[ { "URL": "https://arxiv.org/abs/2305.19308v2", "archive": "arXiv", "archive_location": "2305.19308", "author": [ { "literal": "Hongxin Li" }, { "literal": "Jingran Su" }, { "literal": "Yuntao Chen" }, { "literal": "Qing Li" }, { "literal": "Zhaoxiang Zhang" } ], "citation-key": "arxiv_2305_19308", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "320ff40872677e9d32efae360dc289ca345076e037e7044188868f765e816008", "submitted_at": "2023-05-30T17:59:30Z", "updated_at": "2023-10-30T06:36:24Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2305.19308v2" }, "canonical_source_url": "https://arxiv.org/abs/2305.19308", "catalog_id": "arxiv:2305.19308", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2023-05-30", "identifiers": { "arxiv": "2305.19308" }, "record_updated_at": "2023-10-30" }, "genre": "preprint", "id": "arxiv:2305.19308", "issued": { "date-parts": [ [ 2023, 5, 30 ] ] }, "note": "First published: 2023-05-30; Recorded arXiv version: v2; Recorded version updated: 2023-10-30T06:36:24Z.", "title": "SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2310.10634v1", "archive": "arXiv", "archive_location": "2310.10634", "author": [ { "literal": "Tianbao Xie" }, { "literal": "Fan Zhou" }, { "literal": "Zhoujun Cheng" }, { "literal": "Peng Shi" }, { "literal": "Luoxuan Weng" }, { "literal": "Yitao Liu" }, { "literal": "Toh Jing Hua" }, { "literal": "Junning Zhao" }, { "literal": "Qian Liu" }, { "literal": "Che Liu" }, { "literal": "Leo Z. Liu" }, { "literal": "Yiheng Xu" }, { "literal": "Hongjin Su" }, { "literal": "Dongchan Shin" }, { "literal": "Caiming Xiong" }, { "literal": "Tao Yu" } ], "citation-key": "arxiv_2310_10634", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "15d7945fcf1ee4290761d34bbeef9e24bed82bb748bdb7aaa791457c42892fec", "submitted_at": "2023-10-16T17:54:53Z", "updated_at": "2023-10-16T17:54:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2310.10634v1" }, "canonical_source_url": "https://arxiv.org/abs/2310.10634", "catalog_id": "arxiv:2310.10634", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2023-10-16", "identifiers": { "arxiv": "2310.10634" }, "record_updated_at": "2023-10-16" }, "genre": "preprint", "id": "arxiv:2310.10634", "issued": { "date-parts": [ [ 2023, 10, 16 ] ] }, "note": "First published: 2023-10-16; Recorded arXiv version: v1; Recorded version updated: 2023-10-16T17:54:53Z.", "title": "OpenAgents: An Open Platform for Language Agents in the Wild", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2310.16042v2", "archive": "arXiv", "archive_location": "2310.16042", "author": [ { "literal": "Heyi Tao" }, { "literal": "Sethuraman T" }, { "literal": "Michal Shlapentokh-Rothman" }, { "literal": "Derek Hoiem" } ], "citation-key": "arxiv_2310_16042", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7defced3e3beb77a5a6513dbfdff3f102edd922907b523bd062522e54720fa5e", "submitted_at": "2023-10-24T17:57:03Z", "updated_at": "2023-10-25T03:54:11Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2310.16042v2" }, "canonical_source_url": "https://arxiv.org/abs/2310.16042", "catalog_id": "arxiv:2310.16042", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2023-10-24", "identifiers": { "arxiv": "2310.16042" }, "record_updated_at": "2023-10-25" }, "genre": "preprint", "id": "arxiv:2310.16042", "issued": { "date-parts": [ [ 2023, 10, 24 ] ] }, "note": "First published: 2023-10-24; Recorded arXiv version: v2; Recorded version updated: 2023-10-25T03:54:11Z.", "title": "WebWISE: Web Interface Control and Sequential Exploration with Large Language Models", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2311.01767v2", "archive": "arXiv", "archive_location": "2311.01767", "author": [ { "literal": "Yiduo Guo" }, { "literal": "Zekai Zhang" }, { "literal": "Yaobo Liang" }, { "literal": "Dongyan Zhao" }, { "literal": "Nan Duan" } ], "citation-key": "arxiv_2311_01767", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "58dfa75fd82a2cc1d41954f10feb1d987de6469782d11d04c3b8bfffc8a3b745", "submitted_at": "2023-11-03T08:06:35Z", "updated_at": "2023-11-07T10:13:34Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2311.01767v2" }, "canonical_source_url": "https://arxiv.org/abs/2311.01767", "catalog_id": "arxiv:2311.01767", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2023-11-03", "identifiers": { "arxiv": "2311.01767" }, "record_updated_at": "2023-11-07" }, "genre": "preprint", "id": "arxiv:2311.01767", "issued": { "date-parts": [ [ 2023, 11, 3 ] ] }, "note": "First published: 2023-11-03; Recorded arXiv version: v2; Recorded version updated: 2023-11-07T10:13:34Z.", "title": "PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2311.12983v1", "archive": "arXiv", "archive_location": "2311.12983", "author": [ { "literal": "Grégoire Mialon" }, { "literal": "Clémentine Fourrier" }, { "literal": "Craig Swift" }, { "literal": "Thomas Wolf" }, { "literal": "Yann LeCun" }, { "literal": "Thomas Scialom" } ], "citation-key": "arxiv_2311_12983", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "29ddf2b7b4d495ee18bbd263cd77f86a71b3014b58a6f140c3bfce7cbae9c922", "submitted_at": "2023-11-21T20:34:47Z", "updated_at": "2023-11-21T20:34:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2311.12983v1" }, "canonical_source_url": "https://arxiv.org/abs/2311.12983", "catalog_id": "arxiv:2311.12983", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2023-11-21", "identifiers": { "arxiv": "2311.12983" }, "record_updated_at": "2023-11-21" }, "genre": "preprint", "id": "arxiv:2311.12983", "issued": { "date-parts": [ [ 2023, 11, 21 ] ] }, "note": "First published: 2023-11-21; Recorded arXiv version: v1; Recorded version updated: 2023-11-21T20:34:47Z.", "title": "GAIA: a benchmark for General AI Assistants", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2402.07456v2", "archive": "arXiv", "archive_location": "2402.07456", "author": [ { "literal": "Zhiyong Wu" }, { "literal": "Chengcheng Han" }, { "literal": "Zichen Ding" }, { "literal": "Zhenmin Weng" }, { "literal": "Zhoumianze Liu" }, { "literal": "Shunyu Yao" }, { "literal": "Tao Yu" }, { "literal": "Lingpeng Kong" } ], "citation-key": "arxiv_2402_07456", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "674b005f670a3593bd215a8ff75eac05c90ee068578fc26afdd998c40f5b7b71", "submitted_at": "2024-02-12T07:29:22Z", "updated_at": "2024-02-15T09:30:48Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2402.07456v2" }, "canonical_source_url": "https://arxiv.org/abs/2402.07456", "catalog_id": "arxiv:2402.07456", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-02-12", "identifiers": { "arxiv": "2402.07456" }, "record_updated_at": "2024-02-15" }, "genre": "preprint", "id": "arxiv:2402.07456", "issued": { "date-parts": [ [ 2024, 2, 12 ] ] }, "note": "First published: 2024-02-12; Recorded arXiv version: v2; Recorded version updated: 2024-02-15T09:30:48Z.", "title": "OS-Copilot: Towards Generalist Computer Agents with Self-Improvement", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2406.09187v3", "archive": "arXiv", "archive_location": "2406.09187", "author": [ { "literal": "Zhen Xiang" }, { "literal": "Linzhi Zheng" }, { "literal": "Yanjie Li" }, { "literal": "Junyuan Hong" }, { "literal": "Qinbin Li" }, { "literal": "Han Xie" }, { "literal": "Jiawei Zhang" }, { "literal": "Zidi Xiong" }, { "literal": "Chulin Xie" }, { "literal": "Carl Yang" }, { "literal": "Dawn Song" }, { "literal": "Bo Li" } ], "citation-key": "arxiv_2406_09187", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "50a8ea492d3f1c2ff2bd00ebfb18e19077bacc96b44c751d985bfe0f7bef0247", "submitted_at": "2024-06-13T14:49:26Z", "updated_at": "2025-05-29T03:09:05Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2406.09187v3" }, "canonical_source_url": "https://arxiv.org/abs/2406.09187", "catalog_id": "arxiv:2406.09187", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2024-06-13", "identifiers": { "arxiv": "2406.09187" }, "record_updated_at": "2025-05-29" }, "genre": "preprint", "id": "arxiv:2406.09187", "issued": { "date-parts": [ [ 2024, 6, 13 ] ] }, "note": "First published: 2024-06-13; Recorded arXiv version: v3; Recorded version updated: 2025-05-29T03:09:05Z.", "title": "GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2407.00993v1", "archive": "arXiv", "archive_location": "2407.00993", "author": [ { "literal": "Shihan Deng" }, { "literal": "Weikai Xu" }, { "literal": "Hongda Sun" }, { "literal": "Wei Liu" }, { "literal": "Tao Tan" }, { "literal": "Jianfeng Liu" }, { "literal": "Ang Li" }, { "literal": "Jian Luan" }, { "literal": "Bin Wang" }, { "literal": "Rui Yan" }, { "literal": "Shuo Shang" } ], "citation-key": "arxiv_2407_00993", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "90ce9900644c21004e0ba9e749e10d94238d2447d0e84bd7205ff55dcbd243f4", "submitted_at": "2024-07-01T06:10:01Z", "updated_at": "2024-07-01T06:10:01Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2407.00993v1" }, "canonical_source_url": "https://arxiv.org/abs/2407.00993", "catalog_id": "arxiv:2407.00993", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-07-01", "identifiers": { "arxiv": "2407.00993" }, "record_updated_at": "2024-07-01" }, "genre": "preprint", "id": "arxiv:2407.00993", "issued": { "date-parts": [ [ 2024, 7, 1 ] ] }, "note": "First published: 2024-07-01; Recorded arXiv version: v1; Recorded version updated: 2024-07-01T06:10:01Z.", "title": "Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2407.03913v1", "archive": "arXiv", "archive_location": "2407.03913", "author": [ { "literal": "Jiayi Zhang" }, { "literal": "Chuang Zhao" }, { "literal": "Yihan Zhao" }, { "literal": "Zhaoyang Yu" }, { "literal": "Ming He" }, { "literal": "Jianping Fan" } ], "citation-key": "arxiv_2407_03913", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aa74755c53e20b3a9ff4b72e03a557f455ecceaefc96a50587aefd78ac3c8176", "submitted_at": "2024-07-04T13:12:19Z", "updated_at": "2024-07-04T13:12:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2407.03913v1" }, "canonical_source_url": "https://arxiv.org/abs/2407.03913", "catalog_id": "arxiv:2407.03913", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-07-04", "identifiers": { "arxiv": "2407.03913" }, "record_updated_at": "2024-07-04" }, "genre": "preprint", "id": "arxiv:2407.03913", "issued": { "date-parts": [ [ 2024, 7, 4 ] ] }, "note": "First published: 2024-07-04; Recorded arXiv version: v1; Recorded version updated: 2024-07-04T13:12:19Z.", "title": "MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devices", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2407.18901v1", "archive": "arXiv", "archive_location": "2407.18901", "author": [ { "literal": "Harsh Trivedi" }, { "literal": "Tushar Khot" }, { "literal": "Mareike Hartmann" }, { "literal": "Ruskin Manku" }, { "literal": "Vinty Dong" }, { "literal": "Edward Li" }, { "literal": "Shashank Gupta" }, { "literal": "Ashish Sabharwal" }, { "literal": "Niranjan Balasubramanian" } ], "citation-key": "arxiv_2407_18901", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e59087ecf28d07baf81b60e4166a866d4bea4d8cd934bea06c2149dd61f38f1a", "submitted_at": "2024-07-26T17:55:45Z", "updated_at": "2024-07-26T17:55:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2407.18901v1" }, "canonical_source_url": "https://arxiv.org/abs/2407.18901", "catalog_id": "arxiv:2407.18901", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2024-07-26", "identifiers": { "arxiv": "2407.18901" }, "record_updated_at": "2024-07-26" }, "genre": "preprint", "id": "arxiv:2407.18901", "issued": { "date-parts": [ [ 2024, 7, 26 ] ] }, "note": "First published: 2024-07-26; Recorded arXiv version: v1; Recorded version updated: 2024-07-26T17:55:45Z.", "title": "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2409.17140v2", "archive": "arXiv", "archive_location": "2409.17140", "author": [ { "literal": "Junting Lu" }, { "literal": "Zhiyang Zhang" }, { "literal": "Fangkai Yang" }, { "literal": "Jue Zhang" }, { "literal": "Lu Wang" }, { "literal": "Chao Du" }, { "literal": "Qingwei Lin" }, { "literal": "Saravan Rajmohan" }, { "literal": "Dongmei Zhang" }, { "literal": "Qi Zhang" } ], "citation-key": "arxiv_2409_17140", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "618f41c2253a532780766b38396f241a48b587c580d6b4d7065d1519e6149751", "submitted_at": "2024-09-25T17:58:08Z", "updated_at": "2025-05-19T16:12:40Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.17140v2" }, "canonical_source_url": "https://arxiv.org/abs/2409.17140", "catalog_id": "arxiv:2409.17140", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-09-25", "identifiers": { "arxiv": "2409.17140" }, "publication": { "authors": [ "Junting Lu", "Zhiyang Zhang", "Fangkai Yang", "Jue Zhang", "Lu Wang", "Chao Du", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.acl-long.381", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.acl-long.381/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "7711-7743", "pdf_url": "https://aclanthology.org/2025.acl-long.381.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.381/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null }, "record_updated_at": "2025-05-19" }, "genre": "preprint", "id": "arxiv:2409.17140", "issued": { "date-parts": [ [ 2024, 9, 25 ] ] }, "note": "First published: 2024-09-25; Recorded arXiv version: v2; Recorded version updated: 2025-05-19T16:12:40Z.", "title": "AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2410.16464v3", "archive": "arXiv", "archive_location": "2410.16464", "author": [ { "literal": "Yueqi Song" }, { "literal": "Frank Xu" }, { "literal": "Shuyan Zhou" }, { "literal": "Graham Neubig" } ], "citation-key": "arxiv_2410_16464", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0944387dd3c65ea7b2f5ca52721496cf10b3c9860b303063201e7811318f4950", "submitted_at": "2024-10-21T19:46:06Z", "updated_at": "2025-06-16T22:23:37Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2410.16464v3" }, "canonical_source_url": "https://arxiv.org/abs/2410.16464", "catalog_id": "arxiv:2410.16464", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-10-21", "identifiers": { "arxiv": "2410.16464" }, "publication": { "authors": [ "Yueqi Song", "Frank F. Xu", "Shuyan Zhou", "Graham Neubig" ], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 7 ], "doi": "10.18653/v1/2025.findings-acl.577", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.findings-acl.577/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "11066-11085", "pdf_url": "https://aclanthology.org/2025.findings-acl.577.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Beyond Browsing: API-Based Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.577/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null }, "record_updated_at": "2025-06-16" }, "genre": "preprint", "id": "arxiv:2410.16464", "issued": { "date-parts": [ [ 2024, 10, 21 ] ] }, "note": "First published: 2024-10-21; Recorded arXiv version: v3; Recorded version updated: 2025-06-16T22:23:37Z.", "title": "Beyond Browsing: API-Based Web Agents", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2410.18603v1", "archive": "arXiv", "archive_location": "2410.18603", "author": [ { "literal": "Chengyou Jia" }, { "literal": "Minnan Luo" }, { "literal": "Zhuohang Dang" }, { "literal": "Qiushi Sun" }, { "literal": "Fangzhi Xu" }, { "literal": "Junlin Hu" }, { "literal": "Tianbao Xie" }, { "literal": "Zhiyong Wu" } ], "citation-key": "arxiv_2410_18603", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ece9f64cc037dad8633388edf1b54d88818d8092b77e19b15780e929b23aa593", "submitted_at": "2024-10-24T09:58:40Z", "updated_at": "2024-10-24T09:58:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2410.18603v1" }, "canonical_source_url": "https://arxiv.org/abs/2410.18603", "catalog_id": "arxiv:2410.18603", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-10-24", "identifiers": { "arxiv": "2410.18603" }, "record_updated_at": "2024-10-24" }, "genre": "preprint", "id": "arxiv:2410.18603", "issued": { "date-parts": [ [ 2024, 10, 24 ] ] }, "note": "First published: 2024-10-24; Recorded arXiv version: v1; Recorded version updated: 2024-10-24T09:58:40Z.", "title": "AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2410.18963v1", "archive": "arXiv", "archive_location": "2410.18963", "author": [ { "literal": "Xiaoqiang Wang" }, { "literal": "Bang Liu" } ], "citation-key": "arxiv_2410_18963", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "66fa51b108ac79cc43a895ba757ca463d5008bfe6db5cde4bdf3a3bb38c444eb", "submitted_at": "2024-10-24T17:58:08Z", "updated_at": "2024-10-24T17:58:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2410.18963v1" }, "canonical_source_url": "https://arxiv.org/abs/2410.18963", "catalog_id": "arxiv:2410.18963", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-10-24", "identifiers": { "arxiv": "2410.18963" }, "record_updated_at": "2024-10-24" }, "genre": "preprint", "id": "arxiv:2410.18963", "issued": { "date-parts": [ [ 2024, 10, 24 ] ] }, "note": "First published: 2024-10-24; Recorded arXiv version: v1; Recorded version updated: 2024-10-24T17:58:08Z.", "title": "OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2411.04468v1", "archive": "arXiv", "archive_location": "2411.04468", "author": [ { "literal": "Adam Fourney" }, { "literal": "Gagan Bansal" }, { "literal": "Hussein Mozannar" }, { "literal": "Cheng Tan" }, { "literal": "Eduardo Salinas" }, { "literal": "Erkang" }, { "literal": "Zhu" }, { "literal": "Friederike Niedtner" }, { "literal": "Grace Proebsting" }, { "literal": "Griffin Bassman" }, { "literal": "Jack Gerrits" }, { "literal": "Jacob Alber" }, { "literal": "Peter Chang" }, { "literal": "Ricky Loynd" }, { "literal": "Robert West" }, { "literal": "Victor Dibia" }, { "literal": "Ahmed Awadallah" }, { "literal": "Ece Kamar" }, { "literal": "Rafah Hosn" }, { "literal": "Saleema Amershi" } ], "citation-key": "arxiv_2411_04468", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4a2c499237dbcbe1482824a2710f5185dee05c9ed66a0882d1e422f30afe056a", "submitted_at": "2024-11-07T06:36:19Z", "updated_at": "2024-11-07T06:36:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2411.04468v1" }, "canonical_source_url": "https://arxiv.org/abs/2411.04468", "catalog_id": "arxiv:2411.04468", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2024-11-07", "identifiers": { "arxiv": "2411.04468" }, "record_updated_at": "2024-11-07" }, "genre": "preprint", "id": "arxiv:2411.04468", "issued": { "date-parts": [ [ 2024, 11, 7 ] ] }, "note": "First published: 2024-11-07; Recorded arXiv version: v1; Recorded version updated: 2024-11-07T06:36:19Z.", "title": "Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2412.00402v1", "archive": "arXiv", "archive_location": "2412.00402", "author": [ { "literal": "Weikai Xie" }, { "literal": "Li Zhang" }, { "literal": "Shihe Wang" }, { "literal": "Rongjie Yi" }, { "literal": "Mengwei Xu" } ], "citation-key": "arxiv_2412_00402", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9c22d6a9aafb89e5628198fb4f6ea50fe40b1e955a2fa367571459753cea61df", "submitted_at": "2024-11-30T08:55:39Z", "updated_at": "2024-11-30T08:55:39Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2412.00402v1" }, "canonical_source_url": "https://arxiv.org/abs/2412.00402", "catalog_id": "arxiv:2412.00402", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2024-11-30", "identifiers": { "arxiv": "2412.00402" }, "record_updated_at": "2024-11-30" }, "genre": "preprint", "id": "arxiv:2412.00402", "issued": { "date-parts": [ [ 2024, 11, 30 ] ] }, "note": "First published: 2024-11-30; Recorded arXiv version: v1; Recorded version updated: 2024-11-30T08:55:39Z.", "title": "DroidCall: A Dataset for LLM-powered Android Intent Invocation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2412.18116v3", "archive": "arXiv", "archive_location": "2412.18116", "author": [ { "literal": "Hao Wen" }, { "literal": "Shizuo Tian" }, { "literal": "Borislav Pavlov" }, { "literal": "Wenjie Du" }, { "literal": "Yixuan Li" }, { "literal": "Ge Chang" }, { "literal": "Shanhui Zhao" }, { "literal": "Jiacheng Liu" }, { "literal": "Yunxin Liu" }, { "literal": "Ya-Qin Zhang" }, { "literal": "Yuanchun Li" } ], "citation-key": "arxiv_2412_18116", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3190c452dbfa24b131cc34f66192bbdb9c538d30a1919082a9fed334f6169fff", "submitted_at": "2024-12-24T02:54:56Z", "updated_at": "2025-05-06T12:24:43Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2412.18116v3" }, "canonical_source_url": "https://arxiv.org/abs/2412.18116", "catalog_id": "arxiv:2412.18116", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-12-24", "identifiers": { "arxiv": "2412.18116" }, "record_updated_at": "2025-05-06" }, "genre": "preprint", "id": "arxiv:2412.18116", "issued": { "date-parts": [ [ 2024, 12, 24 ] ] }, "note": "First published: 2024-12-24; Recorded arXiv version: v3; Recorded version updated: 2025-05-06T12:24:43Z.", "title": "AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2502.18525v2", "archive": "arXiv", "archive_location": "2502.18525", "author": [ { "literal": "Pranjal Aggarwal" }, { "literal": "Sean Welleck" } ], "citation-key": "arxiv_2502_18525", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9e4091fc740249b6406dd9e96f2692d7fac9323759ec6fad6ba5a05f3e445844", "submitted_at": "2025-02-24T18:41:33Z", "updated_at": "2025-10-03T02:09:59Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2502.18525v2" }, "canonical_source_url": "https://arxiv.org/abs/2502.18525", "catalog_id": "arxiv:2502.18525", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-02-24", "identifiers": { "arxiv": "2502.18525" }, "record_updated_at": "2025-10-03" }, "genre": "preprint", "id": "arxiv:2502.18525", "issued": { "date-parts": [ [ 2025, 2, 24 ] ] }, "note": "First published: 2025-02-24; Recorded arXiv version: v2; Recorded version updated: 2025-10-03T02:09:59Z.", "title": "Programming with Pixels: Can Computer-Use Agents do Software Engineering?", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2503.02950v2", "archive": "arXiv", "archive_location": "2503.02950", "author": [ { "literal": "Danqing Zhang" }, { "literal": "Balaji Rama" }, { "literal": "Jingyi Ni" }, { "literal": "Shiying He" }, { "literal": "Fu Zhao" }, { "literal": "Kunyu Chen" }, { "literal": "Arnold Chen" }, { "literal": "Junyu Cao" } ], "citation-key": "arxiv_2503_02950", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "df682f883bed5e0e9917074dfa130839fabaa318c55714f26943d944774854fe", "submitted_at": "2025-03-04T19:13:10Z", "updated_at": "2025-05-06T06:42:34Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.02950v2" }, "canonical_source_url": "https://arxiv.org/abs/2503.02950", "catalog_id": "arxiv:2503.02950", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2025-03-04", "identifiers": { "arxiv": "2503.02950" }, "publication": { "authors": [ "Danqing Zhang", "Balaji Rama", "Jingyi Ni", "Shiying He", "Fu Zhao", "Kunyu Chen", "Arnold Chen", "Junyu Cao" ], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2025, 4 ], "doi": "10.18653/v1/2025.naacl-demo.36", "event_dates": null, "evidence_urls": [ "https://aclanthology.org/2025.naacl-demo.36/" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "449-455", "pdf_url": "https://aclanthology.org/2025.naacl-demo.36.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-demo.36/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "volume": null }, "record_updated_at": "2025-05-06" }, "genre": "preprint", "id": "arxiv:2503.02950", "issued": { "date-parts": [ [ 2025, 3, 4 ] ] }, "note": "First published: 2025-03-04; Recorded arXiv version: v2; Recorded version updated: 2025-05-06T06:42:34Z.", "title": "LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2503.11069v2", "archive": "arXiv", "archive_location": "2503.11069", "author": [ { "literal": "Chaoyun Zhang" }, { "literal": "Shilin He" }, { "literal": "Liqun Li" }, { "literal": "Si Qin" }, { "literal": "Yu Kang" }, { "literal": "Qingwei Lin" }, { "literal": "Saravan Rajmohan" }, { "literal": "Dongmei Zhang" } ], "citation-key": "arxiv_2503_11069", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "43a533866496d3ebd3e34c04142a702e4a3aaa387c3830e3bb993fdbb0ce8432", "submitted_at": "2025-03-14T04:26:21Z", "updated_at": "2025-06-23T13:01:02Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.11069v2" }, "canonical_source_url": "https://arxiv.org/abs/2503.11069", "catalog_id": "arxiv:2503.11069", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-03-14", "identifiers": { "arxiv": "2503.11069" }, "record_updated_at": "2025-06-23" }, "genre": "preprint", "id": "arxiv:2503.11069", "issued": { "date-parts": [ [ 2025, 3, 14 ] ] }, "note": "First published: 2025-03-14; Recorded arXiv version: v2; Recorded version updated: 2025-06-23T13:01:02Z.", "title": "API Agents vs. GUI Agents: Divergence and Convergence", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2504.07079v1", "archive": "arXiv", "archive_location": "2504.07079", "author": [ { "literal": "Boyuan Zheng" }, { "literal": "Michael Y. Fatemi" }, { "literal": "Xiaolong Jin" }, { "literal": "Zora Zhiruo Wang" }, { "literal": "Apurva Gandhi" }, { "literal": "Yueqi Song" }, { "literal": "Yu Gu" }, { "literal": "Jayanth Srinivasa" }, { "literal": "Gaowen Liu" }, { "literal": "Graham Neubig" }, { "literal": "Yu Su" } ], "citation-key": "arxiv_2504_07079", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5f0489433a41b49ab8ab42eea57503685ba60beadabea7822134e96d865a7435", "submitted_at": "2025-04-09T17:51:50Z", "updated_at": "2025-04-09T17:51:50Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2504.07079v1" }, "canonical_source_url": "https://arxiv.org/abs/2504.07079", "catalog_id": "arxiv:2504.07079", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-09", "identifiers": { "arxiv": "2504.07079" }, "record_updated_at": "2025-04-09" }, "genre": "preprint", "id": "arxiv:2504.07079", "issued": { "date-parts": [ [ 2025, 4, 9 ] ] }, "note": "First published: 2025-04-09; Recorded arXiv version: v1; Recorded version updated: 2025-04-09T17:51:50Z.", "title": "SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2504.14603v2", "archive": "arXiv", "archive_location": "2504.14603", "author": [ { "literal": "Chaoyun Zhang" }, { "literal": "He Huang" }, { "literal": "Chiming Ni" }, { "literal": "Jian Mu" }, { "literal": "Si Qin" }, { "literal": "Shilin He" }, { "literal": "Lu Wang" }, { "literal": "Fangkai Yang" }, { "literal": "Pu Zhao" }, { "literal": "Chao Du" }, { "literal": "Liqun Li" }, { "literal": "Yu Kang" }, { "literal": "Zhao Jiang" }, { "literal": "Suzhen Zheng" }, { "literal": "Rujia Wang" }, { "literal": "Jiaxu Qian" }, { "literal": "Minghua Ma" }, { "literal": "Jian-Guang Lou" }, { "literal": "Qingwei Lin" }, { "literal": "Saravan Rajmohan" }, { "literal": "Dongmei Zhang" } ], "citation-key": "arxiv_2504_14603", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dc47a80b48a6a5f126e36fa14639d56d8c8025a453fbcee2cbdb73eb67945561", "submitted_at": "2025-04-20T13:04:43Z", "updated_at": "2025-04-25T05:14:14Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.14603v2" }, "canonical_source_url": "https://arxiv.org/abs/2504.14603", "catalog_id": "arxiv:2504.14603", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-20", "identifiers": { "arxiv": "2504.14603" }, "record_updated_at": "2025-04-25" }, "genre": "preprint", "id": "arxiv:2504.14603", "issued": { "date-parts": [ [ 2025, 4, 20 ] ] }, "note": "First published: 2025-04-20; Recorded arXiv version: v2; Recorded version updated: 2025-04-25T05:14:14Z.", "title": "UFO2: The Desktop AgentOS", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2504.21776v2", "archive": "arXiv", "archive_location": "2504.21776", "author": [ { "literal": "Xiaoxi Li" }, { "literal": "Jiajie Jin" }, { "literal": "Guanting Dong" }, { "literal": "Hongjin Qian" }, { "literal": "Yongkang Wu" }, { "literal": "Ji-Rong Wen" }, { "literal": "Yutao Zhu" }, { "literal": "Zhicheng Dou" } ], "citation-key": "arxiv_2504_21776", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "351b6d7fbe4e217a5211884832c6ad07d76a0463e6a8c996815999ff3a5f1921", "submitted_at": "2025-04-30T16:25:25Z", "updated_at": "2025-10-13T12:40:15Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.21776v2" }, "canonical_source_url": "https://arxiv.org/abs/2504.21776", "catalog_id": "arxiv:2504.21776", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2025-04-30", "identifiers": { "arxiv": "2504.21776" }, "record_updated_at": "2025-10-13" }, "genre": "preprint", "id": "arxiv:2504.21776", "issued": { "date-parts": [ [ 2025, 4, 30 ] ] }, "note": "First published: 2025-04-30; Recorded arXiv version: v2; Recorded version updated: 2025-10-13T12:40:15Z.", "title": "WebThinker: Empowering Large Reasoning Models with Deep Research Capability", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2505.18829v2", "archive": "arXiv", "archive_location": "2505.18829", "author": [ { "literal": "Kai Mei" }, { "literal": "Xi Zhu" }, { "literal": "Hang Gao" }, { "literal": "Shuhang Lin" }, { "literal": "Yongfeng Zhang" } ], "citation-key": "arxiv_2505_18829", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2c382ce428e6dd41ec07af7575461c69906ce386fd2bcd8ad9f0d792d2b8f0b3", "submitted_at": "2025-05-24T18:56:00Z", "updated_at": "2025-10-31T21:48:48Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2505.18829v2" }, "canonical_source_url": "https://arxiv.org/abs/2505.18829", "catalog_id": "arxiv:2505.18829", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-24", "identifiers": { "arxiv": "2505.18829" }, "record_updated_at": "2025-10-31" }, "genre": "preprint", "id": "arxiv:2505.18829", "issued": { "date-parts": [ [ 2025, 5, 24 ] ] }, "note": "First published: 2025-05-24; Recorded arXiv version: v2; Recorded version updated: 2025-10-31T21:48:48Z.", "title": "LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2506.07672v1", "archive": "arXiv", "archive_location": "2506.07672", "author": [ { "literal": "Yunhe Yan" }, { "literal": "Shihe Wang" }, { "literal": "Jiajun Du" }, { "literal": "Yexuan Yang" }, { "literal": "Yuxuan Shan" }, { "literal": "Qichen Qiu" }, { "literal": "Xianqing Jia" }, { "literal": "Xinge Wang" }, { "literal": "Xin Yuan" }, { "literal": "Xu Han" }, { "literal": "Mao Qin" }, { "literal": "Yinxiao Chen" }, { "literal": "Chen Peng" }, { "literal": "Shangguang Wang" }, { "literal": "Mengwei Xu" } ], "citation-key": "arxiv_2506_07672", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2334e017fe49b39dc5d460963988f05d11051f2101bebe23be76005809fafd45", "submitted_at": "2025-06-09T11:50:33Z", "updated_at": "2025-06-09T11:50:33Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2506.07672v1" }, "canonical_source_url": "https://arxiv.org/abs/2506.07672", "catalog_id": "arxiv:2506.07672", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-09", "identifiers": { "arxiv": "2506.07672" }, "record_updated_at": "2025-06-09" }, "genre": "preprint", "id": "arxiv:2506.07672", "issued": { "date-parts": [ [ 2025, 6, 9 ] ] }, "note": "First published: 2025-06-09; Recorded arXiv version: v1; Recorded version updated: 2025-06-09T11:50:33Z.", "title": "MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2507.22358v1", "archive": "arXiv", "archive_location": "2507.22358", "author": [ { "literal": "Hussein Mozannar" }, { "literal": "Gagan Bansal" }, { "literal": "Cheng Tan" }, { "literal": "Adam Fourney" }, { "literal": "Victor Dibia" }, { "literal": "Jingya Chen" }, { "literal": "Jack Gerrits" }, { "literal": "Tyler Payne" }, { "literal": "Matheus Kunzler Maldaner" }, { "literal": "Madeleine Grunde-McLaughlin" }, { "literal": "Eric Zhu" }, { "literal": "Griffin Bassman" }, { "literal": "Jacob Alber" }, { "literal": "Peter Chang" }, { "literal": "Ricky Loynd" }, { "literal": "Friederike Niedtner" }, { "literal": "Ece Kamar" }, { "literal": "Maya Murad" }, { "literal": "Rafah Hosn" }, { "literal": "Saleema Amershi" } ], "citation-key": "arxiv_2507_22358", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c9416ede89036d640412496b5f0def218b69271c5f2449689d4e4afacb43c556", "submitted_at": "2025-07-30T03:49:14Z", "updated_at": "2025-07-30T03:49:14Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2507.22358v1" }, "canonical_source_url": "https://arxiv.org/abs/2507.22358", "catalog_id": "arxiv:2507.22358", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-07-30", "identifiers": { "arxiv": "2507.22358" }, "record_updated_at": "2025-07-30" }, "genre": "preprint", "id": "arxiv:2507.22358", "issued": { "date-parts": [ [ 2025, 7, 30 ] ] }, "note": "First published: 2025-07-30; Recorded arXiv version: v1; Recorded version updated: 2025-07-30T03:49:14Z.", "title": "Magentic-UI: Towards Human-in-the-loop Agentic Systems", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2508.03923v3", "archive": "arXiv", "archive_location": "2508.03923", "author": [ { "literal": "Linxin Song" }, { "literal": "Yutong Dai" }, { "literal": "Viraj Prabhu" }, { "literal": "Jieyu Zhang" }, { "literal": "Taiwei Shi" }, { "literal": "Li Li" }, { "literal": "Junnan Li" }, { "literal": "Silvio Savarese" }, { "literal": "Zeyuan Chen" }, { "literal": "Jieyu Zhao" }, { "literal": "Ran Xu" }, { "literal": "Caiming Xiong" } ], "citation-key": "arxiv_2508_03923", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b6e4272a69c1a93f22bd35032547ffb6021a79c97d179a1075e14aee69dea83a", "submitted_at": "2025-08-05T21:33:36Z", "updated_at": "2026-02-20T10:14:08Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2508.03923v3" }, "canonical_source_url": "https://arxiv.org/abs/2508.03923", "catalog_id": "arxiv:2508.03923", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-05", "identifiers": { "arxiv": "2508.03923" }, "record_updated_at": "2026-02-20" }, "genre": "preprint", "id": "arxiv:2508.03923", "issued": { "date-parts": [ [ 2025, 8, 5 ] ] }, "note": "First published: 2025-08-05; Recorded arXiv version: v3; Recorded version updated: 2026-02-20T10:14:08Z.", "title": "CoAct-1: Computer-using Multi-Agent System with Coding Actions", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2508.14040v2", "archive": "arXiv", "archive_location": "2508.14040", "author": [ { "literal": "Hanyu Lai" }, { "literal": "Xiao Liu" }, { "literal": "Yanxiao Zhao" }, { "literal": "Han Xu" }, { "literal": "Hanchen Zhang" }, { "literal": "Bohao Jing" }, { "literal": "Yanyu Ren" }, { "literal": "Shuntian Yao" }, { "literal": "Yuxiao Dong" }, { "literal": "Jie Tang" } ], "citation-key": "arxiv_2508_14040", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "383d8e80619d58e72ebb9c49229cd9522a0b3586b4bfa8f00b29b1834adca5b9", "submitted_at": "2025-08-19T17:59:45Z", "updated_at": "2025-10-21T05:18:04Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.14040v2" }, "canonical_source_url": "https://arxiv.org/abs/2508.14040", "catalog_id": "arxiv:2508.14040", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-19", "identifiers": { "arxiv": "2508.14040" }, "record_updated_at": "2025-10-21" }, "genre": "preprint", "id": "arxiv:2508.14040", "issued": { "date-parts": [ [ 2025, 8, 19 ] ] }, "note": "First published: 2025-08-19; Recorded arXiv version: v2; Recorded version updated: 2025-10-21T05:18:04Z.", "title": "ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2509.01619v1", "archive": "arXiv", "archive_location": "2509.01619", "author": [ { "literal": "Abhinav Kumar" }, { "literal": "Jaechul Roh" }, { "literal": "Ali Naseh" }, { "literal": "Amir Houmansadr" }, { "literal": "Eugene Bagdasarian" } ], "citation-key": "arxiv_2509_01619", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0f6ff68c59cede9cf59c039416a87ea39b926e3a3179b9f81af9354767befb93", "submitted_at": "2025-09-01T16:56:16Z", "updated_at": "2025-09-01T16:56:16Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.01619v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.01619", "catalog_id": "arxiv:2509.01619", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2025-09-01", "identifiers": { "arxiv": "2509.01619" }, "record_updated_at": "2025-09-01" }, "genre": "preprint", "id": "arxiv:2509.01619", "issued": { "date-parts": [ [ 2025, 9, 1 ] ] }, "note": "First published: 2025-09-01; Recorded arXiv version: v1; Recorded version updated: 2025-09-01T16:56:16Z.", "title": "Throttling Web Agents Using Reasoning Gates", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.02544v2", "archive": "arXiv", "archive_location": "2509.02544", "author": [ { "literal": "Haoming Wang" }, { "literal": "Haoyang Zou" }, { "literal": "Huatong Song" }, { "literal": "Jiazhan Feng" }, { "literal": "Junjie Fang" }, { "literal": "Junting Lu" }, { "literal": "Longxiang Liu" }, { "literal": "Qinyu Luo" }, { "literal": "Shihao Liang" }, { "literal": "Shijue Huang" }, { "literal": "Wanjun Zhong" }, { "literal": "Yining Ye" }, { "literal": "Yujia Qin" }, { "literal": "Yuwen Xiong" }, { "literal": "Yuxin Song" }, { "literal": "Zhiyong Wu" }, { "literal": "Aoyan Li" }, { "literal": "Bo Li" }, { "literal": "Chen Dun" }, { "literal": "Chong Liu" }, { "literal": "Daoguang Zan" }, { "literal": "Fuxing Leng" }, { "literal": "Hanbin Wang" }, { "literal": "Hao Yu" }, { "literal": "Haobin Chen" }, { "literal": "Hongyi Guo" }, { "literal": "Jing Su" }, { "literal": "Jingjia Huang" }, { "literal": "Kai Shen" }, { "literal": "Kaiyu Shi" }, { "literal": "Lin Yan" }, { "literal": "Peiyao Zhao" }, { "literal": "Pengfei Liu" }, { "literal": "Qinghao Ye" }, { "literal": "Renjie Zheng" }, { "literal": "Shulin Xin" }, { "literal": "Wayne Xin Zhao" }, { "literal": "Wen Heng" }, { "literal": "Wenhao Huang" }, { "literal": "Wenqian Wang" }, { "literal": "Xiaobo Qin" }, { "literal": "Yi Lin" }, { "literal": "Youbin Wu" }, { "literal": "Zehui Chen" }, { "literal": "Zihao Wang" }, { "literal": "Baoquan Zhong" }, { "literal": "Xinchun Zhang" }, { "literal": "Xujing Li" }, { "literal": "Yuanfan Li" }, { "literal": "Zhongkai Zhao" }, { "literal": "Chengquan Jiang" }, { "literal": "Faming Wu" }, { "literal": "Haotian Zhou" }, { "literal": "Jinlin Pang" }, { "literal": "Li Han" }, { "literal": "Qi Liu" }, { "literal": "Qianli Ma" }, { "literal": "Siyao Liu" }, { "literal": "Songhua Cai" }, { "literal": "Wenqi Fu" }, { "literal": "Xin Liu" }, { "literal": "Yaohui Wang" }, { "literal": "Zhi Zhang" }, { "literal": "Bo Zhou" }, { "literal": "Guoliang Li" }, { "literal": "Jiajun Shi" }, { "literal": "Jiale Yang" }, { "literal": "Jie Tang" }, { "literal": "Li Li" }, { "literal": "Qihua Han" }, { "literal": "Taoran Lu" }, { "literal": "Woyu Lin" }, { "literal": "Xiaokang Tong" }, { "literal": "Xinyao Li" }, { "literal": "Yichi Zhang" }, { "literal": "Yu Miao" }, { "literal": "Zhengxuan Jiang" }, { "literal": "Zili Li" }, { "literal": "Ziyuan Zhao" }, { "literal": "Chenxin Li" }, { "literal": "Dehua Ma" }, { "literal": "Feng Lin" }, { "literal": "Ge Zhang" }, { "literal": "Haihua Yang" }, { "literal": "Hangyu Guo" }, { "literal": "Hongda Zhu" }, { "literal": "Jiaheng Liu" }, { "literal": "Junda Du" }, { "literal": "Kai Cai" }, { "literal": "Kuanye Li" }, { "literal": "Lichen Yuan" }, { "literal": "Meilan Han" }, { "literal": "Minchao Wang" }, { "literal": "Shuyue Guo" }, { "literal": "Tianhao Cheng" }, { "literal": "Xiaobo Ma" }, { "literal": "Xiaojun Xiao" }, { "literal": "Xiaolong Huang" }, { "literal": "Xinjie Chen" }, { "literal": "Yidi Du" }, { "literal": "Yilin Chen" }, { "literal": "Yiwen Wang" }, { "literal": "Zhaojian Li" }, { "literal": "Zhenzhu Yang" }, { "literal": "Zhiyuan Zeng" }, { "literal": "Chaolin Jin" }, { "literal": "Chen Li" }, { "literal": "Hao Chen" }, { "literal": "Haoli Chen" }, { "literal": "Jian Chen" }, { "literal": "Qinghao Zhao" }, { "literal": "Guang Shi" } ], "citation-key": "arxiv_2509_02544", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "800e417f4a2f720beb436ddd2e7bc60f0dd2483b44ac007a72a5eab2c6001ff8", "submitted_at": "2025-09-02T17:44:45Z", "updated_at": "2025-09-05T14:59:27Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.02544v2" }, "canonical_source_url": "https://arxiv.org/abs/2509.02544", "catalog_id": "arxiv:2509.02544", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-02", "identifiers": { "arxiv": "2509.02544" }, "record_updated_at": "2025-09-05" }, "genre": "preprint", "id": "arxiv:2509.02544", "issued": { "date-parts": [ [ 2025, 9, 2 ] ] }, "note": "First published: 2025-09-02; Recorded arXiv version: v2; Recorded version updated: 2025-09-05T14:59:27Z.", "title": "UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2509.06477v2", "archive": "arXiv", "archive_location": "2509.06477", "author": [ { "literal": "Pengxiang Zhao" }, { "literal": "Guangyi Liu" }, { "literal": "YaoZhen Liang" }, { "literal": "Weiqing He" }, { "literal": "Zhengxi Lu" }, { "literal": "WenHao Wang" }, { "literal": "Yuehao Huang" }, { "literal": "Yuxiang Chai" }, { "literal": "Zhaolu Kang" }, { "literal": "Yaxuan Guo" }, { "literal": "Hao Wang" }, { "literal": "Kexin Zhang" }, { "literal": "Liang Liu" }, { "literal": "Yong Liu" } ], "citation-key": "arxiv_2509_06477", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9b1e0e807f5f396bfd9108ab6cfacd48ed4780abfb792589da0b41d7d246c717", "submitted_at": "2025-09-08T09:43:48Z", "updated_at": "2026-04-15T11:26:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.06477v2" }, "canonical_source_url": "https://arxiv.org/abs/2509.06477", "catalog_id": "arxiv:2509.06477", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-08", "identifiers": { "arxiv": "2509.06477" }, "record_updated_at": "2026-04-15" }, "genre": "preprint", "id": "arxiv:2509.06477", "issued": { "date-parts": [ [ 2025, 9, 8 ] ] }, "note": "First published: 2025-09-08; Recorded arXiv version: v2; Recorded version updated: 2026-04-15T11:26:55Z.", "title": "MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2509.22256v4", "archive": "arXiv", "archive_location": "2509.22256", "author": [ { "literal": "Haochen Gong" }, { "literal": "Chenxiao Li" }, { "literal": "Rui Chang" }, { "literal": "Wenbo Shen" } ], "citation-key": "arxiv_2509_22256", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "922c1d9b60db7c17b9019a320a4cfc2dd4eac325fd946f024ca82d43785f5eba", "submitted_at": "2025-09-26T12:19:27Z", "updated_at": "2026-01-14T06:07:30Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2509.22256v4" }, "canonical_source_url": "https://arxiv.org/abs/2509.22256", "catalog_id": "arxiv:2509.22256", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-26", "identifiers": { "arxiv": "2509.22256" }, "record_updated_at": "2026-01-14" }, "genre": "preprint", "id": "arxiv:2509.22256", "issued": { "date-parts": [ [ 2025, 9, 26 ] ] }, "note": "First published: 2025-09-26; Recorded arXiv version: v4; Recorded version updated: 2026-01-14T06:07:30Z.", "title": "Secure and Efficient Access Control for Computer-Use Agents via Context Space", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2509.26539v1", "archive": "arXiv", "archive_location": "2509.26539", "author": [ { "literal": "Zhen Yang" }, { "literal": "Zi-Yi Dou" }, { "literal": "Di Feng" }, { "literal": "Forrest Huang" }, { "literal": "Anh Nguyen" }, { "literal": "Keen You" }, { "literal": "Omar Attia" }, { "literal": "Yuhao Yang" }, { "literal": "Michael Feng" }, { "literal": "Haotian Zhang" }, { "literal": "Ram Ramrakhya" }, { "literal": "Chao Jia" }, { "literal": "Jeffrey Nichols" }, { "literal": "Alexander Toshev" }, { "literal": "Yinfei Yang" }, { "literal": "Zhe Gan" } ], "citation-key": "arxiv_2509_26539", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "daa35e6bcd86fbdb709652d3592776ed93aebe2a0ebb3595fed91478dc0e3e0a", "submitted_at": "2025-09-30T17:13:56Z", "updated_at": "2025-09-30T17:13:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.26539v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.26539", "catalog_id": "arxiv:2509.26539", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-30", "identifiers": { "arxiv": "2509.26539" }, "record_updated_at": "2025-09-30" }, "genre": "preprint", "id": "arxiv:2509.26539", "issued": { "date-parts": [ [ 2025, 9, 30 ] ] }, "note": "First published: 2025-09-30; Recorded arXiv version: v1; Recorded version updated: 2025-09-30T17:13:56Z.", "title": "Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2510.01524v1", "archive": "arXiv", "archive_location": "2510.01524", "author": [ { "literal": "Viraj Prabhu" }, { "literal": "Yutong Dai" }, { "literal": "Matthew Fernandez" }, { "literal": "Jing Gu" }, { "literal": "Krithika Ramakrishnan" }, { "literal": "Yanqi Luo" }, { "literal": "Silvio Savarese" }, { "literal": "Caiming Xiong" }, { "literal": "Junnan Li" }, { "literal": "Zeyuan Chen" }, { "literal": "Ran Xu" } ], "citation-key": "arxiv_2510_01524", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "23794419031fe219fc342c041d666045080b274926dc22ab101a65581b4e4efd", "submitted_at": "2025-10-01T23:41:47Z", "updated_at": "2025-10-01T23:41:47Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.01524v1" }, "canonical_source_url": "https://arxiv.org/abs/2510.01524", "catalog_id": "arxiv:2510.01524", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-01", "identifiers": { "arxiv": "2510.01524" }, "record_updated_at": "2025-10-01" }, "genre": "preprint", "id": "arxiv:2510.01524", "issued": { "date-parts": [ [ 2025, 10, 1 ] ] }, "note": "First published: 2025-10-01; Recorded arXiv version: v1; Recorded version updated: 2025-10-01T23:41:47Z.", "title": "WALT: Web Agents that Learn Tools", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2510.04039v1", "archive": "arXiv", "archive_location": "2510.04039", "author": [ { "literal": "Bin Lei" }, { "literal": "Nuo Xu" }, { "literal": "Ali Payani" }, { "literal": "Mingyi Hong" }, { "literal": "Chunhua Liao" }, { "literal": "Yu Cao" }, { "literal": "Caiwen Ding" } ], "citation-key": "arxiv_2510_04039", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "798fc5ca4fe483a1235f0979b0c641e9c1732660780c13340c5221319a1b28fc", "submitted_at": "2025-10-05T05:15:45Z", "updated_at": "2025-10-05T05:15:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.04039v1" }, "canonical_source_url": "https://arxiv.org/abs/2510.04039", "catalog_id": "arxiv:2510.04039", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-05", "identifiers": { "arxiv": "2510.04039" }, "record_updated_at": "2025-10-05" }, "genre": "preprint", "id": "arxiv:2510.04039", "issued": { "date-parts": [ [ 2025, 10, 5 ] ] }, "note": "First published: 2025-10-05; Recorded arXiv version: v1; Recorded version updated: 2025-10-05T05:15:45Z.", "title": "\\textsc{GUI-Spotlight}: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2510.04607v2", "archive": "arXiv", "archive_location": "2510.04607", "author": [ { "literal": "Yuan Wang" }, { "literal": "Mingyu Li" }, { "literal": "Haibo Chen" } ], "citation-key": "arxiv_2510_04607", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1c22547bf82eb2fb87e8bf6a3846d25c17cac296763726ed9a25faf88bdca33c", "submitted_at": "2025-10-06T09:14:58Z", "updated_at": "2026-03-25T11:29:08Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.04607v2" }, "canonical_source_url": "https://arxiv.org/abs/2510.04607", "catalog_id": "arxiv:2510.04607", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-06", "identifiers": { "arxiv": "2510.04607" }, "record_updated_at": "2026-03-25" }, "genre": "preprint", "id": "arxiv:2510.04607", "issued": { "date-parts": [ [ 2025, 10, 6 ] ] }, "note": "First published: 2025-10-06; Recorded arXiv version: v2; Recorded version updated: 2026-03-25T11:29:08Z.", "title": "From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2510.17790v3", "archive": "arXiv", "archive_location": "2510.17790", "author": [ { "literal": "Yuhao Yang" }, { "literal": "Zhen Yang" }, { "literal": "Zi-Yi Dou" }, { "literal": "Anh Nguyen" }, { "literal": "Keen You" }, { "literal": "Omar Attia" }, { "literal": "Andrew Szot" }, { "literal": "Michael Feng" }, { "literal": "Ram Ramrakhya" }, { "literal": "Alexander Toshev" }, { "literal": "Chao Huang" }, { "literal": "Yinfei Yang" }, { "literal": "Zhe Gan" } ], "citation-key": "arxiv_2510_17790", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "33569f6ccca9c7e2675796191124424e76636828179c300d35da01ad9ccef1ce", "submitted_at": "2025-10-20T17:48:26Z", "updated_at": "2026-05-26T11:29:37Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2510.17790v3" }, "canonical_source_url": "https://arxiv.org/abs/2510.17790", "catalog_id": "arxiv:2510.17790", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-20", "identifiers": { "arxiv": "2510.17790" }, "record_updated_at": "2026-05-26" }, "genre": "preprint", "id": "arxiv:2510.17790", "issued": { "date-parts": [ [ 2025, 10, 20 ] ] }, "note": "First published: 2025-10-20; Recorded arXiv version: v3; Recorded version updated: 2026-05-26T11:29:37Z.", "title": "UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2510.24563v2", "archive": "arXiv", "archive_location": "2510.24563", "author": [ { "literal": "Hongrui Jia" }, { "literal": "Jitong Liao" }, { "literal": "Xi Zhang" }, { "literal": "Haiyang Xu" }, { "literal": "Tianbao Xie" }, { "literal": "Chaoya Jiang" }, { "literal": "Ming Yan" }, { "literal": "Si Liu" }, { "literal": "Wei Ye" }, { "literal": "Fei Huang" } ], "citation-key": "arxiv_2510_24563", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d115356f723746ce95c3e40fed933786a0747b3b560c8f73a6b7af05ca22d24f", "submitted_at": "2025-10-28T15:56:36Z", "updated_at": "2025-11-11T04:10:32Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.24563v2" }, "canonical_source_url": "https://arxiv.org/abs/2510.24563", "catalog_id": "arxiv:2510.24563", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-28", "identifiers": { "arxiv": "2510.24563" }, "record_updated_at": "2025-11-11" }, "genre": "preprint", "id": "arxiv:2510.24563", "issued": { "date-parts": [ [ 2025, 10, 28 ] ] }, "note": "First published: 2025-10-28; Recorded arXiv version: v2; Recorded version updated: 2025-11-11T04:10:32Z.", "title": "OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2511.19477v1", "archive": "arXiv", "archive_location": "2511.19477", "author": [ { "literal": "Aram Vardanyan" } ], "citation-key": "arxiv_2511_19477", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "17debfa3b59e5a2fcae950c2659e5851ae101cc58181e0cc4e0320befe9b4cb1", "submitted_at": "2025-11-22T12:18:35Z", "updated_at": "2025-11-22T12:18:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.19477v1" }, "canonical_source_url": "https://arxiv.org/abs/2511.19477", "catalog_id": "arxiv:2511.19477", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-22", "identifiers": { "arxiv": "2511.19477" }, "record_updated_at": "2025-11-22" }, "genre": "preprint", "id": "arxiv:2511.19477", "issued": { "date-parts": [ [ 2025, 11, 22 ] ] }, "note": "First published: 2025-11-22; Recorded arXiv version: v1; Recorded version updated: 2025-11-22T12:18:35Z.", "title": "Building Browser Agents: Architecture, Security, and Practical Solutions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.15431v2", "archive": "arXiv", "archive_location": "2512.15431", "author": [ { "literal": "Haolong Yan" }, { "literal": "Jia Wang" }, { "literal": "Xin Huang" }, { "literal": "Yeqing Shen" }, { "literal": "Ziyang Meng" }, { "literal": "Zhimin Fan" }, { "literal": "Kaijun Tan" }, { "literal": "Jin Gao" }, { "literal": "Lieyu Shi" }, { "literal": "Mi Yang" }, { "literal": "Shiliang Yang" }, { "literal": "Zhirui Wang" }, { "literal": "Brian Li" }, { "literal": "Kang An" }, { "literal": "Chenyang Li" }, { "literal": "Lei Lei" }, { "literal": "Mengmeng Duan" }, { "literal": "Danxun Liang" }, { "literal": "Guodong Liu" }, { "literal": "Hang Cheng" }, { "literal": "Hao Wu" }, { "literal": "Jie Dong" }, { "literal": "Junhao Huang" }, { "literal": "Mei Chen" }, { "literal": "Renjie Yu" }, { "literal": "Shunshan Li" }, { "literal": "Xu Zhou" }, { "literal": "Yiting Dai" }, { "literal": "Yineng Deng" }, { "literal": "Yingdan Liang" }, { "literal": "Zelin Chen" }, { "literal": "Wen Sun" }, { "literal": "Chengxu Yan" }, { "literal": "Chunqin Xu" }, { "literal": "Dong Li" }, { "literal": "Fengqiong Xiao" }, { "literal": "Guanghao Fan" }, { "literal": "Guopeng Li" }, { "literal": "Guozhen Peng" }, { "literal": "Hongbing Li" }, { "literal": "Hang Li" }, { "literal": "Hongming Chen" }, { "literal": "Jingjing Xie" }, { "literal": "Jianyong Li" }, { "literal": "Jingyang Zhang" }, { "literal": "Jiaju Ren" }, { "literal": "Jiayu Yuan" }, { "literal": "Jianpeng Yin" }, { "literal": "Kai Cao" }, { "literal": "Liang Zhao" }, { "literal": "Liguo Tan" }, { "literal": "Liying Shi" }, { "literal": "Mengqiang Ren" }, { "literal": "Min Xu" }, { "literal": "Manjiao Liu" }, { "literal": "Mao Luo" }, { "literal": "Mingxin Wan" }, { "literal": "Na Wang" }, { "literal": "Nan Wu" }, { "literal": "Ning Wang" }, { "literal": "Peiyao Ma" }, { "literal": "Qingzhou Zhang" }, { "literal": "Qiao Wang" }, { "literal": "Qinlin Zeng" }, { "literal": "Qiong Gao" }, { "literal": "Qiongyao Li" }, { "literal": "Shangwu Zhong" }, { "literal": "Shuli Gao" }, { "literal": "Shaofan Liu" }, { "literal": "Shisi Gao" }, { "literal": "Shuang Luo" }, { "literal": "Xingbin Liu" }, { "literal": "Xiaojia Liu" }, { "literal": "Xiaojie Hou" }, { "literal": "Xin Liu" }, { "literal": "Xuanti Feng" }, { "literal": "Xuedan Cai" }, { "literal": "Xuan Wen" }, { "literal": "Xianwei Zhu" }, { "literal": "Xin Liang" }, { "literal": "Xin Liu" }, { "literal": "Xin Zhou" }, { "literal": "Yifan Sui" }, { "literal": "Yingxiu Zhao" }, { "literal": "Yukang Shi" }, { "literal": "Yunfang Xu" }, { "literal": "Yuqing Zeng" }, { "literal": "Yixun Zhang" }, { "literal": "Zejia Weng" }, { "literal": "Zhonghao Yan" }, { "literal": "Zhiguo Huang" }, { "literal": "Zhuoyu Wang" }, { "literal": "Zihan Yan" }, { "literal": "Zheng Ge" }, { "literal": "Jing Li" }, { "literal": "Yibo Zhu" }, { "literal": "Binxing Jiao" }, { "literal": "Xiangyu Zhang" }, { "literal": "Daxin Jiang" } ], "citation-key": "arxiv_2512_15431", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2fc824bdeabca3451fd895447a0321c507da1ac7bc7cc24184c7768992549daf", "submitted_at": "2025-12-17T13:26:30Z", "updated_at": "2025-12-19T17:36:21Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2512.15431v2" }, "canonical_source_url": "https://arxiv.org/abs/2512.15431", "catalog_id": "arxiv:2512.15431", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-17", "identifiers": { "arxiv": "2512.15431" }, "record_updated_at": "2025-12-19" }, "genre": "preprint", "id": "arxiv:2512.15431", "issued": { "date-parts": [ [ 2025, 12, 17 ] ] }, "note": "First published: 2025-12-17; Recorded arXiv version: v2; Recorded version updated: 2025-12-19T17:36:21Z.", "title": "Step-GUI Technical Report", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2512.19432v3", "archive": "arXiv", "archive_location": "2512.19432", "author": [ { "literal": "Quyu Kong" }, { "literal": "Xu Zhang" }, { "literal": "Zhenyu Yang" }, { "literal": "Nolan Gao" }, { "literal": "Chen Liu" }, { "literal": "Panrong Tong" }, { "literal": "Chenglin Cai" }, { "literal": "Hanzhang Zhou" }, { "literal": "Jianan Zhang" }, { "literal": "Liangyu Chen" }, { "literal": "Zhidan Liu" }, { "literal": "Steven Hoi" }, { "literal": "Yue Wang" } ], "citation-key": "arxiv_2512_19432", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cf3258fd2286b0ee6babb69b9bfc459ecf40536eec498a3af3403d2971791f3d", "submitted_at": "2025-12-22T14:31:28Z", "updated_at": "2025-12-30T07:15:15Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2512.19432v3" }, "canonical_source_url": "https://arxiv.org/abs/2512.19432", "catalog_id": "arxiv:2512.19432", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-22", "identifiers": { "arxiv": "2512.19432" }, "record_updated_at": "2025-12-30" }, "genre": "preprint", "id": "arxiv:2512.19432", "issued": { "date-parts": [ [ 2025, 12, 22 ] ] }, "note": "First published: 2025-12-22; Recorded arXiv version: v3; Recorded version updated: 2025-12-30T07:15:15Z.", "title": "MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2512.22047v1", "archive": "arXiv", "archive_location": "2512.22047", "author": [ { "literal": "Hanzhang Zhou" }, { "literal": "Xu Zhang" }, { "literal": "Panrong Tong" }, { "literal": "Jianan Zhang" }, { "literal": "Liangyu Chen" }, { "literal": "Quyu Kong" }, { "literal": "Chenglin Cai" }, { "literal": "Chen Liu" }, { "literal": "Yue Wang" }, { "literal": "Jingren Zhou" }, { "literal": "Steven Hoi" } ], "citation-key": "arxiv_2512_22047", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a89eb3fd173680c127245933d252d4e245b7179d77bca4b463d50800c78f7238", "submitted_at": "2025-12-26T14:51:52Z", "updated_at": "2025-12-26T14:51:52Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.22047v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.22047", "catalog_id": "arxiv:2512.22047", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-26", "identifiers": { "arxiv": "2512.22047" }, "record_updated_at": "2025-12-26" }, "genre": "preprint", "id": "arxiv:2512.22047", "issued": { "date-parts": [ [ 2025, 12, 26 ] ] }, "note": "First published: 2025-12-26; Recorded arXiv version: v1; Recorded version updated: 2025-12-26T14:51:52Z.", "title": "MAI-UI Technical Report: Real-World Centric Foundation GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.23647v1", "archive": "arXiv", "archive_location": "2512.23647", "author": [ { "literal": "Baixuan Li" }, { "literal": "Jialong Wu" }, { "literal": "Wenbiao Yin" }, { "literal": "Kuan Li" }, { "literal": "Zhongwang Zhang" }, { "literal": "Huifeng Yin" }, { "literal": "Zhengwei Tao" }, { "literal": "Liwen Zhang" }, { "literal": "Pengjun Xie" }, { "literal": "Jingren Zhou" }, { "literal": "Yong Jiang" } ], "citation-key": "arxiv_2512_23647", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fde71dd935acb953bc5d01bcd48f0d6c3351db6a66126761baf134c114e7893c", "submitted_at": "2025-12-29T17:59:14Z", "updated_at": "2025-12-29T17:59:14Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.23647v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.23647", "catalog_id": "arxiv:2512.23647", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-29", "identifiers": { "arxiv": "2512.23647" }, "record_updated_at": "2025-12-29" }, "genre": "preprint", "id": "arxiv:2512.23647", "issued": { "date-parts": [ [ 2025, 12, 29 ] ] }, "note": "First published: 2025-12-29; Recorded arXiv version: v1; Recorded version updated: 2025-12-29T17:59:14Z.", "title": "Nested Browser-Use Learning for Agentic Information Seeking", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.07779v1", "archive": "arXiv", "archive_location": "2601.07779", "author": [ { "literal": "Bowen Yang" }, { "literal": "Kaiming Jin" }, { "literal": "Zhenyu Wu" }, { "literal": "Zhaoyang Liu" }, { "literal": "Qiushi Sun" }, { "literal": "Zehao Li" }, { "literal": "JingJing Xie" }, { "literal": "Zhoumianze Liu" }, { "literal": "Fangzhi Xu" }, { "literal": "Kanzhi Cheng" }, { "literal": "Qingyun Li" }, { "literal": "Yian Wang" }, { "literal": "Yu Qiao" }, { "literal": "Zun Wang" }, { "literal": "Zichen Ding" } ], "citation-key": "arxiv_2601_07779", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cfdaabaf3c6df80eb718e51dc666c54fb2ecf38ec520f6a71ccf5e5ce54248c8", "submitted_at": "2026-01-12T17:55:51Z", "updated_at": "2026-01-12T17:55:51Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.07779v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.07779", "catalog_id": "arxiv:2601.07779", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-12", "identifiers": { "arxiv": "2601.07779" }, "record_updated_at": "2026-01-12" }, "genre": "preprint", "id": "arxiv:2601.07779", "issued": { "date-parts": [ [ 2026, 1, 12 ] ] }, "note": "First published: 2026-01-12; Recorded arXiv version: v1; Recorded version updated: 2026-01-12T17:55:51Z.", "title": "OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.09770v1", "archive": "arXiv", "archive_location": "2601.09770", "author": [ { "literal": "Chen Chen" }, { "literal": "Jiawei Shao" }, { "literal": "Dakuan Lu" }, { "literal": "Haoyi Hu" }, { "literal": "Xiangcheng Liu" }, { "literal": "Hantao Yao" }, { "literal": "Wu Liu" } ], "citation-key": "arxiv_2601_09770", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0d5ed7e72534fc55d028d4f25cb98b2373c88b622cf76396933d7a49d8ecf2e8", "submitted_at": "2026-01-14T14:27:28Z", "updated_at": "2026-01-14T14:27:28Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.09770v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.09770", "catalog_id": "arxiv:2601.09770", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-14", "identifiers": { "arxiv": "2601.09770" }, "record_updated_at": "2026-01-14" }, "genre": "preprint", "id": "arxiv:2601.09770", "issued": { "date-parts": [ [ 2026, 1, 14 ] ] }, "note": "First published: 2026-01-14; Recorded arXiv version: v1; Recorded version updated: 2026-01-14T14:27:28Z.", "title": "GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.21123v2", "archive": "arXiv", "archive_location": "2601.21123", "author": [ { "literal": "Tianyi Chen" }, { "literal": "Yinheng Li" }, { "literal": "Michael Solodko" }, { "literal": "Sen Wang" }, { "literal": "Nan Jiang" }, { "literal": "Tingyuan Cui" }, { "literal": "Junheng Hao" }, { "literal": "Jongwoo Ko" }, { "literal": "Sara Abdali" }, { "literal": "Leon Xu" }, { "literal": "Suzhen Zheng" }, { "literal": "Hao Fan" }, { "literal": "Pashmina Cameron" }, { "literal": "Justin Wagle" }, { "literal": "Kazuhito Koishida" } ], "citation-key": "arxiv_2601_21123", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5a3efa3cd0add437e327ea49896a3ee794daa178664dfb4096aba66fed27554b", "submitted_at": "2026-01-28T23:38:25Z", "updated_at": "2026-02-02T23:11:55Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.21123v2" }, "canonical_source_url": "https://arxiv.org/abs/2601.21123", "catalog_id": "arxiv:2601.21123", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-28", "identifiers": { "arxiv": "2601.21123" }, "record_updated_at": "2026-02-02" }, "genre": "preprint", "id": "arxiv:2601.21123", "issued": { "date-parts": [ [ 2026, 1, 28 ] ] }, "note": "First published: 2026-01-28; Recorded arXiv version: v2; Recorded version updated: 2026-02-02T23:11:55Z.", "title": "CUA-Skill: Develop Skills for Computer Using Agent", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.00575v2", "archive": "arXiv", "archive_location": "2602.00575", "author": [ { "literal": "Chaoqun Cui" }, { "literal": "Jing Huang" }, { "literal": "Shijing Wang" }, { "literal": "Liming Zheng" }, { "literal": "Qingchao Kong" }, { "literal": "Zhixiong Zeng" } ], "citation-key": "arxiv_2602_00575", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "86225f2e52e1394e2a0a56b1e82327d756bff95739e01ce7cc5898af49944aba", "submitted_at": "2026-01-31T07:36:54Z", "updated_at": "2026-07-25T06:54:35Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.00575v2" }, "canonical_source_url": "https://arxiv.org/abs/2602.00575", "catalog_id": "arxiv:2602.00575", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-31", "identifiers": { "arxiv": "2602.00575" }, "record_updated_at": "2026-07-25" }, "genre": "preprint", "id": "arxiv:2602.00575", "issued": { "date-parts": [ [ 2026, 1, 31 ] ] }, "note": "First published: 2026-01-31; Recorded arXiv version: v2; Recorded version updated: 2026-07-25T06:54:35Z.", "title": "Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.02548v1", "archive": "arXiv", "archive_location": "2602.02548", "author": [ { "literal": "Xiaoce Wang" }, { "literal": "Guibin Zhang" }, { "literal": "Junzhe Li" }, { "literal": "Jinzhe Tu" }, { "literal": "Chun Li" }, { "literal": "Ming Li" } ], "citation-key": "arxiv_2602_02548", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "49b0dbff31dcf8c966bebd367ae05984e46a7fd13b2cfb1ad5ef061332b43f00", "submitted_at": "2026-01-30T08:38:05Z", "updated_at": "2026-01-30T08:38:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.02548v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.02548", "catalog_id": "arxiv:2602.02548", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-30", "identifiers": { "arxiv": "2602.02548" }, "record_updated_at": "2026-01-30" }, "genre": "preprint", "id": "arxiv:2602.02548", "issued": { "date-parts": [ [ 2026, 1, 30 ] ] }, "note": "First published: 2026-01-30; Recorded arXiv version: v1; Recorded version updated: 2026-01-30T08:38:05Z.", "title": "ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.12430v4", "archive": "arXiv", "archive_location": "2602.12430", "author": [ { "literal": "Renjun Xu" }, { "literal": "Yang Yan" } ], "citation-key": "arxiv_2602_12430", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f0edc70265a8d46a7c22a9c6384de8aa19f79dbb6987f8c23f4a260647a6a3f0", "submitted_at": "2026-02-12T21:33:25Z", "updated_at": "2026-06-02T16:14:54Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2602.12430v4" }, "canonical_source_url": "https://arxiv.org/abs/2602.12430", "catalog_id": "arxiv:2602.12430", "catalog_kind": "survey", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-02-12", "identifiers": { "arxiv": "2602.12430" }, "record_updated_at": "2026-06-02" }, "genre": "preprint", "id": "arxiv:2602.12430", "issued": { "date-parts": [ [ 2026, 2, 12 ] ] }, "note": "First published: 2026-02-12; Recorded arXiv version: v4; Recorded version updated: 2026-06-02T16:14:54Z.", "title": "Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward", "type": "article", "version": "4" }, { "URL": "https://arxiv.org/abs/2602.14865v1", "archive": "arXiv", "archive_location": "2602.14865", "author": [ { "literal": "Chenyang Ma" }, { "literal": "Clyde Fare" }, { "literal": "Matthew Wilson" }, { "literal": "Dave Braines" } ], "citation-key": "arxiv_2602_14865", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "353036db8a5609d64792ea49523ca424cf265d981ff34d1e7bc8fed35ffb21c0", "submitted_at": "2026-02-16T15:59:56Z", "updated_at": "2026-02-16T15:59:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.14865v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.14865", "catalog_id": "arxiv:2602.14865", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-16", "identifiers": { "arxiv": "2602.14865" }, "record_updated_at": "2026-02-16" }, "genre": "preprint", "id": "arxiv:2602.14865", "issued": { "date-parts": [ [ 2026, 2, 16 ] ] }, "note": "First published: 2026-02-16; Recorded arXiv version: v1; Recorded version updated: 2026-02-16T15:59:56Z.", "title": "EmbeWebAgent: Embedding Web Agents into Any Customized UI", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.16855v1", "archive": "arXiv", "archive_location": "2602.16855", "author": [ { "literal": "Haiyang Xu" }, { "literal": "Xi Zhang" }, { "literal": "Haowei Liu" }, { "literal": "Junyang Wang" }, { "literal": "Zhaozai Zhu" }, { "literal": "Shengjie Zhou" }, { "literal": "Xuhao Hu" }, { "literal": "Feiyu Gao" }, { "literal": "Junjie Cao" }, { "literal": "Zihua Wang" }, { "literal": "Zhiyuan Chen" }, { "literal": "Jitong Liao" }, { "literal": "Qi Zheng" }, { "literal": "Jiahui Zeng" }, { "literal": "Ze Xu" }, { "literal": "Shuai Bai" }, { "literal": "Junyang Lin" }, { "literal": "Jingren Zhou" }, { "literal": "Ming Yan" } ], "citation-key": "arxiv_2602_16855", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "eeaddd8a32bdd4b53356ca43e849ea3697ac3d40a05b32e6c930dc445c243898", "submitted_at": "2026-02-15T01:52:19Z", "updated_at": "2026-02-15T01:52:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.16855v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.16855", "catalog_id": "arxiv:2602.16855", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-15", "identifiers": { "arxiv": "2602.16855" }, "record_updated_at": "2026-02-15" }, "genre": "preprint", "id": "arxiv:2602.16855", "issued": { "date-parts": [ [ 2026, 2, 15 ] ] }, "note": "First published: 2026-02-15; Recorded arXiv version: v1; Recorded version updated: 2026-02-15T01:52:19Z.", "title": "Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2603.10664v1", "archive": "arXiv", "archive_location": "2603.10664", "author": [ { "literal": "Alexandre De Masi" } ], "citation-key": "arxiv_2603_10664", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5944045ee4562641ee02612969d1c2d038e019fa02cc8d48c671c1d5397557ad", "submitted_at": "2026-03-11T11:24:31Z", "updated_at": "2026-03-11T11:24:31Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2603.10664v1" }, "canonical_source_url": "https://arxiv.org/abs/2603.10664", "catalog_id": "arxiv:2603.10664", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-03-11", "identifiers": { "arxiv": "2603.10664" }, "record_updated_at": "2026-03-11" }, "genre": "preprint", "id": "arxiv:2603.10664", "issued": { "date-parts": [ [ 2026, 3, 11 ] ] }, "note": "First published: 2026-03-11; Recorded arXiv version: v1; Recorded version updated: 2026-03-11T11:24:31Z.", "title": "Terminal Is All You Need: Design Properties for Human-AI Agent Collaboration", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.09815v1", "archive": "arXiv", "archive_location": "2604.09815", "author": [ { "literal": "Tiantian He" }, { "literal": "Yihang Chen" }, { "literal": "Keyue Jiang" }, { "literal": "Ka Yiu Lee" }, { "literal": "Kaiwen Zhou" }, { "literal": "Kun Shao" }, { "literal": "Shuai Wang" } ], "citation-key": "arxiv_2604_09815", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "dd2bc0ee1955dbc8e98a9306a3d6260251cbab89d36ac117e4dc49b6fa99766e", "submitted_at": "2026-04-10T18:46:05Z", "updated_at": "2026-04-10T18:46:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.09815v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.09815", "catalog_id": "arxiv:2604.09815", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-10", "identifiers": { "arxiv": "2604.09815" }, "record_updated_at": "2026-04-10" }, "genre": "preprint", "id": "arxiv:2604.09815", "issued": { "date-parts": [ [ 2026, 4, 10 ] ] }, "note": "First published: 2026-04-10; Recorded arXiv version: v1; Recorded version updated: 2026-04-10T18:46:05Z.", "title": "EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.11784v1", "archive": "arXiv", "archive_location": "2604.11784", "author": [ { "literal": "Fei Tang" }, { "literal": "Zhiqiong Lu" }, { "literal": "Boxuan Zhang" }, { "literal": "Weiming Lu" }, { "literal": "Jun Xiao" }, { "literal": "Yueting Zhuang" }, { "literal": "Yongliang Shen" } ], "citation-key": "arxiv_2604_11784", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "df56b38203bc5ec8d7e871eb2ad9fca9891a049df62b7d72796fe400eb8bce5e", "submitted_at": "2026-04-13T17:52:04Z", "updated_at": "2026-04-13T17:52:04Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.11784v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.11784", "catalog_id": "arxiv:2604.11784", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-13", "identifiers": { "arxiv": "2604.11784" }, "record_updated_at": "2026-04-13" }, "genre": "preprint", "id": "arxiv:2604.11784", "issued": { "date-parts": [ [ 2026, 4, 13 ] ] }, "note": "First published: 2026-04-13; Recorded arXiv version: v1; Recorded version updated: 2026-04-13T17:52:04Z.", "title": "ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.13822v1", "archive": "arXiv", "archive_location": "2604.13822", "author": [ { "literal": "Zhengxi Lu" }, { "literal": "Fei Tang" }, { "literal": "Guangyi Liu" }, { "literal": "Kaitao Song" }, { "literal": "Xu Tan" }, { "literal": "Jin Ma" }, { "literal": "Wenqi Zhang" }, { "literal": "Weiming Lu" }, { "literal": "Jun Xiao" }, { "literal": "Yueting Zhuang" }, { "literal": "Yongliang Shen" } ], "citation-key": "arxiv_2604_13822", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d6e81b448c9c22e2fd25dce519db3fdc0585b0265b94d448751d7a37ed910dfa", "submitted_at": "2026-04-15T12:55:46Z", "updated_at": "2026-04-15T12:55:46Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.13822v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.13822", "catalog_id": "arxiv:2604.13822", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-15", "identifiers": { "arxiv": "2604.13822" }, "record_updated_at": "2026-04-15" }, "genre": "preprint", "id": "arxiv:2604.13822", "issued": { "date-parts": [ [ 2026, 4, 15 ] ] }, "note": "First published: 2026-04-15; Recorded arXiv version: v1; Recorded version updated: 2026-04-15T12:55:46Z.", "title": "UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.16520v1", "archive": "arXiv", "archive_location": "2604.16520", "author": [ { "literal": "Haomin Zhuang" }, { "literal": "Hanwen Xing" }, { "literal": "Xiangliang Zhang" } ], "citation-key": "arxiv_2604_16520", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7b1788e6fbb4c14a6d993ce329bf7bf05e3a1e6ffbfc7c14a9fa9d36fbf7ef16", "submitted_at": "2026-04-15T18:22:50Z", "updated_at": "2026-04-15T18:22:50Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.16520v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.16520", "catalog_id": "arxiv:2604.16520", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-04-15", "identifiers": { "arxiv": "2604.16520" }, "record_updated_at": "2026-04-15" }, "genre": "preprint", "id": "arxiv:2604.16520", "issued": { "date-parts": [ [ 2026, 4, 15 ] ] }, "note": "First published: 2026-04-15; Recorded arXiv version: v1; Recorded version updated: 2026-04-15T18:22:50Z.", "title": "AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.21375v3", "archive": "arXiv", "archive_location": "2604.21375", "author": [ { "literal": "Qijun Han" }, { "literal": "Haoqin Tu" }, { "literal": "Zijun Wang" }, { "literal": "Haoyue Dai" }, { "literal": "Yiyang Zhou" }, { "literal": "Nancy Lau" }, { "literal": "Alvaro A. Cardenas" }, { "literal": "Yuhui Xu" }, { "literal": "Ran Xu" }, { "literal": "Caiming Xiong" }, { "literal": "Zeyu Zheng" }, { "literal": "Huaxiu Yao" }, { "literal": "Yuyin Zhou" }, { "literal": "Cihang Xie" } ], "citation-key": "arxiv_2604_21375", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7e675476121ab3ef51a8627ccfcc86d76eddde73987ea882398f72e3cb31c5d9", "submitted_at": "2026-04-23T07:42:37Z", "updated_at": "2026-09-24T23:58:02Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2604.21375v3" }, "canonical_source_url": "https://arxiv.org/abs/2604.21375", "catalog_id": "arxiv:2604.21375", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-23", "identifiers": { "arxiv": "2604.21375" }, "record_updated_at": "2026-09-24" }, "genre": "preprint", "id": "arxiv:2604.21375", "issued": { "date-parts": [ [ 2026, 4, 23 ] ] }, "note": "First published: 2026-04-23; Recorded arXiv version: v3; Recorded version updated: 2026-09-24T23:58:02Z.", "title": "VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2604.27996v3", "archive": "arXiv", "archive_location": "2604.27996", "author": [ { "literal": "Jackson Vonderhorst" }, { "literal": "Kuangshi Ai" }, { "literal": "Haichao Miao" }, { "literal": "Shusen Liu" }, { "literal": "Chaoli Wang" } ], "citation-key": "arxiv_2604_27996", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8e7b07a811df7e74a28f91a5b6c59c69b7ba066bd6c64452a299e678a3187733", "submitted_at": "2026-04-30T15:22:28Z", "updated_at": "2026-06-26T20:31:32Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2604.27996v3" }, "canonical_source_url": "https://arxiv.org/abs/2604.27996", "catalog_id": "arxiv:2604.27996", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-30", "identifiers": { "arxiv": "2604.27996" }, "record_updated_at": "2026-06-26" }, "genre": "preprint", "id": "arxiv:2604.27996", "issued": { "date-parts": [ [ 2026, 4, 30 ] ] }, "note": "First published: 2026-04-30; Recorded arXiv version: v3; Recorded version updated: 2026-06-26T20:31:32Z.", "title": "Exploring LLM Agent Designs and Interaction Modalities for Scientific Visualization", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2605.10966v1", "archive": "arXiv", "archive_location": "2605.10966", "author": [ { "literal": "Chiyeong Heo" }, { "literal": "Jaechang Kim" }, { "literal": "Junhyuk Kwon" }, { "literal": "Hoyoung Kim" }, { "literal": "Dongmin Park" }, { "literal": "Jonghyun Lee" }, { "literal": "Jungseul Ok" } ], "citation-key": "arxiv_2605_10966", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0bd75e6bf9d5a8185a2204cdd99d42f9d96c102f7297abcadb9f8425e9246349", "submitted_at": "2026-05-08T10:57:19Z", "updated_at": "2026-05-08T10:57:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.10966v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.10966", "catalog_id": "arxiv:2605.10966", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-05-08", "identifiers": { "arxiv": "2605.10966" }, "record_updated_at": "2026-05-08" }, "genre": "preprint", "id": "arxiv:2605.10966", "issued": { "date-parts": [ [ 2026, 5, 8 ] ] }, "note": "First published: 2026-05-08; Recorded arXiv version: v1; Recorded version updated: 2026-05-08T10:57:19Z.", "title": "MMTB: Evaluating Terminal Agents on Multimedia-File Tasks", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.12481v2", "archive": "arXiv", "archive_location": "2605.12481", "author": [ { "literal": "Xuhao Hu" }, { "literal": "Xi Zhang" }, { "literal": "Haiyang Xu" }, { "literal": "Kyle Qiao" }, { "literal": "Jingyi Yang" }, { "literal": "Xuanjing Huang" }, { "literal": "Jing Shao" }, { "literal": "Ming Yan" }, { "literal": "Jieping Ye" } ], "citation-key": "arxiv_2605_12481", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "09128e90b925ac0cd2cf6e967853180bbef1e97a0960c22065f1b0b50c30d58b", "submitted_at": "2026-05-12T17:57:04Z", "updated_at": "2026-09-19T14:53:46Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.12481v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.12481", "catalog_id": "arxiv:2605.12481", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-12", "identifiers": { "arxiv": "2605.12481" }, "record_updated_at": "2026-09-19" }, "genre": "preprint", "id": "arxiv:2605.12481", "issued": { "date-parts": [ [ 2026, 5, 12 ] ] }, "note": "First published: 2026-05-12; Recorded arXiv version: v2; Recorded version updated: 2026-09-19T14:53:46Z.", "title": "ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2605.14290v1", "archive": "arXiv", "archive_location": "2605.14290", "author": [ { "literal": "Julien Piet" }, { "literal": "Annabella Chow" }, { "literal": "Yiwei Hou" }, { "literal": "Muxi Lyu" }, { "literal": "Sylvie Venuto" }, { "literal": "Jinhao Zhu" }, { "literal": "Raluca Ada Popa" }, { "literal": "David Wagner" } ], "citation-key": "arxiv_2605_14290", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "572be49190554bbfb6accac4c87ef91608f88e90d06250f229db2922e19fcd56", "submitted_at": "2026-05-14T02:48:57Z", "updated_at": "2026-05-14T02:48:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2605.14290v1" }, "canonical_source_url": "https://arxiv.org/abs/2605.14290", "catalog_id": "arxiv:2605.14290", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-05-14", "identifiers": { "arxiv": "2605.14290" }, "record_updated_at": "2026-05-14" }, "genre": "preprint", "id": "arxiv:2605.14290", "issued": { "date-parts": [ [ 2026, 5, 14 ] ] }, "note": "First published: 2026-05-14; Recorded arXiv version: v1; Recorded version updated: 2026-05-14T02:48:57Z.", "title": "Web Agents Should Adopt the Plan-Then-Execute Paradigm", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.21470v2", "archive": "arXiv", "archive_location": "2605.21470", "author": [ { "literal": "Caleb Winston" }, { "literal": "Ron Yifeng Wang" }, { "literal": "Azalia Mirhoseini" }, { "literal": "Christos Kozyrakis" } ], "citation-key": "arxiv_2605_21470", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9b73bf7776e280a9040b1d7d1e29957913723253014c1dfe84f64916b2a08e5e", "submitted_at": "2026-05-20T17:54:27Z", "updated_at": "2026-05-29T17:54:05Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.21470v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.21470", "catalog_id": "arxiv:2605.21470", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-20", "identifiers": { "arxiv": "2605.21470" }, "record_updated_at": "2026-05-29" }, "genre": "preprint", "id": "arxiv:2605.21470", "issued": { "date-parts": [ [ 2026, 5, 20 ] ] }, "note": "First published: 2026-05-20; Recorded arXiv version: v2; Recorded version updated: 2026-05-29T17:54:05Z.", "title": "Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2606.03854v1", "archive": "arXiv", "archive_location": "2606.03854", "author": [ { "literal": "Yuhao Yang" }, { "literal": "Tianyu Fan" }, { "literal": "Chao Huang" } ], "citation-key": "arxiv_2606_03854", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f7490150e82a5abfc510c60401cccf21c821d829e66cc5f2b40fd2fbbf4b0df4", "submitted_at": "2026-06-02T16:30:33Z", "updated_at": "2026-06-02T16:30:33Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.03854v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.03854", "catalog_id": "arxiv:2606.03854", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-06-02", "identifiers": { "arxiv": "2606.03854" }, "record_updated_at": "2026-06-02" }, "genre": "preprint", "id": "arxiv:2606.03854", "issued": { "date-parts": [ [ 2026, 6, 2 ] ] }, "note": "First published: 2026-06-02; Recorded arXiv version: v1; Recorded version updated: 2026-06-02T16:30:33Z.", "title": "CLI-Anything: Towards Agent-Native Computer Use", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.09426v3", "archive": "arXiv", "archive_location": "2606.09426", "author": [ { "literal": "Wanli Li" }, { "literal": "Bowen Zhou" }, { "literal": "Yunyao Yu" }, { "literal": "Zhou Xu" }, { "literal": "Yifan Yang" }, { "literal": "Dongsheng Li" }, { "literal": "Caihua Shan" } ], "citation-key": "arxiv_2606_09426", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "73b751efd63d98fc81166a1a80cb0c162d68bf1ec4ecca0a1a1a7717ad62e680", "submitted_at": "2026-06-08T12:39:23Z", "updated_at": "2026-07-06T14:25:02Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2606.09426v3" }, "canonical_source_url": "https://arxiv.org/abs/2606.09426", "catalog_id": "arxiv:2606.09426", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-08", "identifiers": { "arxiv": "2606.09426" }, "record_updated_at": "2026-07-06" }, "genre": "preprint", "id": "arxiv:2606.09426", "issued": { "date-parts": [ [ 2026, 6, 8 ] ] }, "note": "First published: 2026-06-08; Recorded arXiv version: v3; Recorded version updated: 2026-07-06T14:25:02Z.", "title": "WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2606.13239v2", "archive": "arXiv", "archive_location": "2606.13239", "author": [ { "literal": "Jiaxin Ai" }, { "literal": "Tao Hu" }, { "literal": "Xuemeng Yang" }, { "literal": "Shu Zou" }, { "literal": "Hairong Zhang" }, { "literal": "Daocheng Fu" }, { "literal": "Yu Yang" }, { "literal": "Hongbin Zhou" }, { "literal": "Nianchen Deng" }, { "literal": "Pinlong Cai" }, { "literal": "Zhongyuan Wang" }, { "literal": "Botian Shi" }, { "literal": "Kaipeng Zhang" }, { "literal": "Licheng Wen" } ], "citation-key": "arxiv_2606_13239", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "edf7e63803efba89551aa297bff1da9b0babf8ec898a2971fa6c8a20cc58dea8", "submitted_at": "2026-06-11T11:53:32Z", "updated_at": "2026-06-30T03:31:20Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.13239v2" }, "canonical_source_url": "https://arxiv.org/abs/2606.13239", "catalog_id": "arxiv:2606.13239", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-06-11", "identifiers": { "arxiv": "2606.13239" }, "record_updated_at": "2026-06-30" }, "genre": "preprint", "id": "arxiv:2606.13239", "issued": { "date-parts": [ [ 2026, 6, 11 ] ] }, "note": "First published: 2026-06-11; Recorded arXiv version: v2; Recorded version updated: 2026-06-30T03:31:20Z.", "title": "ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2606.14832v1", "archive": "arXiv", "archive_location": "2606.14832", "author": [ { "literal": "Chenxin Li" }, { "literal": "Zhengyao Fang" }, { "literal": "Zhengyang Tang" }, { "literal": "Pengyuan Lyu" }, { "literal": "Xingran Zhou" }, { "literal": "Xin Lai" }, { "literal": "Fei Tang" }, { "literal": "Liang Wu" }, { "literal": "Yiduo Guo" }, { "literal": "Weinong Wang" }, { "literal": "Junyi Li" }, { "literal": "Yi Zhang" }, { "literal": "Yang Ding" }, { "literal": "Huawen Shen" }, { "literal": "Sunqi Fan" }, { "literal": "Shangpin Peng" }, { "literal": "Zheng Ruan" }, { "literal": "Anran Zhang" }, { "literal": "Benyou Wang" }, { "literal": "Chengquan Zhang" }, { "literal": "Han Hu" } ], "citation-key": "arxiv_2606_14832", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "280ec12bcb246f1f07cf3627011945e8a9ff4afed93b1fb2937f2d6b1bc1323b", "submitted_at": "2026-06-12T15:01:32Z", "updated_at": "2026-06-12T15:01:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.14832v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.14832", "catalog_id": "arxiv:2606.14832", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-12", "identifiers": { "arxiv": "2606.14832" }, "record_updated_at": "2026-06-12" }, "genre": "preprint", "id": "arxiv:2606.14832", "issued": { "date-parts": [ [ 2026, 6, 12 ] ] }, "note": "First published: 2026-06-12; Recorded arXiv version: v1; Recorded version updated: 2026-06-12T15:01:32Z.", "title": "PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.18448v1", "archive": "arXiv", "archive_location": "2606.18448", "author": [ { "literal": "Ziyan Jiang" }, { "literal": "Li An" }, { "literal": "Yujian Liu" }, { "literal": "Jiabao Ji" }, { "literal": "Qiucheng Wu" }, { "literal": "Jacob Andreas" }, { "literal": "Yang Zhang" }, { "literal": "Shiyu Chang" } ], "citation-key": "arxiv_2606_18448", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2605cedb4359aa0cf1e694455903871ed334dd37b7b8e15edf31bac9d5e51b13", "submitted_at": "2026-06-16T19:57:07Z", "updated_at": "2026-06-16T19:57:07Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.18448v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.18448", "catalog_id": "arxiv:2606.18448", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-16", "identifiers": { "arxiv": "2606.18448" }, "record_updated_at": "2026-06-16" }, "genre": "preprint", "id": "arxiv:2606.18448", "issued": { "date-parts": [ [ 2026, 6, 16 ] ] }, "note": "First published: 2026-06-16; Recorded arXiv version: v1; Recorded version updated: 2026-06-16T19:57:07Z.", "title": "VISUALSKILL: Multimodal Skills for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.19388v1", "archive": "arXiv", "archive_location": "2606.19388", "author": [ { "literal": "Li Gu" }, { "literal": "Zihuan Jiang" }, { "literal": "Linqiang Guo" }, { "literal": "Zhixiang Chi" }, { "literal": "Ziqiang Wang" }, { "literal": "Huan Liu" }, { "literal": "Yuanhao Yu" }, { "literal": "Tse-Hsun Chen" }, { "literal": "Yang Wang" } ], "citation-key": "arxiv_2606_19388", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9bf8b07e08b275d90fcbfc63d867f54f5579509132cc9cf694d01447b7f91b78", "submitted_at": "2026-06-16T02:36:22Z", "updated_at": "2026-06-16T02:36:22Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.19388v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.19388", "catalog_id": "arxiv:2606.19388", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-06-16", "identifiers": { "arxiv": "2606.19388" }, "record_updated_at": "2026-06-16" }, "genre": "preprint", "id": "arxiv:2606.19388", "issued": { "date-parts": [ [ 2026, 6, 16 ] ] }, "note": "First published: 2026-06-16; Recorded arXiv version: v1; Recorded version updated: 2026-06-16T02:36:22Z.", "title": "Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.22557v1", "archive": "arXiv", "archive_location": "2606.22557", "author": [ { "literal": "Yikun Fu" }, { "literal": "Bowen Fu" }, { "literal": "Zhenyu Wu" }, { "literal": "Shuang Cheng" }, { "literal": "Xiaowei Sun" }, { "literal": "Bowen Yang" }, { "literal": "Zehao Li" }, { "literal": "Yibo Zhao" }, { "literal": "Zichen Ding" }, { "literal": "Zhoumianze Liu" }, { "literal": "Shijie Wang" }, { "literal": "Biqing Qi" }, { "literal": "Bowen Zhou" } ], "citation-key": "arxiv_2606_22557", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6dc52f58bb2237d12041fa8b994b20bd1e41290aaab0c70d2c5dd79fcaca37b6", "submitted_at": "2026-06-21T15:32:57Z", "updated_at": "2026-06-21T15:32:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.22557v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.22557", "catalog_id": "arxiv:2606.22557", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-21", "identifiers": { "arxiv": "2606.22557" }, "record_updated_at": "2026-06-21" }, "genre": "preprint", "id": "arxiv:2606.22557", "issued": { "date-parts": [ [ 2026, 6, 21 ] ] }, "note": "First published: 2026-06-21; Recorded arXiv version: v1; Recorded version updated: 2026-06-21T15:32:57Z.", "title": "MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.24551v1", "archive": "arXiv", "archive_location": "2606.24551", "author": [ { "literal": "Xiao Zhou" }, { "literal": "Siyue Zhang" }, { "literal": "Yilun Zhao" }, { "literal": "Jinbiao Wei" }, { "literal": "Tingyu Song" }, { "literal": "Arman Cohan" }, { "literal": "Chen Zhao" } ], "citation-key": "arxiv_2606_24551", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "77f777f05b1c169ee4ad7ae7d77e9d1fc80a0696e9a1f6eefb5028a5c3e6fe5d", "submitted_at": "2026-06-22T17:05:07Z", "updated_at": "2026-06-22T17:05:07Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.24551v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.24551", "catalog_id": "arxiv:2606.24551", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-22", "identifiers": { "arxiv": "2606.24551" }, "record_updated_at": "2026-06-22" }, "genre": "preprint", "id": "arxiv:2606.24551", "issued": { "date-parts": [ [ 2026, 6, 22 ] ] }, "note": "First published: 2026-06-22; Recorded arXiv version: v1; Recorded version updated: 2026-06-22T17:05:07Z.", "title": "GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.30697v1", "archive": "arXiv", "archive_location": "2606.30697", "author": [ { "literal": "Yogeswar Reddy Thota" } ], "citation-key": "arxiv_2606_30697", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f3f2ae1438986c11146fec508dd61fd3e848ddcbf830f86a7dfa759280d730a", "submitted_at": "2026-06-29T03:19:40Z", "updated_at": "2026-06-29T03:19:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.30697v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.30697", "catalog_id": "arxiv:2606.30697", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-29", "identifiers": { "arxiv": "2606.30697" }, "record_updated_at": "2026-06-29" }, "genre": "preprint", "id": "arxiv:2606.30697", "issued": { "date-parts": [ [ 2026, 6, 29 ] ] }, "note": "First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T03:19:40Z.", "title": "LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.14443v1", "archive": "arXiv", "archive_location": "2607.14443", "author": [ { "literal": "Yong Liu" }, { "literal": "Zhenyi Zhong" }, { "literal": "Zhanpeng Shi" } ], "citation-key": "arxiv_2607_14443", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a779b2c1ff9ba3b531d399204b0986e3affcea81c67fdd7951e3b7da343b0e17", "submitted_at": "2026-07-16T00:35:25Z", "updated_at": "2026-07-16T00:35:25Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.14443v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.14443", "catalog_id": "arxiv:2607.14443", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-16", "identifiers": { "arxiv": "2607.14443" }, "record_updated_at": "2026-07-16" }, "genre": "preprint", "id": "arxiv:2607.14443", "issued": { "date-parts": [ [ 2026, 7, 16 ] ] }, "note": "First published: 2026-07-16; Recorded arXiv version: v1; Recorded version updated: 2026-07-16T00:35:25Z.", "title": "Tactile: Giving Computer-Using Agents Hands and Feet", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.21557v3", "archive": "arXiv", "archive_location": "2607.21557", "author": [ { "literal": "Xiao Yu" }, { "literal": "Baolin Peng" }, { "literal": "Ruize Xu" }, { "literal": "Hao Zou" }, { "literal": "Qianhui Wu" }, { "literal": "Hao Cheng" }, { "literal": "Wenlin Yao" }, { "literal": "Nikhil Singh" }, { "literal": "Zhou Yu" }, { "literal": "Jianfeng Gao" } ], "citation-key": "arxiv_2607_21557", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "965fe5aabfb44b4c82290fc347a463eb58fb2be7a3761496efd38167d0f7d5b6", "submitted_at": "2026-07-23T17:38:30Z", "updated_at": "2026-08-07T17:40:50Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2607.21557v3" }, "canonical_source_url": "https://arxiv.org/abs/2607.21557", "catalog_id": "arxiv:2607.21557", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-23", "identifiers": { "arxiv": "2607.21557" }, "record_updated_at": "2026-08-07" }, "genre": "preprint", "id": "arxiv:2607.21557", "issued": { "date-parts": [ [ 2026, 7, 23 ] ] }, "note": "First published: 2026-07-23; Recorded arXiv version: v3; Recorded version updated: 2026-08-07T17:40:50Z.", "title": "OpenForgeRL: Train Harness-native Agents in Any Environment", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2607.22798v1", "archive": "arXiv", "archive_location": "2607.22798", "author": [ { "literal": "Yan Yang" }, { "literal": "Xiangru Jian" }, { "literal": "Ziyang Luo" }, { "literal": "Zirui Zhao" }, { "literal": "Yutong Dai" }, { "literal": "Ziji Shi" }, { "literal": "Hanshu Yan" }, { "literal": "Jun Hao Liew" }, { "literal": "Silvio Savarese" }, { "literal": "Junnan Li" } ], "citation-key": "arxiv_2607_22798", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a010fbef09d8359550cf156bf0dcba873f25a0d6fb8f118d53bf6e23715cf203", "submitted_at": "2026-07-24T14:17:03Z", "updated_at": "2026-07-24T14:17:03Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.22798v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.22798", "catalog_id": "arxiv:2607.22798", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-24", "identifiers": { "arxiv": "2607.22798" }, "record_updated_at": "2026-07-24" }, "genre": "preprint", "id": "arxiv:2607.22798", "issued": { "date-parts": [ [ 2026, 7, 24 ] ] }, "note": "First published: 2026-07-24; Recorded arXiv version: v1; Recorded version updated: 2026-07-24T14:17:03Z.", "title": "StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.25904v2", "archive": "arXiv", "archive_location": "2607.25904", "author": [ { "literal": "Chenrui Shi" }, { "literal": "Yuwei Wu" }, { "literal": "Yang Liu" }, { "literal": "Ruining Feng" }, { "literal": "Zirui Shang" }, { "literal": "Zhi Gao" }, { "literal": "Lifeng Fan" }, { "literal": "Che Sun" } ], "citation-key": "arxiv_2607_25904", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d1688a528d35a8213a8027385b1b1327536567f6ec307aa6562eea543ee71d7f", "submitted_at": "2026-07-28T16:01:38Z", "updated_at": "2026-07-29T05:13:57Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2607.25904v2" }, "canonical_source_url": "https://arxiv.org/abs/2607.25904", "catalog_id": "arxiv:2607.25904", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-28", "identifiers": { "arxiv": "2607.25904" }, "record_updated_at": "2026-07-29" }, "genre": "preprint", "id": "arxiv:2607.25904", "issued": { "date-parts": [ [ 2026, 7, 28 ] ] }, "note": "First published: 2026-07-28; Recorded arXiv version: v2; Recorded version updated: 2026-07-29T05:13:57Z.", "title": "Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2607.28227v1", "archive": "arXiv", "archive_location": "2607.28227", "author": [ { "literal": "Hanzhang Zhou" }, { "literal": "Panrong Tong" }, { "literal": "Xu Zhang" }, { "literal": "Quyu Kong" }, { "literal": "Chenglin Cai" }, { "literal": "Tianyu Xia" }, { "literal": "Gongjie Zhang" }, { "literal": "Jianan Zhang" }, { "literal": "Long Li" }, { "literal": "Long Chen" }, { "literal": "Lei Wang" }, { "literal": "Gaole Dai" }, { "literal": "Pengxiang Li" }, { "literal": "Liangyu Chen" }, { "literal": "Yue Wang" }, { "literal": "Steven Hoi" } ], "citation-key": "arxiv_2607_28227", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "52fb1b49501132f1dbe3564daa02cca22a93fc8d7c28dec8ee6070a23889574a", "submitted_at": "2026-07-30T13:58:41Z", "updated_at": "2026-07-30T13:58:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.28227v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.28227", "catalog_id": "arxiv:2607.28227", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-30", "identifiers": { "arxiv": "2607.28227" }, "record_updated_at": "2026-07-30" }, "genre": "preprint", "id": "arxiv:2607.28227", "issued": { "date-parts": [ [ 2026, 7, 30 ] ] }, "note": "First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T13:58:41Z.", "title": "Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents", "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/2608.24017v1", "archive": "arXiv", "archive_location": "2608.24017", "author": [ { "literal": "Lin-Fa Lee" }, { "literal": "YI-YU Chang" }, { "literal": "Kuo-Hui Yeh" } ], "citation-key": "arxiv_2608_24017", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1bddfe5b5b2312e9b71d01dbb6bb23a8b0ad1c8cd787e4e98449b71a2ac2d678", "submitted_at": "2026-08-25T03:16:45Z", "updated_at": "2026-08-25T03:16:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.24017v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.24017", "catalog_id": "arxiv:2608.24017", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-08-25", "identifiers": { "arxiv": "2608.24017" }, "record_updated_at": "2026-08-25" }, "genre": "preprint", "id": "arxiv:2608.24017", "issued": { "date-parts": [ [ 2026, 8, 25 ] ] }, "note": "First published: 2026-08-25; Recorded arXiv version: v1; Recorded version updated: 2026-08-25T03:16:45Z.", "title": "WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.26991v1", "archive": "arXiv", "archive_location": "2608.26991", "author": [ { "literal": "Rui Xie" }, { "literal": "Lu Chen" } ], "citation-key": "arxiv_2608_26991", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e1626d5190f145c668c9b7f363b7f84904c12daae485e63b858e440ded5ea6df", "submitted_at": "2026-08-27T11:38:19Z", "updated_at": "2026-08-27T11:38:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.26991v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.26991", "catalog_id": "arxiv:2608.26991", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-27", "identifiers": { "arxiv": "2608.26991" }, "record_updated_at": "2026-08-27" }, "genre": "preprint", "id": "arxiv:2608.26991", "issued": { "date-parts": [ [ 2026, 8, 27 ] ] }, "note": "First published: 2026-08-27; Recorded arXiv version: v1; Recorded version updated: 2026-08-27T11:38:19Z.", "title": "ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.05374v1", "archive": "arXiv", "archive_location": "2609.05374", "author": [ { "literal": "Haoting Shi" }, { "literal": "Wenhao Wang" }, { "literal": "Weicheng Fang" }, { "literal": "Yaozhong Liang" }, { "literal": "Tian Jin" }, { "literal": "Pengxiang Zhao" }, { "literal": "Guangyi Liu" }, { "literal": "Siheng Chen" }, { "literal": "Yanfeng Wang" } ], "citation-key": "arxiv_2609_05374", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "69eab19b6e45e1b2ddf9f29f6f0937d51e06a5bb7dea34dadb761361c82f08d4", "submitted_at": "2026-09-04T17:26:18Z", "updated_at": "2026-09-04T17:26:18Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.05374v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.05374", "catalog_id": "arxiv:2609.05374", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-04", "identifiers": { "arxiv": "2609.05374" }, "record_updated_at": "2026-09-04" }, "genre": "preprint", "id": "arxiv:2609.05374", "issued": { "date-parts": [ [ 2026, 9, 4 ] ] }, "note": "First published: 2026-09-04; Recorded arXiv version: v1; Recorded version updated: 2026-09-04T17:26:18Z.", "title": "CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.06792v1", "archive": "arXiv", "archive_location": "2609.06792", "author": [ { "literal": "Juyong Lee" }, { "literal": "Woogyeol Jin" }, { "literal": "Kimin Lee" } ], "citation-key": "arxiv_2609_06792", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "14790f9565861cdba0b24661f6bfe87d7572cbad9d76d9a0b2d7216e9bac7ea7", "submitted_at": "2026-09-06T19:22:53Z", "updated_at": "2026-09-06T19:22:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.06792v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.06792", "catalog_id": "arxiv:2609.06792", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-06", "identifiers": { "arxiv": "2609.06792" }, "record_updated_at": "2026-09-06" }, "genre": "preprint", "id": "arxiv:2609.06792", "issued": { "date-parts": [ [ 2026, 9, 6 ] ] }, "note": "First published: 2026-09-06; Recorded arXiv version: v1; Recorded version updated: 2026-09-06T19:22:53Z.", "title": "Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.13548v1", "archive": "arXiv", "archive_location": "2609.13548", "author": [ { "literal": "Xinyun Cao" }, { "literal": "Adriana Szekeres" }, { "literal": "Fazle Elahi Faisal" } ], "citation-key": "arxiv_2609_13548", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0ce929c347ed5160b1f8455cc9d7e73ac2cc1b678e9d386d00dd4b2ef146b56d", "submitted_at": "2026-09-11T21:24:40Z", "updated_at": "2026-09-11T21:24:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.13548v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.13548", "catalog_id": "arxiv:2609.13548", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-11", "identifiers": { "arxiv": "2609.13548" }, "record_updated_at": "2026-09-11" }, "genre": "preprint", "id": "arxiv:2609.13548", "issued": { "date-parts": [ [ 2026, 9, 11 ] ] }, "note": "First published: 2026-09-11; Recorded arXiv version: v1; Recorded version updated: 2026-09-11T21:24:40Z.", "title": "AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.22000v2", "archive": "arXiv", "archive_location": "2609.22000", "author": [ { "literal": "Shuai Bai" }, { "literal": "Jiayong Deng" }, { "literal": "Sicheng Fan" }, { "literal": "Yikun Fu" }, { "literal": "Chang Gao" }, { "literal": "Xuhao Hu" }, { "literal": "Mianqiu Huang" }, { "literal": "Yizhen Jiang" }, { "literal": "Yuheng Jing" }, { "literal": "Dehui Kong" }, { "literal": "Keliang Li" }, { "literal": "Ning Li" }, { "literal": "Wanli Li" }, { "literal": "Dayiheng Liu" }, { "literal": "Dunjie Lu" }, { "literal": "Changwei Luo" }, { "literal": "Que Shen" }, { "literal": "Zheyuan Wang" }, { "literal": "Zijian Wang" }, { "literal": "Jie Wu" }, { "literal": "Gao Wu" }, { "literal": "Zhihui Xie" }, { "literal": "Rui Xie" }, { "literal": "Haiyang Xu" }, { "literal": "An Yang" }, { "literal": "Jiakang Yuan" }, { "literal": "Yanming Zhang" }, { "literal": "Jiajun Zhang" }, { "literal": "Xi Zhang" }, { "literal": "Zhenru Zhang" }, { "literal": "Zhuo Zhen" }, { "literal": "Mingkang Zhu" }, { "literal": "Bowen Zhou" } ], "citation-key": "arxiv_2609_22000", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3b312c5a4d638ec9f9a7408fd9ce2d8cbf74fa462d48c8aa37f59e4ad3bd8edc", "submitted_at": "2026-09-18T17:00:56Z", "updated_at": "2026-09-21T07:09:10Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2609.22000v2" }, "canonical_source_url": "https://arxiv.org/abs/2609.22000", "catalog_id": "arxiv:2609.22000", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-18", "identifiers": { "arxiv": "2609.22000" }, "record_updated_at": "2026-09-21" }, "genre": "preprint", "id": "arxiv:2609.22000", "issued": { "date-parts": [ [ 2026, 9, 18 ] ] }, "note": "First published: 2026-09-18; Recorded arXiv version: v2; Recorded version updated: 2026-09-21T07:09:10Z.", "title": "RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2609.22083v1", "archive": "arXiv", "archive_location": "2609.22083", "author": [ { "literal": "Mingfei Gao" }, { "literal": "Rui Tian" }, { "literal": "Haiming Gang" }, { "literal": "Bohan Zhai" }, { "literal": "Le Zhang" }, { "literal": "Yuanzheng Gong" }, { "literal": "Di Feng" }, { "literal": "Ege Özsoy" }, { "literal": "Kaixin Ma" }, { "literal": "Vishwesh Kirthivasan" }, { "literal": "Oğuzhan Fatih Kar" }, { "literal": "Roman Bachmann" }, { "literal": "Anders Boesen Lindbo Larsen" }, { "literal": "Afshin Dehghan" } ], "citation-key": "arxiv_2609_22083", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4dfb0703133032426ff8f40ed6a2c8131025b07658c0b643603f8d50ba163d16", "submitted_at": "2026-09-18T17:59:34Z", "updated_at": "2026-09-18T17:59:34Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.22083v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.22083", "catalog_id": "arxiv:2609.22083", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-18", "identifiers": { "arxiv": "2609.22083" }, "record_updated_at": "2026-09-18" }, "genre": "preprint", "id": "arxiv:2609.22083", "issued": { "date-parts": [ [ 2026, 9, 18 ] ] }, "note": "First published: 2026-09-18; Recorded arXiv version: v1; Recorded version updated: 2026-09-18T17:59:34Z.", "title": "MintAct: A Unified Visual Agent for Digital Environments", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.30887v1", "archive": "arXiv", "archive_location": "2609.30887", "author": [ { "literal": "Yuchen Sun" }, { "literal": "Chenglin Cai" }, { "literal": "Gongjie Zhang" }, { "literal": "Tianyu Xia" }, { "literal": "Quyu Kong" }, { "literal": "Panrong Tong" }, { "literal": "Zhengwen Zeng" }, { "literal": "Long Chen" }, { "literal": "Steven Hoi" }, { "literal": "Chongyang Zhang" }, { "literal": "Yue Wang" } ], "citation-key": "arxiv_2609_30887", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "838635f067b706c7b36a948c8100b30bf4cacd218470aaed6970e5186fa44fb9", "submitted_at": "2026-09-25T06:50:04Z", "updated_at": "2026-09-25T06:50:04Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.30887v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.30887", "catalog_id": "arxiv:2609.30887", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-25", "identifiers": { "arxiv": "2609.30887" }, "record_updated_at": "2026-09-25" }, "genre": "preprint", "id": "arxiv:2609.30887", "issued": { "date-parts": [ [ 2026, 9, 25 ] ] }, "note": "First published: 2026-09-25; Recorded arXiv version: v1; Recorded version updated: 2026-09-25T06:50:04Z.", "title": "From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.32600v1", "archive": "arXiv", "archive_location": "2609.32600", "author": [ { "literal": "Prince Zizhuang Wang" }, { "literal": "Chenhao Liang" }, { "literal": "Zelong Xu" }, { "literal": "Aojie Yuan" }, { "literal": "Xiaolin Zhou" }, { "literal": "Haiyue Zhang" }, { "literal": "Yue Zhao" }, { "literal": "Xiyang Hu" }, { "literal": "Shuli Jiang" } ], "citation-key": "arxiv_2609_32600", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d53f2512b99828849f047f63412264437a59b730c117c801de252e6dc80a33fc", "submitted_at": "2026-09-26T13:18:00Z", "updated_at": "2026-09-26T13:18:00Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.32600v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.32600", "catalog_id": "arxiv:2609.32600", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-26", "identifiers": { "arxiv": "2609.32600" }, "record_updated_at": "2026-09-26" }, "genre": "preprint", "id": "arxiv:2609.32600", "issued": { "date-parts": [ [ 2026, 9, 26 ] ] }, "note": "First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T13:18:00Z.", "title": "CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.36201v1", "archive": "arXiv", "archive_location": "2609.36201", "author": [ { "literal": "Jianxing Chen" }, { "literal": "Xiao Yu" }, { "literal": "Shipra Agrawal" }, { "literal": "Zhou Yu" } ], "citation-key": "arxiv_2609_36201", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e92c63d4cf58375aa7068570f8a98c145e24f8d393c5807c0aff3ed67f18b9f0", "submitted_at": "2026-09-28T20:01:35Z", "updated_at": "2026-09-28T20:01:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.36201v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.36201", "catalog_id": "arxiv:2609.36201", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-28", "identifiers": { "arxiv": "2609.36201" }, "record_updated_at": "2026-09-28" }, "genre": "preprint", "id": "arxiv:2609.36201", "issued": { "date-parts": [ [ 2026, 9, 28 ] ] }, "note": "First published: 2026-09-28; Recorded arXiv version: v1; Recorded version updated: 2026-09-28T20:01:35Z.", "title": "SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.38008v1", "archive": "arXiv", "archive_location": "2609.38008", "author": [ { "literal": "Tongbo Chen" }, { "literal": "Junbo Niu" }, { "literal": "Zhengxi Lu" }, { "literal": "Niu Lian" }, { "literal": "Fei Tang" }, { "literal": "Yuchen Yan" }, { "literal": "Yike Hong" }, { "literal": "Yong Du" }, { "literal": "Yizhou Liu" }, { "literal": "Bofan Chen" }, { "literal": "Yongliang Shen" } ], "citation-key": "arxiv_2609_38008", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b394677ebe37782950cfc56c0be65ca7a93f34e5550ec9425d91921bf1799847", "submitted_at": "2026-09-29T16:57:25Z", "updated_at": "2026-09-29T16:57:25Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.38008v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.38008", "catalog_id": "arxiv:2609.38008", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-29", "identifiers": { "arxiv": "2609.38008" }, "record_updated_at": "2026-09-29" }, "genre": "preprint", "id": "arxiv:2609.38008", "issued": { "date-parts": [ [ 2026, 9, 29 ] ] }, "note": "First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T16:57:25Z.", "title": "HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.04116v1", "archive": "arXiv", "archive_location": "2610.04116", "author": [ { "literal": "Yadong Lu" }, { "literal": "Theodore Lee" }, { "literal": "Yifei Li" }, { "literal": "Lawrence Keunho Jang" }, { "literal": "Tianci Xue" }, { "literal": "Yu Su" }, { "literal": "Huan Sun" }, { "literal": "Ahmed Hassan Awadallah" } ], "citation-key": "arxiv_2610_04116", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "97af38af8647b769c129d917b65f8f744035308f6ace88706a4888a96fe345b9", "submitted_at": "2026-10-02T22:43:06Z", "updated_at": "2026-10-02T22:43:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.04116v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.04116", "catalog_id": "arxiv:2610.04116", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-10-02", "identifiers": { "arxiv": "2610.04116" }, "record_updated_at": "2026-10-02" }, "genre": "preprint", "id": "arxiv:2610.04116", "issued": { "date-parts": [ [ 2026, 10, 2 ] ] }, "note": "First published: 2026-10-02; Recorded arXiv version: v1; Recorded version updated: 2026-10-02T22:43:06Z.", "title": "CUAWright: A Minimal Unified Interface for Digital Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.13416v1", "archive": "arXiv", "archive_location": "2610.13416", "author": [ { "literal": "Sunghwan Kim" }, { "literal": "Deogyong Kim" }, { "literal": "Sangam Lee" }, { "literal": "Donguk Kwon" }, { "literal": "Dongha Lee" } ], "citation-key": "arxiv_2610_13416", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cadcf2ab7be51b17d06975eba0e56573c333dca9ec034ade67b84e62d0096903", "submitted_at": "2026-10-09T11:23:40Z", "updated_at": "2026-10-09T11:23:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.13416v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.13416", "catalog_id": "arxiv:2610.13416", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-09", "identifiers": { "arxiv": "2610.13416" }, "record_updated_at": "2026-10-09" }, "genre": "preprint", "id": "arxiv:2610.13416", "issued": { "date-parts": [ [ 2026, 10, 9 ] ] }, "note": "First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T11:23:40Z.", "title": "Web$hell: A Unified Interface for Agentic Web Access", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.14157v1", "archive": "arXiv", "archive_location": "2610.14157", "author": [ { "literal": "Chenyang Yan" }, { "literal": "Yingying Zhang" }, { "literal": "Kanzhi Cheng" }, { "literal": "Qiushi Sun" }, { "literal": "Zhengyuan Pan" }, { "literal": "Zheng Ma" }, { "literal": "Hang Yan" }, { "literal": "Yian Wang" }, { "literal": "Nuo Chen" }, { "literal": "Jialin Cao" }, { "literal": "Xingdong Gong" }, { "literal": "Wenpo Song" }, { "literal": "Han Chen" }, { "literal": "Zichen Ding" }, { "literal": "Fangzhi Xu" }, { "literal": "Shujian Huang" }, { "literal": "Xinyu Dai" }, { "literal": "Yichen Liu" }, { "literal": "Tiankuo Yao" }, { "literal": "Bo Wang" }, { "literal": "Ben Kao" }, { "literal": "Jianbing Zhang" }, { "literal": "Lewei Lu" }, { "literal": "Dahua Lin" } ], "citation-key": "arxiv_2610_14157", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6f7d940d3e341fd8c9f23a4829a5ab1150fc07ee231ccda9b108a3f0d785efb9", "submitted_at": "2026-10-09T17:26:38Z", "updated_at": "2026-10-09T17:26:38Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.14157v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.14157", "catalog_id": "arxiv:2610.14157", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-09", "identifiers": { "arxiv": "2610.14157" }, "record_updated_at": "2026-10-09" }, "genre": "preprint", "id": "arxiv:2610.14157", "issued": { "date-parts": [ [ 2026, 10, 9 ] ] }, "note": "First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T17:26:38Z.", "title": "OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.15502v1", "archive": "arXiv", "archive_location": "2610.15502", "author": [ { "literal": "Hyobin Ahn" }, { "literal": "Dongjae Lee" } ], "citation-key": "arxiv_2610_15502", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ff5470e792d14ced2cdff648d97e2606eea4b3c822046b7c10272fd2a5f1695f", "submitted_at": "2026-10-11T10:09:44Z", "updated_at": "2026-10-11T10:09:44Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.15502v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.15502", "catalog_id": "arxiv:2610.15502", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-11", "identifiers": { "arxiv": "2610.15502" }, "record_updated_at": "2026-10-11" }, "genre": "preprint", "id": "arxiv:2610.15502", "issued": { "date-parts": [ [ 2026, 10, 11 ] ] }, "note": "First published: 2026-10-11; Recorded arXiv version: v1; Recorded version updated: 2026-10-11T10:09:44Z.", "title": "From Observations to Authorized Actions: Measuring Source Information in Android Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.22200v1", "archive": "arXiv", "archive_location": "2610.22200", "author": [ { "literal": "Hanzhang Zhou" }, { "literal": "Long Li" }, { "literal": "Quyu Kong" }, { "literal": "Lei Wang" }, { "literal": "Panrong Tong" }, { "literal": "Long Chen" }, { "literal": "Tianyu Xia" }, { "literal": "Gongjie Zhang" }, { "literal": "Xu Zhang" }, { "literal": "Chen Liu" }, { "literal": "Jianan Zhang" }, { "literal": "Chenglin Cai" }, { "literal": "Zhengwen Zeng" }, { "literal": "Steven Hoi" }, { "literal": "Yue Wang" } ], "citation-key": "arxiv_2610_22200", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "beab15a2bf8a6aca19d219dbe0a047e8c6d6bd84a580df33633b5d366c175a0e", "submitted_at": "2026-10-15T16:51:35Z", "updated_at": "2026-10-15T16:51:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.22200v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.22200", "catalog_id": "arxiv:2610.22200", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-15", "identifiers": { "arxiv": "2610.22200" }, "record_updated_at": "2026-10-15" }, "genre": "preprint", "id": "arxiv:2610.22200", "issued": { "date-parts": [ [ 2026, 10, 15 ] ] }, "note": "First published: 2026-10-15; Recorded arXiv version: v1; Recorded version updated: 2026-10-15T16:51:35Z.", "title": "OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.22234v1", "archive": "arXiv", "archive_location": "2610.22234", "author": [ { "literal": "Bowen Yang" }, { "literal": "Kaiming Jin" }, { "literal": "Zichen Ding" }, { "literal": "Zhenyu Wu" }, { "literal": "Zehao Li" }, { "literal": "Zhoumianze Liu" }, { "literal": "Kanzhi Cheng" }, { "literal": "Fangzhi Xu" }, { "literal": "Yanan Sun" }, { "literal": "Qiushi Sun" }, { "literal": "Yu Qiao" } ], "citation-key": "arxiv_2610_22234", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2b7f3542ca2faa63df81e25721a01928bfb35e9e3de458e8be27fd3f9010adc8", "submitted_at": "2026-10-15T17:14:02Z", "updated_at": "2026-10-15T17:14:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.22234v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.22234", "catalog_id": "arxiv:2610.22234", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-15", "identifiers": { "arxiv": "2610.22234" }, "record_updated_at": "2026-10-15" }, "genre": "preprint", "id": "arxiv:2610.22234", "issued": { "date-parts": [ [ 2026, 10, 15 ] ] }, "note": "First published: 2026-10-15; Recorded arXiv version: v1; Recorded version updated: 2026-10-15T17:14:02Z.", "title": "OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.23986v1", "archive": "arXiv", "archive_location": "2610.23986", "author": [ { "literal": "Xinyu Fang" }, { "literal": "Yuchi Wang" }, { "literal": "Weihao Yu" }, { "literal": "Rongyao Fang" }, { "literal": "Zhaohai Li" }, { "literal": "Zhixun Li" }, { "literal": "Tiancheng Gu" }, { "literal": "Xilin Wei" }, { "literal": "Yuhang Zang" }, { "literal": "Hongsheng Li" }, { "literal": "Dahua Lin" }, { "literal": "Guofeng Zhang" }, { "literal": "Shuai Bai" }, { "literal": "Zhibo Yang" }, { "literal": "Dayiheng Liu" } ], "citation-key": "arxiv_2610_23986", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6dfa0c59ec1262cebcf2a4e61ab1e0b58c647513d8e6eedb2ce7e6a1a675558c", "submitted_at": "2026-10-14T12:46:54Z", "updated_at": "2026-10-14T12:46:54Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.23986v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.23986", "catalog_id": "arxiv:2610.23986", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-10-14", "identifiers": { "arxiv": "2610.23986" }, "record_updated_at": "2026-10-14" }, "genre": "preprint", "id": "arxiv:2610.23986", "issued": { "date-parts": [ [ 2026, 10, 14 ] ] }, "note": "First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T12:46:54Z.", "title": "BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.26071v1", "archive": "arXiv", "archive_location": "2610.26071", "author": [ { "literal": "Zhanhui Zhou" }, { "literal": "Weichen Zhang" }, { "literal": "Haoran Liu" }, { "literal": "Lingjie Chen" }, { "literal": "Tianneng Shi" }, { "literal": "Kevin Lin" }, { "literal": "Zhengyuan Yang" }, { "literal": "Lijuan Wang" }, { "literal": "Dawn Song" } ], "citation-key": "arxiv_2610_26071", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0a297401f7ad4dcd2f485ade6bab295e365280bb803dcecc111aebf0693dd203", "submitted_at": "2026-10-19T09:30:54Z", "updated_at": "2026-10-19T09:30:54Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.26071v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.26071", "catalog_id": "arxiv:2610.26071", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-19", "identifiers": { "arxiv": "2610.26071" }, "record_updated_at": "2026-10-19" }, "genre": "preprint", "id": "arxiv:2610.26071", "issued": { "date-parts": [ [ 2026, 10, 19 ] ] }, "note": "First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T09:30:54Z.", "title": "CUA-Lite: An Open Platform for Computer Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.26828v1", "archive": "arXiv", "archive_location": "2610.26828", "author": [ { "literal": "Zhaoyang Wang" }, { "literal": "Qianhui Wu" }, { "literal": "Haorui Wang" }, { "literal": "Simon Yu" }, { "literal": "Baolin Peng" }, { "literal": "Canwen Xu" }, { "literal": "Hao Cheng" }, { "literal": "Wenlin Yao" }, { "literal": "Boyi Liu" }, { "literal": "Yite Wang" }, { "literal": "Jianfeng Gao" }, { "literal": "Huaxiu Yao" } ], "citation-key": "arxiv_2610_26828", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1f1ff33859352b61f017709fff91fd8e32f08636e9423fb044e7ca8e28f06905", "submitted_at": "2026-10-19T17:55:35Z", "updated_at": "2026-10-19T17:55:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.26828v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.26828", "catalog_id": "arxiv:2610.26828", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-19", "identifiers": { "arxiv": "2610.26828" }, "record_updated_at": "2026-10-19" }, "genre": "preprint", "id": "arxiv:2610.26828", "issued": { "date-parts": [ [ 2026, 10, 19 ] ] }, "note": "First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T17:55:35Z.", "title": "Agent World Model in the Wild: Computer-Use Agent Environment Synthesis", "type": "article", "version": "1" } ]