiers": { "arxiv": "2512.01763" }, "record_updated_at": "2026-03-08" }, "genre": "preprint", "id": "arxiv:2512.01763", "issued": { "date-parts": [ [ 2025, 12, 1 ] ] }, "note": "First published: 2025-12-01; Recorded arXiv version: v2; Recorded version updated: 2026-03-08T10:18:14Z.", "title": "HiconAgent: History Context-aware Policy Optimization for GUI Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2512.10371v2", "archive": "arXiv", "archive_location": "2512.10371", "author": [ { "literal": "Shizuo Tian" }, { "literal": "Hao Wen" }, { "literal": "Yuxuan Chen" }, { "literal": "Jiacheng Liu" }, { "literal": "Shanhui Zhao" }, { "literal": "Guohong Liu" }, { "literal": "Ju Ren" }, { "literal": "Yunxin Liu" }, { "literal": "Yuanchun Li" } ], "citation-key": "arxiv_2512_10371", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "72b2db237a52ae31eaba58183a2777e79379aa8e849d18de5d8633daf27ccbf9", "submitted_at": "2025-12-11T07:37:38Z", "updated_at": "2026-05-08T09:40:02Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2512.10371v2" }, "canonical_source_url": "https://arxiv.org/abs/2512.10371", "catalog_id": "arxiv:2512.10371", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-11", "identifiers": { "arxiv": "2512.10371" }, "record_updated_at": "2026-05-08" }, "genre": "preprint", "id": "arxiv:2512.10371", "issued": { "date-parts": [ [ 2025, 12, 11 ] ] }, "note": "First published: 2025-12-11; Recorded arXiv version: v2; Recorded version updated: 2026-05-08T09:40:02Z.", "title": "AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2601.11631v1", "archive": "arXiv", "archive_location": "2601.11631", "author": [ { "literal": "Yurun Song" }, { "literal": "Jiong Yin" }, { "literal": "Rongjunchen Zhang" }, { "literal": "Ian G. Harris" } ], "citation-key": "arxiv_2601_11631", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "600f2a44695886fc527b04e1a8b1ad07cec90cf5c58dee834605d5133a760b1e", "submitted_at": "2026-01-14T03:52:57Z", "updated_at": "2026-01-14T03:52:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.11631v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.11631", "catalog_id": "arxiv:2601.11631", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-14", "identifiers": { "arxiv": "2601.11631" }, "record_updated_at": "2026-01-14" }, "genre": "preprint", "id": "arxiv:2601.11631", "issued": { "date-parts": [ [ 2026, 1, 14 ] ] }, "note": "First published: 2026-01-14; Recorded arXiv version: v1; Recorded version updated: 2026-01-14T03:52:57Z.", "title": "Compress to Focus: Efficient Coordinate Compression for Policy Optimization in Multi-Turn GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.16313v2", "archive": "arXiv", "archive_location": "2602.16313", "author": [ { "literal": "Zexue He" }, { "literal": "Yu Wang" }, { "literal": "Churan Zhi" }, { "literal": "Yuanzhe Hu" }, { "literal": "Tzu-Ping Chen" }, { "literal": "Lang Yin" }, { "literal": "Ze Chen" }, { "literal": "Tong Arthur Wu" }, { "literal": "Siru Ouyang" }, { "literal": "Zihan Wang" }, { "literal": "Jiaxin Pei" }, { "literal": "Julian McAuley" }, { "literal": "Yejin Choi" }, { "literal": "Alex Pentland" } ], "citation-key": "arxiv_2602_16313", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2317a94d54b4458a1b7c5e92754aeaefcbf270aabfa0bd8ea333c673cd4596b3", "submitted_at": "2026-02-18T09:49:14Z", "updated_at": "2026-09-17T22:55:03Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.16313v2" }, "canonical_source_url": "https://arxiv.org/abs/2602.16313", "catalog_id": "arxiv:2602.16313", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-18", "identifiers": { "arxiv": "2602.16313" }, "record_updated_at": "2026-09-17" }, "genre": "preprint", "id": "arxiv:2602.16313", "issued": { "date-parts": [ [ 2026, 2, 18 ] ] }, "note": "First published: 2026-02-18; Recorded arXiv version: v2; Recorded version updated: 2026-09-17T22:55:03Z.", "title": "MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2603.26041v4", "archive": "arXiv", "archive_location": "2603.26041", "author": [ { "literal": "Daiqiang Li" }, { "literal": "Zihao Pan" }, { "literal": "Zeyu Zhang" }, { "literal": "Xuyang Liu" }, { "literal": "Shijia Xu" }, { "literal": "Ronghao Chen" }, { "literal": "Huacan Wang" }, { "literal": "Honggang Chen" }, { "literal": "Linfeng Zhang" }, { "literal": "Zhangquan Chen" }, { "literal": "Haiyun Jiang" } ], "citation-key": "arxiv_2603_26041", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "738d5048bb7a137d848b6f6068a7ce92694469f1e7bce0702dce422c230a3d0b", "submitted_at": "2026-03-27T03:21:19Z", "updated_at": "2026-08-09T16:37:37Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2603.26041v4" }, "canonical_source_url": "https://arxiv.org/abs/2603.26041", "catalog_id": "arxiv:2603.26041", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-03-27", "identifiers": { "arxiv": "2603.26041" }, "record_updated_at": "2026-08-09" }, "genre": "preprint", "id": "arxiv:2603.26041", "issued": { "date-parts": [ [ 2026, 3, 27 ] ] }, "note": "First published: 2026-03-27; Recorded arXiv version: v4; Recorded version updated: 2026-08-09T16:37:37Z.", "title": "Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2604.27151v1", "archive": "arXiv", "archive_location": "2604.27151", "author": [ { "literal": "Jinbiao Wei" }, { "literal": "Kangqi Ni" }, { "literal": "Yilun Zhao" }, { "literal": "Guo Gan" }, { "literal": "Arman Cohan" } ], "citation-key": "arxiv_2604_27151", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "68183be37dbd78314aca35f7f1420e5f2f8da8d8c0042a258b45ae03c90606cf", "submitted_at": "2026-04-29T19:59:36Z", "updated_at": "2026-04-29T19:59:36Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.27151v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.27151", "catalog_id": "arxiv:2604.27151", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-29", "identifiers": { "arxiv": "2604.27151" }, "record_updated_at": "2026-04-29" }, "genre": "preprint", "id": "arxiv:2604.27151", "issued": { "date-parts": [ [ 2026, 4, 29 ] ] }, "note": "First published: 2026-04-29; Recorded arXiv version: v1; Recorded version updated: 2026-04-29T19:59:36Z.", "title": "Step-level Optimization for Efficient Computer-use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.11212v3", "archive": "arXiv", "archive_location": "2605.11212", "author": [ { "literal": "Amirhossein Abaskohi" }, { "literal": "Yuhang He" }, { "literal": "Peter West" }, { "literal": "Giuseppe Carenini" }, { "literal": "Pranit Chawla" }, { "literal": "Vibhav Vineet" } ], "citation-key": "arxiv_2605_11212", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "422d2fdf2d7f665df1a5672e03d837ba41fe9c6832d64c40317f77481f642130", "submitted_at": "2026-05-11T20:27:54Z", "updated_at": "2026-06-05T22:18:46Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2605.11212v3" }, "canonical_source_url": "https://arxiv.org/abs/2605.11212", "catalog_id": "arxiv:2605.11212", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-11", "identifiers": { "arxiv": "2605.11212" }, "record_updated_at": "2026-06-05" }, "genre": "preprint", "id": "arxiv:2605.11212", "issued": { "date-parts": [ [ 2026, 5, 11 ] ] }, "note": "First published: 2026-05-11; Recorded arXiv version: v3; Recorded version updated: 2026-06-05T22:18:46Z.", "title": "ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2605.12493v1", "archive": "arXiv", "archive_location": "2605.12493", "author": [ { "literal": "Di Wu" }, { "literal": "Zixiang Ji" }, { "literal": "Asmi Kawatkar" }, { "literal": "Bryan Kwan" }, { "literal": "Jia-Chen Gu" }, { "literal": "Nanyun Peng" }, { "literal": "Kai-Wei Chang" } ], "citation-key": "arxiv_2605_12493", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5893d1d9205776667a1e1d89720ec3baf55fafe80cc9c6201ca97088f44a10ac", "submitted_at": "2026-05-12T17:59:34Z", "updated_at": "2026-05-12T17:59:34Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.12493v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.12493", "catalog_id": "arxiv:2605.12493", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-12", "identifiers": { "arxiv": "2605.12493" }, "record_updated_at": "2026-05-12" }, "genre": "preprint", "id": "arxiv:2605.12493", "issued": { "date-parts": [ [ 2026, 5, 12 ] ] }, "note": "First published: 2026-05-12; Recorded arXiv version: v1; Recorded version updated: 2026-05-12T17:59:34Z.", "title": "LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.16883v1", "archive": "arXiv", "archive_location": "2605.16883", "author": [ { "literal": "Shilong Jin" }, { "literal": "Lanjun Wang" }, { "literal": "Zhuosheng Zhang" } ], "citation-key": "arxiv_2605_16883", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "52c1bf4c614ac05a55f2c2c66d3ac4eeb1bf31743814a45eb9f0ce064b6baaab", "submitted_at": "2026-05-16T08:51:57Z", "updated_at": "2026-05-16T08:51:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.16883v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.16883", "catalog_id": "arxiv:2605.16883", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-16", "identifiers": { "arxiv": "2605.16883" }, "record_updated_at": "2026-05-16" }, "genre": "preprint", "id": "arxiv:2605.16883", "issued": { "date-parts": [ [ 2026, 5, 16 ] ] }, "note": "First published: 2026-05-16; Recorded arXiv version: v1; Recorded version updated: 2026-05-16T08:51:57Z.", "title": "SE-GA: Memory-Augmented Self-Evolution for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.18652v1", "archive": "arXiv", "archive_location": "2605.18652", "author": [ { "literal": "Ziyun Zeng" }, { "literal": "Hang Hua" }, { "literal": "Bocheng Zou" }, { "literal": "Mu Cai" }, { "literal": "Rogerio Feris" }, { "literal": "Jiebo Luo" } ], "citation-key": "arxiv_2605_18652", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d96c8844274f79adea167169a0853e3a7cd82fee4a8a666913f97898a0836e7c", "submitted_at": "2026-05-18T16:57:36Z", "updated_at": "2026-05-18T16:57:36Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.18652v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.18652", "catalog_id": "arxiv:2605.18652", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-18", "identifiers": { "arxiv": "2605.18652" }, "record_updated_at": "2026-05-18" }, "genre": "preprint", "id": "arxiv:2605.18652", "issued": { "date-parts": [ [ 2026, 5, 18 ] ] }, "note": "First published: 2026-05-18; Recorded arXiv version: v1; Recorded version updated: 2026-05-18T16:57:36Z.", "title": "MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.26086v1", "archive": "arXiv", "archive_location": "2605.26086", "author": [ { "literal": "Yusong Lin" }, { "literal": "Xinyuan Liang" }, { "literal": "Haiyang Wang" }, { "literal": "Qipeng Gu" }, { "literal": "Siqi Cheng" }, { "literal": "Jiangui Chen" }, { "literal": "Shuzhe Wu" }, { "literal": "Feiyang Pan" }, { "literal": "Lue Fan" }, { "literal": "Sanyuan Zhao" }, { "literal": "Dandan Tu" } ], "citation-key": "arxiv_2605_26086", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "27999553928305cfa4223011feb3f9c2decda8a861e5800865537a81c7c08832", "submitted_at": "2026-05-25T17:50:04Z", "updated_at": "2026-05-25T17:50:04Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.26086v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.26086", "catalog_id": "arxiv:2605.26086", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-25", "identifiers": { "arxiv": "2605.26086" }, "record_updated_at": "2026-05-25" }, "genre": "preprint", "id": "arxiv:2605.26086", "issued": { "date-parts": [ [ 2026, 5, 25 ] ] }, "note": "First published: 2026-05-25; Recorded arXiv version: v1; Recorded version updated: 2026-05-25T17:50:04Z.", "title": "Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.01790v1", "archive": "arXiv", "archive_location": "2606.01790", "author": [ { "literal": "Yuhang Han" }, { "literal": "Wenzheng Yang" }, { "literal": "Yujie Chen" }, { "literal": "Xiangqi Jin" }, { "literal": "Yaojie Zhang" }, { "literal": "Siteng Huang" }, { "literal": "Linfeng Zhang" } ], "citation-key": "arxiv_2606_01790", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "73364572c0f21976048c89cd7732a16c7a952b08986792d02681a5ad0288c3ca", "submitted_at": "2026-06-01T07:10:00Z", "updated_at": "2026-06-01T07:10:00Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.01790v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.01790", "catalog_id": "arxiv:2606.01790", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-01", "identifiers": { "arxiv": "2606.01790" }, "record_updated_at": "2026-06-01" }, "genre": "preprint", "id": "arxiv:2606.01790", "issued": { "date-parts": [ [ 2026, 6, 1 ] ] }, "note": "First published: 2026-06-01; Recorded arXiv version: v1; Recorded version updated: 2026-06-01T07:10:00Z.", "title": "STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.04391v1", "archive": "arXiv", "archive_location": "2606.04391", "author": [ { "literal": "Jiaxi Li" }, { "literal": "Ke Deng" }, { "literal": "Yun Wang" }, { "literal": "Jingyuan Huang" }, { "literal": "Yucheng Shi" }, { "literal": "Qiaoyu Tan" }, { "literal": "Jin Lu" }, { "literal": "Ninghao Liu" } ], "citation-key": "arxiv_2606_04391", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6d891956bde9b8672859fcfcd2d54dfd3e4720964c25d77cc28bc1200ef3a56c", "submitted_at": "2026-06-03T03:11:50Z", "updated_at": "2026-06-03T03:11:50Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.04391v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.04391", "catalog_id": "arxiv:2606.04391", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-03", "identifiers": { "arxiv": "2606.04391" }, "record_updated_at": "2026-06-03" }, "genre": "preprint", "id": "arxiv:2606.04391", "issued": { "date-parts": [ [ 2026, 6, 3 ] ] }, "note": "First published: 2026-06-03; Recorded arXiv version: v1; Recorded version updated: 2026-06-03T03:11:50Z.", "title": "Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.11078v1", "archive": "arXiv", "archive_location": "2606.11078", "author": [ { "literal": "Jaewoo Lee" }, { "literal": "Zaid Khan" }, { "literal": "Archiki Prasad" }, { "literal": "Justin Chih-Yao Chen" }, { "literal": "Supriyo Chakraborty" }, { "literal": "Kartik Balasubramaniam" }, { "literal": "Sambit Sahu" }, { "literal": "Elias Stengel-Eskin" }, { "literal": "Hyunji Lee" }, { "literal": "Mohit Bansal" } ], "citation-key": "arxiv_2606_11078", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a8ed399c8b489a80c5313a00232d2ecca0fbc8228b1f56745c02d4fedb6f6908", "submitted_at": "2026-06-09T16:39:10Z", "updated_at": "2026-06-09T16:39:10Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.11078v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.11078", "catalog_id": "arxiv:2606.11078", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-09", "identifiers": { "arxiv": "2606.11078" }, "record_updated_at": "2026-06-09" }, "genre": "preprint", "id": "arxiv:2606.11078", "issued": { "date-parts": [ [ 2026, 6, 9 ] ] }, "note": "First published: 2026-06-09; Recorded arXiv version: v1; Recorded version updated: 2026-06-09T16:39:10Z.", "title": "A History-Aware Visually Grounded Critic for Computer Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.14106v1", "archive": "arXiv", "archive_location": "2606.14106", "author": [ { "literal": "Seoyoung Choi" }, { "literal": "Minseok Ko" }, { "literal": "Hyunseok Lee" }, { "literal": "Kunwoong Kim" }, { "literal": "Woomin Song" }, { "literal": "Chanseok Jeon" }, { "literal": "Jinwoo Shin" } ], "citation-key": "arxiv_2606_14106", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1fb87da27071ab21519599b7d16359a38118aa358f620de94e66b15cad040828", "submitted_at": "2026-06-12T04:39:01Z", "updated_at": "2026-06-12T04:39:01Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.14106v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.14106", "catalog_id": "arxiv:2606.14106", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-12", "identifiers": { "arxiv": "2606.14106" }, "record_updated_at": "2026-06-12" }, "genre": "preprint", "id": "arxiv:2606.14106", "issued": { "date-parts": [ [ 2026, 6, 12 ] ] }, "note": "First published: 2026-06-12; Recorded arXiv version: v1; Recorded version updated: 2026-06-12T04:39:01Z.", "title": "Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.19926v1", "archive": "arXiv", "archive_location": "2606.19926", "author": [ { "literal": "Guangyi Liu" }, { "literal": "Gao Wu" }, { "literal": "Congxiao Liu" }, { "literal": "Pengxiang Zhao" }, { "literal": "Liang Liu" }, { "literal": "Mading Li" }, { "literal": "Qi Zhang" }, { "literal": "Mengyan Wang" }, { "literal": "Liang Guo" }, { "literal": "Yong Liu" } ], "citation-key": "arxiv_2606_19926", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cbbb1bd57057e465ce9d991d3f6e2bb52112fc133a5846fc8cb6ce51eddc2121", "submitted_at": "2026-06-18T08:26:09Z", "updated_at": "2026-06-18T08:26:09Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.19926v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.19926", "catalog_id": "arxiv:2606.19926", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-18", "identifiers": { "arxiv": "2606.19926" }, "record_updated_at": "2026-06-18" }, "genre": "preprint", "id": "arxiv:2606.19926", "issued": { "date-parts": [ [ 2026, 6, 18 ] ] }, "note": "First published: 2026-06-18; Recorded arXiv version: v1; Recorded version updated: 2026-06-18T08:26:09Z.", "title": "MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.12625v2", "archive": "arXiv", "archive_location": "2607.12625", "author": [ { "literal": "Yunxin Li" }, { "literal": "Jinchao Li" }, { "literal": "Shibo Su" }, { "literal": "Zhenran Xu" }, { "literal": "Chenrui Zhao" }, { "literal": "Tongshu Bian" }, { "literal": "Xiaoman Liang" }, { "literal": "Meishan Zhang" }, { "literal": "Baotian Hu" }, { "literal": "Min Zhang" } ], "citation-key": "arxiv_2607_12625", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "281de2bb6e45a58efd047735accc2049deab0f8815931c86abbd38b86b6d23bf", "submitted_at": "2026-07-14T11:04:01Z", "updated_at": "2026-07-15T04:41:47Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.12625v2" }, "canonical_source_url": "https://arxiv.org/abs/2607.12625", "catalog_id": "arxiv:2607.12625", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-14", "identifiers": { "arxiv": "2607.12625" }, "record_updated_at": "2026-07-15" }, "genre": "preprint", "id": "arxiv:2607.12625", "issued": { "date-parts": [ [ 2026, 7, 14 ] ] }, "note": "First published: 2026-07-14; Recorded arXiv version: v2; Recorded version updated: 2026-07-15T04:41:47Z.", "title": "KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2608.02352v1", "archive": "arXiv", "archive_location": "2608.02352", "author": [ { "literal": "Dunjie Lu" }, { "literal": "Shuai Bai" }, { "literal": "Tianyi Bai" }, { "literal": "Sicheng Fan" }, { "literal": "Chang Gao" }, { "literal": "Jian Guan" }, { "literal": "Feng Hu" }, { "literal": "Mianqiu Huang" }, { "literal": "Xingyang Huang" }, { "literal": "Yizhen Jiang" }, { "literal": "Yuheng Jing" }, { "literal": "Dehui Kong" }, { "literal": "Ning Li" }, { "literal": "Dayiheng Liu" }, { "literal": "Shixuan Liu" }, { "literal": "Zheng Liu" }, { "literal": "Que Shen" }, { "literal": "Bowen Wang" }, { "literal": "Junli Wang" }, { "literal": "Chencan Wu" }, { "literal": "Rui Xie" }, { "literal": "Tianbao Xie" }, { "literal": "Zhihui Xie" }, { "literal": "Haiyang Xu" }, { "literal": "An Yang" }, { "literal": "Tao Yu" }, { "literal": "Wenzhen Yuan" }, { "literal": "Xi Zhang" }, { "literal": "Zhenru Zhang" }, { "literal": "Mingkang Zhu" }, { "literal": "Zhaoqing Zhu" }, { "literal": "Yizhong Cao" }, { "literal": "Kai Dang" }, { "literal": "Binyuan Hui" }, { "literal": "Kaixin Li" }, { "literal": "Junyang Lin" }, { "literal": "Haiquan Wang" }, { "literal": "Zekun Wang" }, { "literal": "Yiheng Xu" }, { "literal": "Fan Yan" }, { "literal": "Mengqi Yuan" }, { "literal": "Danyang Zhang" }, { "literal": "Jiajun Zhang" }, { "literal": "Zhipeng Zhang" }, { "literal": "Fan Zhou" }, { "literal": "Fan Zhou" } ], "citation-key": "arxiv_2608_02352", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "26a61ccfdddb5cdc2da2b14d29ae8d4098544fea4e9458126f2a49c28418c4f0", "submitted_at": "2026-08-03T15:04:20Z", "updated_at": "2026-08-03T15:04:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.02352v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.02352", "catalog_id": "arxiv:2608.02352", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-03", "identifiers": { "arxiv": "2608.02352" }, "record_updated_at": "2026-08-03" }, "genre": "preprint", "id": "arxiv:2608.02352", "issued": { "date-parts": [ [ 2026, 8, 3 ] ] }, "note": "First published: 2026-08-03; Recorded arXiv version: v1; Recorded version updated: 2026-08-03T15:04:20Z.", "title": "Qwen-CUA: Native Computer Use for (almost) Everything", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.03327v2", "archive": "arXiv", "archive_location": "2608.03327", "author": [ { "literal": "Siqi Fan" }, { "literal": "Minghao Li" }, { "literal": "Xiaoqian Ma" }, { "literal": "Wenhui Tan" }, { "literal": "Xiusheng Huang" }, { "literal": "Juntong Wu" }, { "literal": "Liujie Zhang" }, { "literal": "Shuo Shang" }, { "literal": "Weihang Chen" } ], "citation-key": "arxiv_2608_03327", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2c8692712194d0ff822091d13324e6bb540339103a824f1030f7a971699d0a0b", "submitted_at": "2026-08-04T08:35:51Z", "updated_at": "2026-08-06T07:26:24Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2608.03327v2" }, "canonical_source_url": "https://arxiv.org/abs/2608.03327", "catalog_id": "arxiv:2608.03327", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-04", "identifiers": { "arxiv": "2608.03327" }, "record_updated_at": "2026-08-06" }, "genre": "preprint", "id": "arxiv:2608.03327", "issued": { "date-parts": [ [ 2026, 8, 4 ] ] }, "note": "First published: 2026-08-04; Recorded arXiv version: v2; Recorded version updated: 2026-08-06T07:26:24Z.", "title": "Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2608.06065v1", "archive": "arXiv", "archive_location": "2608.06065", "author": [ { "literal": "Weiwei Li" }, { "literal": "Junzhuo Liu" }, { "literal": "Tong Chu" }, { "literal": "Hengfu Yu" }, { "literal": "Wen Li" } ], "citation-key": "arxiv_2608_06065", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bb90627131765746e3a138ab0862dd68ea963106db4055760d78041c856acc8b", "submitted_at": "2026-08-06T14:10:23Z", "updated_at": "2026-08-06T14:10:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.06065v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.06065", "catalog_id": "arxiv:2608.06065", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-06", "identifiers": { "arxiv": "2608.06065" }, "record_updated_at": "2026-08-06" }, "genre": "preprint", "id": "arxiv:2608.06065", "issued": { "date-parts": [ [ 2026, 8, 6 ] ] }, "note": "First published: 2026-08-06; Recorded arXiv version: v1; Recorded version updated: 2026-08-06T14:10:23Z.", "title": "The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.20319v1", "archive": "arXiv", "archive_location": "2608.20319", "author": [ { "literal": "Yucheng Jiang" }, { "literal": "Zora Zhiruo Wang" }, { "literal": "Ruishi Chen" }, { "literal": "Diyi Yang" } ], "citation-key": "arxiv_2608_20319", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a85b3a99d551fcdffdd306d839b39cdfbe7f0f7654aa9adbf81f939aa874e3b9", "submitted_at": "2026-08-20T17:57:00Z", "updated_at": "2026-08-20T17:57:00Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.20319v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.20319", "catalog_id": "arxiv:2608.20319", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-20", "identifiers": { "arxiv": "2608.20319" }, "record_updated_at": "2026-08-20" }, "genre": "preprint", "id": "arxiv:2608.20319", "issued": { "date-parts": [ [ 2026, 8, 20 ] ] }, "note": "First published: 2026-08-20; Recorded arXiv version: v1; Recorded version updated: 2026-08-20T17:57:00Z.", "title": "Inducing Task Models from Computer-Use Traces", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.02057v1", "archive": "arXiv", "archive_location": "2609.02057", "author": [ { "literal": "Sitong Pan" }, { "literal": "Yipeng Shen" }, { "literal": "Yilin Lu" }, { "literal": "Caiwen Ding" }, { "literal": "Lu Cheng" }, { "literal": "Qianwen Wang" } ], "citation-key": "arxiv_2609_02057", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "967f1cdda69349da3280827c0b90301e4942c44398902ab6cfb868f1d3e94a84", "submitted_at": "2026-09-02T03:34:47Z", "updated_at": "2026-09-02T03:34:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.02057v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.02057", "catalog_id": "arxiv:2609.02057", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-02", "identifiers": { "arxiv": "2609.02057" }, "record_updated_at": "2026-09-02" }, "genre": "preprint", "id": "arxiv:2609.02057", "issued": { "date-parts": [ [ 2026, 9, 2 ] ] }, "note": "First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T03:34:47Z.", "title": "Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.10031v1", "archive": "arXiv", "archive_location": "2609.10031", "author": [ { "literal": "Xiaolei Li" }, { "literal": "Jialun Cao" }, { "literal": "Zhijian Hou" }, { "literal": "Yuzhi Zhao" }, { "literal": "Yepang Liu" }, { "literal": "Shing-Chi Cheung" } ], "citation-key": "arxiv_2609_10031", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3307d90ef09c16afaee160eacc9d2994d142be9b9a26ce9c4a57f61345e2e8ec", "submitted_at": "2026-09-09T11:04:53Z", "updated_at": "2026-09-09T11:04:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.10031v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.10031", "catalog_id": "arxiv:2609.10031", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-09", "identifiers": { "arxiv": "2609.10031" }, "record_updated_at": "2026-09-09" }, "genre": "preprint", "id": "arxiv:2609.10031", "issued": { "date-parts": [ [ 2026, 9, 9 ] ] }, "note": "First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T11:04:53Z.", "title": "GraphDroid: Asynchronous LLM-Based Mobile App GUI Testing via History-Aware Exploration and Hybrid Intent Fulfillment", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.10297v1", "archive": "arXiv", "archive_location": "2609.10297", "author": [ { "literal": "Yuhao Wang" }, { "literal": "Mu Qiao" }, { "literal": "Xindong Zhang" }, { "literal": "Yunzhi Zhuge" }, { "literal": "Lei Zhang" }, { "literal": "Huchuan Lu" } ], "citation-key": "arxiv_2609_10297", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "20d3bc3137e163f6b467b8c464101478b2375fbab8aebe9179e2e1113b34f503", "submitted_at": "2026-09-09T15:12:48Z", "updated_at": "2026-09-09T15:12:48Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.10297v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.10297", "catalog_id": "arxiv:2609.10297", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-09", "identifiers": { "arxiv": "2609.10297" }, "record_updated_at": "2026-09-09" }, "genre": "preprint", "id": "arxiv:2609.10297", "issued": { "date-parts": [ [ 2026, 9, 9 ] ] }, "note": "First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T15:12:48Z.", "title": "TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.15457v1", "archive": "arXiv", "archive_location": "2609.15457", "author": [ { "literal": "Shengjie Jin" }, { "literal": "Zelong Sun" }, { "literal": "Hengbo Xu" }, { "literal": "Yanbiao Ma" }, { "literal": "Zhiwu Lu" } ], "citation-key": "arxiv_2609_15457", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e8a98337941972fadb725906b9d1315a0ca5921859bd04780cacbabb0500e6a5", "submitted_at": "2026-09-14T12:22:26Z", "updated_at": "2026-09-14T12:22:26Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.15457v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.15457", "catalog_id": "arxiv:2609.15457", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-14", "identifiers": { "arxiv": "2609.15457" }, "record_updated_at": "2026-09-14" }, "genre": "preprint", "id": "arxiv:2609.15457", "issued": { "date-parts": [ [ 2026, 9, 14 ] ] }, "note": "First published: 2026-09-14; Recorded arXiv version: v1; Recorded version updated: 2026-09-14T12:22:26Z.", "title": "AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.27307v1", "archive": "arXiv", "archive_location": "2609.27307", "author": [ { "literal": "Yan Zhang" }, { "literal": "Daiqing Wu" }, { "literal": "Huawen Shen" }, { "literal": "Liang Li" }, { "literal": "Gang Cao" }, { "literal": "Zhi Gong" }, { "literal": "Wei Dai" }, { "literal": "Xiaode Zhang" }, { "literal": "Can Ma" }, { "literal": "Yu Zhou" } ], "citation-key": "arxiv_2609_27307", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0ae6c83c017a05c2916f31e388f6584cc2cab7b87e1eb0038c33a707bbd66e24", "submitted_at": "2026-09-23T03:38:11Z", "updated_at": "2026-09-23T03:38:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.27307v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.27307", "catalog_id": "arxiv:2609.27307", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-23", "identifiers": { "arxiv": "2609.27307" }, "record_updated_at": "2026-09-23" }, "genre": "preprint", "id": "arxiv:2609.27307", "issued": { "date-parts": [ [ 2026, 9, 23 ] ] }, "note": "First published: 2026-09-23; Recorded arXiv version: v1; Recorded version updated: 2026-09-23T03:38:11Z.", "title": "Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.18579v1", "archive": "arXiv", "archive_location": "2610.18579", "author": [ { "literal": "Yubo Li" }, { "literal": "Ramayya Krishnan" }, { "literal": "Rema Padman" } ], "citation-key": "arxiv_2610_18579", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "070f02f1ea798369817f471df5fe1d002b68d544135a1ac8e3a2aed2830e8c01", "submitted_at": "2026-10-13T15:43:30Z", "updated_at": "2026-10-13T15:43:30Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.18579v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.18579", "catalog_id": "arxiv:2610.18579", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-10-13", "identifiers": { "arxiv": "2610.18579" }, "record_updated_at": "2026-10-13" }, "genre": "preprint", "id": "arxiv:2610.18579", "issued": { "date-parts": [ [ 2026, 10, 13 ] ] }, "note": "First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T15:43:30Z.", "title": "Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.19366v1", "archive": "arXiv", "archive_location": "2610.19366", "author": [ { "literal": "Minghao Guo" }, { "literal": "Qingyue Jiao" }, { "literal": "Xiujin Liu" }, { "literal": "Jianhong Pang" }, { "literal": "Ruimeng Yang" }, { "literal": "Naihao Xu" }, { "literal": "Liwei Che" }, { "literal": "Haochen Xue" }, { "literal": "Ziqi Wang" }, { "literal": "Xinying Cai" }, { "literal": "Jiaxuan Luo" }, { "literal": "Jiaxin Deng" }, { "literal": "Xuesong Ye" }, { "literal": "Jintao Qu" }, { "literal": "Wenyao Gao" }, { "literal": "Jingwen Gu" }, { "literal": "Chenyang Zhao" }, { "literal": "Shichun Liu" }, { "literal": "Guibin Zhang" }, { "literal": "Zefang Liu" }, { "literal": "Siyin Wang" }, { "literal": "Wujiang Xu" }, { "literal": "Danrui Li" }, { "literal": "Zeru Shi" }, { "literal": "Woongyeong Yeo" }, { "literal": "Shuang Liu" }, { "literal": "Wei-Chieh Huang" }, { "literal": "Weizhi Zhang" }, { "literal": "Tianyu Yang" }, { "literal": "Kangsan Kim" }, { "literal": "Yebowen Hu" }, { "literal": "Bowen Wen" }, { "literal": "Bowen Jiang" }, { "literal": "Haohao Su" }, { "literal": "Ming Yin" }, { "literal": "Sheldon Yu" }, { "literal": "Mian Zhang" }, { "literal": "Yuyan Chen" }, { "literal": "Hanrong Zhang" }, { "literal": "Kai Mei" }, { "literal": "Zihao Zhang" }, { "literal": "Mingyu Jin" }, { "literal": "Xi Zhu" }, { "literal": "Hengyi Wang" }, { "literal": "Tianxin Wei" }, { "literal": "Linyong Nan" }, { "literal": "Zhenwen Liang" }, { "literal": "Zhendong Chu" }, { "literal": "Ziqi Huang" }, { "literal": "Yongye Su" }, { "literal": "Sixun Dong" }, { "literal": "Shujian Liu" }, { "literal": "Kaiqu Liang" }, { "literal": "Jiaojiao Han" }, { "literal": "Zhaoye Fei" }, { "literal": "Kun Wang" }, { "literal": "Shihan Dou" }, { "literal": "Zhichun Guo" }, { "literal": "Xingjian Diao" }, { "literal": "Zeqi Gu" }, { "literal": "Heng Wang" }, { "literal": "Tao Feng" }, { "literal": "Cheng Qian" }, { "literal": "Hamid Palangi" }, { "literal": "Silei Xu" }, { "literal": "Xi Yun" }, { "literal": "Yi Zhu" }, { "literal": "Shilong Liu" }, { "literal": "Qingsong Wen" }, { "literal": "Sung Ju Hwang" }, { "literal": "Zuxuan Wu" }, { "literal": "Yu-Gang Jiang" }, { "literal": "Yiyu Shi" }, { "literal": "Dimitris N. Metaxas" }, { "literal": "Jiaxuan You" }, { "literal": "Julian McAuley" }, { "literal": "Mengdi Wang" }, { "literal": "Jiawei Han" }, { "literal": "Philip S. Yu" }, { "literal": "Ziyi Ye" } ], "citation-key": "arxiv_2610_19366", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7f1a48aa4b89fb97e8e1a186ba7345826a8b9efc9aa7b82e0dd1f5ce17d42b73", "submitted_at": "2026-10-14T01:11:57Z", "updated_at": "2026-10-14T01:11:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.19366v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.19366", "catalog_id": "arxiv:2610.19366", "catalog_kind": "survey", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-10-14", "identifiers": { "arxiv": "2610.19366" }, "record_updated_at": "2026-10-14" }, "genre": "preprint", "id": "arxiv:2610.19366", "issued": { "date-parts": [ [ 2026, 10, 14 ] ] }, "note": "First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T01:11:57Z.", "title": "Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.22408v1", "archive": "arXiv", "archive_location": "2610.22408", "author": [ { "literal": "Tengda Guo" }, { "literal": "Jiawang Hu" }, { "literal": "Yifei Tao" }, { "literal": "Yin Wang" }, { "literal": "Haotian Hu" }, { "literal": "Fanyi Wang" }, { "literal": "Liujuan Tang" } ], "citation-key": "arxiv_2610_22408", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "025c7018c86ae4de79a659242070b2f91c5913333e9ecd4bd7fd357d13d27a34", "submitted_at": "2026-10-14T14:39:41Z", "updated_at": "2026-10-14T14:39:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.22408v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.22408", "catalog_id": "arxiv:2610.22408", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-14", "identifiers": { "arxiv": "2610.22408" }, "record_updated_at": "2026-10-14" }, "genre": "preprint", "id": "arxiv:2610.22408", "issued": { "date-parts": [ [ 2026, 10, 14 ] ] }, "note": "First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T14:39:41Z.", "title": "ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.26203v1", "archive": "arXiv", "archive_location": "2610.26203", "author": [ { "literal": "Fuyao Zhang" }, { "literal": "Wenwen He" }, { "literal": "Jiaming Zhang" }, { "literal": "Yurong Hao" }, { "literal": "Xuan Wang" }, { "literal": "Guowei Guan" }, { "literal": "Che Wang" }, { "literal": "Longtao Huang" }, { "literal": "Wei Yang Bryan Lim" } ], "citation-key": "arxiv_2610_26203", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "41178d19a23653c0f49423b8f725584bded7ab8819a1a46e83a062794460b4cb", "submitted_at": "2026-10-19T11:30:48Z", "updated_at": "2026-10-19T11:30:48Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.26203v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.26203", "catalog_id": "arxiv:2610.26203", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-19", "identifiers": { "arxiv": "2610.26203" }, "record_updated_at": "2026-10-19" }, "genre": "preprint", "id": "arxiv:2610.26203", "issued": { "date-parts": [ [ 2026, 10, 19 ] ] }, "note": "First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T11:30:48Z.", "title": "Focused Omni-Modal GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.26503v1", "archive": "arXiv", "archive_location": "2610.26503", "author": [ { "literal": "Zhicheng Zheng" }, { "literal": "Cheng Zhang" }, { "literal": "Shengping Yu" }, { "literal": "Tianxiang Zhao" } ], "citation-key": "arxiv_2610_26503", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7dc2ceb9aadbf7506efc068df99326fea5b60fdc6feb340c490841b88aa19c30", "submitted_at": "2026-10-19T14:38:41Z", "updated_at": "2026-10-19T14:38:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.26503v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.26503", "catalog_id": "arxiv:2610.26503", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-19", "identifiers": { "arxiv": "2610.26503" }, "record_updated_at": "2026-10-19" }, "genre": "preprint", "id": "arxiv:2610.26503", "issued": { "date-parts": [ [ 2026, 10, 19 ] ] }, "note": "First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T14:38:41Z.", "title": "ScopeMem: Latent Memory That Learns Where to Revise Frozen GUI Agents", "type": "article", "version": "1" }, { "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" } ]