{"aliases": [], "authors": ["Lingbo Mo", "Zeyi Liao", "Boyuan Zheng", "Yu Su", "Chaowei Xiao", "Huan Sun"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b6d81a6b9de6fa32c8f5749d029d0819ddf3b310ae00a4872877ee72580e8879", "submitted_at": "2024-02-15T18:51:32Z", "updated_at": "2024-02-15T18:51:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2402.10196v1"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:08Z", "role": "primary", "sha256": "00d275cd5407cec847fa9d43fe73cfc4384c5570b68a5e058c97921799be0bec", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2302.01560%2C2303.16563%2C2305.15486%2C2305.16291%2C2305.17144%2C2306.00003%2C2306.00349%2C2306.17882%2C2310.01557%2C2310.08235%2C2310.08367%2C2311.05997%2C2311.17600%2C2312.02519%2C2312.11865%2C2402.01118%2C2402.10196%2C2402.11208%2C2403.10249%2C2403.12037%2C2404.06647%2C2404.12241%2C2404.13246%2C2407.15325%2C2409.00138%2C2410.14573%2C2410.18927%2C2410.19012%2C2411.09523%2C2411.10349%2C2411.13543%2C2412.01547%2C2501.05366%2C2501.09004%2C2502.07463%2C2502.14538%2C2503.02732%2C2503.08175%2C2503.11387%2C2504.10147%2C2504.11703%2C2504.14064%2C2504.15810%2C2504.16208%2C2504.20635%2C2504.21776%2C2505.12981%2C2505.13076%2C2506.01616%2C2506.13205&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:08Z", "role": "primary", "sha256": "00d275cd5407cec847fa9d43fe73cfc4384c5570b68a5e058c97921799be0bec", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2302.01560%2C2303.16563%2C2305.15486%2C2305.16291%2C2305.17144%2C2306.00003%2C2306.00349%2C2306.17882%2C2310.01557%2C2310.08235%2C2310.08367%2C2311.05997%2C2311.17600%2C2312.02519%2C2312.11865%2C2402.01118%2C2402.10196%2C2402.11208%2C2403.10249%2C2403.12037%2C2404.06647%2C2404.12241%2C2404.13246%2C2407.15325%2C2409.00138%2C2410.14573%2C2410.18927%2C2410.19012%2C2411.09523%2C2411.10349%2C2411.13543%2C2412.01547%2C2501.05366%2C2501.09004%2C2502.07463%2C2502.14538%2C2503.02732%2C2503.08175%2C2503.11387%2C2504.10147%2C2504.11703%2C2504.14064%2C2504.15810%2C2504.16208%2C2504.20635%2C2504.21776%2C2505.12981%2C2505.13076%2C2506.01616%2C2506.13205&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T13:00:03.117157+00:00", "role": "primary", "sha256": "a1d4dc44a6572863df1d8cc68bff592c3a04a174a3dbc87ab5cdcd0d33be92b0", "supports": ["summary", "scope", "environments", "notes"], "url": "https://arxiv.org/html/2402.10196v1"}], "id": "arxiv:2402.10196", "identifiers": {"arxiv": "2402.10196"}, "kind": "survey", "last_verified_at": "2026-10-18T10:54:08Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2402.10196"}], "name": "A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents", "notes": "Adjacent conceptual security work: the paper describes hypothetical scenarios and a future generalist agent, rather than an implemented attack benchmark. Scope was checked against the retained abstract and full-text Sections 2.4 and 3; no results were independently reproduced.", "published_at": "2024-02-15", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Presents a conceptual perception–reasoning–action framework and 12 potential attack scenarios for language agents, including hypothetical web-navigation attacks.", "topics": ["safety-security", "survey", "robustness"], "updated_at": "2024-02-15", "url": "https://arxiv.org/abs/2402.10196"}
{"aliases": [], "authors": ["Biao Wu", "Yanda Li", "Zhiwei Zhang", "Yunchao Wei", "Meng Fang", "Ling Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "de860a29f6c54317586c2218688436898f1d7a8b61207b1d5f4a65b05b3a4e6e", "submitted_at": "2024-11-04T11:50:58Z", "updated_at": "2025-09-14T09:13:39Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2411.02006v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T07:57:41Z", "role": "primary", "sha256": "0ba893415123ecc1763614ef5fc97e5c8bb7835f10b26b43f1b921ea860484cf", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2410.06212%2C2410.06215%2C2410.07283%2C2410.07331%2C2410.07869%2C2410.08209%2C2410.08368%2C2410.10570%2C2410.12481%2C2410.12669%2C2410.15549%2C2410.16950%2C2410.21909%2C2410.22584%2C2410.22770%2C2410.23022%2C2410.23555%2C2411.02006%2C2411.02393%2C2411.02479%2C2411.03312%2C2411.03817%2C2411.05451%2C2411.11145%2C2411.11904%2C2411.11916%2C2411.12990%2C2411.14228%2C2411.15397%2C2412.01857%2C2412.04144%2C2412.04383%2C2412.05819%2C2412.06224%2C2412.06771%2C2412.09530%2C2412.09613%2C2412.10047%2C2412.10380%2C2412.10673%2C2412.12004%2C2412.13178%2C2412.13810%2C2412.14203%2C2412.14222%2C2412.16359%2C2412.19638%2C2412.20206%2C2501.03895%2C2501.05179&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:13:27Z", "role": "primary", "sha256": "bda47fcb119c581a798dbc791b4929af91832d5053ac073a02dab8fd4e10ace3", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/2411.02006v3"}], "id": "arxiv:2411.02006", "identifiers": {"arxiv": "2411.02006"}, "kind": "survey", "last_verified_at": "2026-10-17T09:13:27Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2411.02006"}], "name": "Foundations and Recent Trends in Multimodal Mobile Agents: A Survey", "notes": "Reviewed against the exact-version official arXiv abstract page; its normalized abstract SHA-256 matches the retained bibliographic snapshot. The original API response body was not locally available for this review. Experimental results and artifact availability have not been independently reproduced.", "published_at": "2024-11-04", "relations": [], "review_status": "curated", "scope": "core", "summary": "Surveys multimodal mobile agents, organizing prompt-based and training-based approaches alongside evaluation benchmarks, supporting technologies, and open challenges in mobile task execution.", "topics": ["survey", "mobile-navigation", "evaluation"], "updated_at": "2025-09-14", "url": "https://arxiv.org/abs/2411.02006"}
{"aliases": [], "authors": ["Shuai Wang", "Weiwen Liu", "Jingxuan Chen", "Yuqi Zhou", "Weinan Gan", "Xingshan Zeng", "Yuhan Che", "Shuai Yu", "Xinlong Hao", "Kun Shao", "Bin Wang", "Chuhan Wu", "Yasheng Wang", "Ruiming Tang", "Jianye Hao"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "57670445f9b0041bfb505a195d01a9ded6234e01e44c9aa43a6aee5ebd57dd93", "submitted_at": "2024-11-07T17:28:10Z", "updated_at": "2025-02-13T10:09:37Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2411.04890v2"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2411.04890", "identifiers": {"arxiv": "2411.04890"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2411.04890"}], "name": "GUI Agents with Foundation Models: A Comprehensive Survey", "notes": "", "published_at": "2024-11-07", "relations": [], "review_status": "curated", "scope": "core", "summary": "Survey of (M)LLM-based GUI agents organized around their datasets and benchmarks, a unified agent framework with a taxonomy, and commercial applications.", "topics": ["survey"], "updated_at": "2025-02-13", "url": "https://arxiv.org/abs/2411.04890"}
{"aliases": [], "authors": ["Minghe Gao", "Wendong Bu", "Bingchen Miao", "Yang Wu", "Yunfei Li", "Juncheng Li", "Siliang Tang", "Qi Wu", "Yueting Zhuang", "Meng Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "daa9b7092616e94a1d0124d36d8b75d0401b9647ec762c963524616a92def9a5", "submitted_at": "2024-11-17T02:44:56Z", "updated_at": "2024-11-17T02:44:56Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2411.10943v1"}}, "environments": ["web", "desktop", "android", "windows"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:29:13.577033+00:00", "role": "primary", "sha256": "92f18020e481d6f42a6d35e96dff820594e9370597f5392d038e9ee908c49f1e", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/html/2411.10943v1"}], "id": "arxiv:2411.10943", "identifiers": {"arxiv": "2411.10943"}, "kind": "survey", "last_verified_at": "2026-10-18T04:29:13.577033+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2411.10943"}], "name": "Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platforms", "notes": "Reviewed the complete retained arXiv abstract and exact-version official HTML sections on browser/application/OS environments, screen observations, input actions and evaluation. The HTML abstract fingerprint and ordered authors match the retained Atom entry. Literature claims and experiments were not independently reproduced.", "published_at": "2024-11-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "Surveys virtual agents for browsers, applications and operating systems, organizing prior work by task type, observation and action spaces, model strategies and evaluation methods. It examines screen-based interaction and keyboard, mouse and touch control, alongside transferability and long-sequence decision-making challenges.", "topics": ["survey", "web-navigation", "mobile-navigation", "evaluation", "planning"], "updated_at": "2024-11-17", "url": "https://arxiv.org/abs/2411.10943"}
{"aliases": [], "authors": ["Chaoyun Zhang", "Shilin He", "Jiaxu Qian", "Bowen Li", "Liqun Li", "Si Qin", "Yu Kang", "Minghua Ma", "Guyue Liu", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2f692aa06152820ae60359fc2cc52aaed2ca8a97fe1efb9b8037de973956467a", "submitted_at": "2024-11-27T12:13:39Z", "updated_at": "2025-05-06T15:08:00Z", "version": 12, "versioned_url": "https://arxiv.org/abs/2411.18279v12"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2411.18279", "identifiers": {"arxiv": "2411.18279"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2411.18279"}], "name": "Large Language Model-Brained GUI Agents: A Survey", "notes": "", "published_at": "2024-11-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "Survey of LLM-brained GUI agents that carry out natural-language instructions across web, mobile, and desktop interfaces, organizing research and industry progress.", "topics": ["survey"], "updated_at": "2025-05-06", "url": "https://arxiv.org/abs/2411.18279"}
{"aliases": [], "authors": ["Dang Nguyen", "Jian Chen", "Yu Wang", "Gang Wu", "Namyong Park", "Zhengmian Hu", "Hanjia Lyu", "Junda Wu", "Ryan Aponte", "Yu Xia", "Xintong Li", "Jing Shi", "Hongjie Chen", "Viet Dac Lai", "Zhouhang Xie", "Sungchul Kim", "Ruiyi Zhang", "Tong Yu", "Mehrab Tanjim", "Nesreen K. Ahmed", "Puneet Mathur", "Seunghyun Yoon", "Lina Yao", "Branislav Kveton", "Jihyung Kil", "Thien Huu Nguyen", "Trung Bui", "Tianyi Zhou", "Ryan A. Rossi", "Franck Dernoncourt"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ae8f83d0490e70db1ae9c55c071935fb1f59e1358335c1bd3f50835611f4360c", "submitted_at": "2024-12-18T04:48:28Z", "updated_at": "2025-09-26T21:01:59Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2412.13501v3"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2412.13501", "identifiers": {"arxiv": "2412.13501"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2412.13501"}], "name": "GUI Agents: A Survey", "notes": "", "published_at": "2024-12-18", "relations": [], "review_status": "curated", "scope": "core", "summary": "Categorizes GUI-agent benchmarks, evaluation metrics, architectures, and training methods, and proposes a unified perception, reasoning, planning, and acting framework.", "topics": ["survey"], "updated_at": "2025-09-26", "url": "https://arxiv.org/abs/2412.13501"}
{"aliases": [], "authors": ["Pascal J. Sager", "Benjamin Meyer", "Peng Yan", "Rebekka von Wartburg-Kottler", "Layan Etaiwi", "Aref Enayati", "Gabriel Nobel", "Ahmed Abdulkadir", "Benjamin F. Grewe", "Thilo Stadelmann"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b36fe818cb176c434b953fe8d2c97b67176b58cc6f8426b629231875de3c0896", "submitted_at": "2025-01-27T15:44:02Z", "updated_at": "2026-03-27T07:41:10Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2501.16150v3"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2501.16150", "identifiers": {"arxiv": "2501.16150"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:58Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2501.16150"}], "name": "A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions", "notes": "", "published_at": "2025-01-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "Reviews 87 computer-use agents and 33 datasets through a taxonomy of operating domain, observation and action modalities, and agent design.", "topics": ["survey"], "updated_at": "2026-03-27", "url": "https://arxiv.org/abs/2501.16150"}
{"aliases": [], "authors": ["Chaoyun Zhang", "Shilin He", "Liqun Li", "Si Qin", "Yu Kang", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang"], "details": {"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"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2503.11069", "identifiers": {"arxiv": "2503.11069"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.11069"}], "name": "API Agents vs. GUI Agents: Divergence and Convergence", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2025-03-14", "relations": [], "review_status": "curated", "scope": "core", "summary": "Compares API-driven and GUI-driven agents across architecture, development, and interaction considerations, discussing when hybrid approaches are useful.", "topics": ["tool-integration", "survey", "automation"], "updated_at": "2025-06-23", "url": "https://arxiv.org/abs/2503.11069"}
{"aliases": [], "authors": ["Liangbo Ning", "Ziran Liang", "Zhuohang Jiang", "Haohao Qu", "Yujuan Ding", "Wenqi Fan", "Xiao-yong Wei", "Shanru Lin", "Hui Liu", "Philip S. Yu", "Qing Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4b214bd8e5a34c0e8ca16a3be4fcf638a59a17ca524276dbef3c6b75f08398bb", "submitted_at": "2025-03-30T08:15:44Z", "updated_at": "2025-08-05T11:47:41Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2503.23350v4"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:21:52Z", "role": "primary", "sha256": "c194d15b7e422aae48b4e05216a1f1d84471b6666718b9d3dd4c9d250c356e77", "supports": ["name", "kind", "scope", "environments", "topics", "summary", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2210.03347%2C2403.04984%2C2405.07090%2C2406.06282%2C2409.00088%2C2409.10811%2C2411.10943%2C2503.09241%2C2503.20279%2C2503.23350%2C2505.05440%2C2505.10593%2C2505.16422%2C2505.21279%2C2505.24878%2C2506.02153%2C2506.02839%2C2506.05079%2C2506.07976%2C2508.02046%2C2511.07885%2C2511.11248%2C2512.21720%2C2603.20351%2C2604.19299&max_results=25"}], "id": "arxiv:2503.23350", "identifiers": {"arxiv": "2503.23350"}, "kind": "survey", "last_verified_at": "2026-10-18T04:21:52Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.23350"}], "name": "A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models", "notes": "Reviewed against the complete official arXiv abstract. Experimental results and linked artifact availability have not been independently reproduced.", "published_at": "2025-03-30", "relations": [], "review_status": "curated", "scope": "core", "summary": "Surveys foundation-model web agents through their architectures, training methods and trustworthiness. It organizes research on completing browser tasks from user instructions and identifies directions for further development.", "topics": ["survey", "web-navigation", "safety-security"], "updated_at": "2025-08-05", "url": "https://arxiv.org/abs/2503.23350"}
{"aliases": [], "authors": ["Yucheng Shi", "Wenhao Yu", "Jingyuan Huang", "Wenlin Yao", "Wenhu Chen", "Ninghao Liu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5a6811c6d0c3b30d4e6af2f7b0beef8aa8f1ad99ceb325182305e571fe5c398f", "submitted_at": "2025-03-30T13:26:00Z", "updated_at": "2026-02-24T05:24:23Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2503.23434v2"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2503.23434", "identifiers": {"arxiv": "2503.23434"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2503.23434"}], "name": "Towards Trustworthy GUI Agents: A Survey", "notes": "", "published_at": "2025-03-30", "relations": [], "review_status": "curated", "scope": "core", "summary": "Frames GUI-agent trustworthiness as an execution gap and reviews failures, attacks, and defenses across perception, reasoning, and interaction.", "topics": ["survey", "safety-security"], "updated_at": "2026-02-24", "url": "https://arxiv.org/abs/2503.23434"}
{"aliases": [], "authors": ["Fei Tang", "Haolei Xu", "Hang Zhang", "Siqi Chen", "Xingyu Wu", "Yongliang Shen", "Wenqi Zhang", "Guiyang Hou", "Zeqi Tan", "Yuchen Yan", "Kaitao Song", "Jian Shao", "Weiming Lu", "Jun Xiao", "Yueting Zhuang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "216d0605205cfd7f17ffd7d7f4c9752577ca427f370df42faf4a2250b80bcc39", "submitted_at": "2025-03-27T17:58:31Z", "updated_at": "2025-06-04T17:29:13Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.13865v2"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2504.13865", "identifiers": {"arxiv": "2504.13865"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2504.13865"}], "name": "A Survey on (M)LLM-Based GUI Agents", "notes": "", "published_at": "2025-03-27", "relations": [], "review_status": "curated", "scope": "core", "summary": "Analyzes LLM-based GUI agents through four components (perception, exploration, planning, and interaction) and the methods used to evaluate them.", "topics": ["survey"], "updated_at": "2025-06-04", "url": "https://arxiv.org/abs/2504.13865"}
{"aliases": [], "authors": ["Guangyi Liu", "Pengxiang Zhao", "Yaozhen Liang", "Liang Liu", "Yaxuan Guo", "Han Xiao", "Weifeng Lin", "Yuxiang Chai", "Yue Han", "Shuai Ren", "Hao Wang", "Xiaoyu Liang", "WenHao Wang", "Tianze Wu", "Zhengxi Lu", "Siheng Chen", "LiLinghao", "Hao Wang", "Guanjing Xiong", "Yong Liu", "Hongsheng Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9103197fa1274fac79ae9e4472f5fbdc9a210548afb024f1d4259c6bb0131bf2", "submitted_at": "2025-04-28T14:39:25Z", "updated_at": "2025-11-17T15:51:58Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2504.19838v3"}}, "environments": ["android", "ios"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2504.19838", "identifiers": {"arxiv": "2504.19838"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2504.19838"}], "name": "LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects", "notes": "", "published_at": "2025-04-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "Reviews LLM-driven phone GUI agents with a taxonomy of agent frameworks, prompt- and training-based modeling, datasets, and benchmarks.", "topics": ["survey"], "updated_at": "2025-11-17", "url": "https://arxiv.org/abs/2504.19838"}
{"aliases": [], "authors": ["Jiahao Li", "Kaer Huang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5040073e7c278734df219d71d94e236468468621f5971ef3ccbc97b94e1792b9", "submitted_at": "2025-04-29T06:55:15Z", "updated_at": "2025-05-13T01:59:29Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.20464v2"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2504.20464", "identifiers": {"arxiv": "2504.20464"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2504.20464"}], "name": "A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning", "notes": "", "published_at": "2025-04-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "Formalizes GUI tasks as Markov decision processes and traces agent training from prompting through supervised fine-tuning to reinforcement learning.", "topics": ["survey", "reinforcement-learning"], "updated_at": "2025-05-13", "url": "https://arxiv.org/abs/2504.20464"}
{"aliases": [], "authors": ["Ada Chen", "Yongjiang Wu", "Junyuan Zhang", "Jingyu Xiao", "Shu Yang", "Jen-tse Huang", "Kun Wang", "Wenxuan Wang", "Shuai Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e8a0890cd57809ff5e3bede6dc2b851b42fad9307a5bfa0ddd744cc2ac70d0c2", "submitted_at": "2025-05-16T06:56:42Z", "updated_at": "2026-04-29T05:56:22Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2505.10924v4"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:54Z", "role": "primary", "sha256": "4953a8e0f029016aef668bce98cec4d2873a7ae49c1fe33c4311fa5eb8d24089", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=700&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2505.10924", "identifiers": {"arxiv": "2505.10924"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:54Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.10924"}], "name": "A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?", "notes": "", "published_at": "2025-05-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "Systematizes safety and security threats to computer-using agents, with taxonomies of threats and defensive strategies.", "topics": ["survey", "safety-security"], "updated_at": "2026-04-29", "url": "https://arxiv.org/abs/2505.10924"}
{"aliases": [], "authors": ["Xueyu Hu", "Tao Xiong", "Biao Yi", "Zishu Wei", "Ruixuan Xiao", "Yurun Chen", "Jiasheng Ye", "Meiling Tao", "Xiangxin Zhou", "Ziyu Zhao", "Yuhuai Li", "Shengze Xu", "Shenzhi Wang", "Xinchen Xu", "Shuofei Qiao", "Zhaokai Wang", "Kun Kuang", "Tieyong Zeng", "Liang Wang", "Jiwei Li", "Yuchen Eleanor Jiang", "Wangchunshu Zhou", "Guoyin Wang", "Keting Yin", "Zhou Zhao", "Hongxia Yang", "Fan Wu", "Shengyu Zhang", "Fei Wu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "f14fdd895e52277a3695eeb83e5095472051d139aec63f22f9c63d344c051dad", "submitted_at": "2025-08-06T14:33:45Z", "updated_at": "2025-08-06T14:33:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2508.04482v1"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:49Z", "role": "primary", "sha256": "c208e36ae75cef4b32cfcb2f8182dd4aaaa218e3119bb3d4a2c20a5832f8b1ee", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2506.10387%2C2506.14866%2C2506.20332%2C2507.00008%2C2507.02592%2C2507.03730%2C2507.04227%2C2507.05445%2C2507.05673%2C2507.05720%2C2507.05791%2C2507.14293%2C2507.14799%2C2507.15846%2C2507.16853%2C2507.19132%2C2507.19478%2C2507.21071%2C2507.22025%2C2507.22358%2C2507.23779%2C2508.00935%2C2508.01330%2C2508.03700%2C2508.03923%2C2508.04010%2C2508.04026%2C2508.04482%2C2508.04700%2C2508.05615%2C2508.05731%2C2508.09057%2C2508.09123%2C2508.13167%2C2508.14040%2C2508.15144%2C2508.18689%2C2508.19679%2C2508.20096%2C2509.02544%2C2509.03891%2C2509.06477%2C2509.10723%2C2509.11250%2C2509.11543%2C2509.15221%2C2509.15566%2C2509.15738%2C2509.18119%2C2510.01354&max_results=50"}], "id": "arxiv:2508.04482", "identifiers": {"arxiv": "2508.04482"}, "kind": "survey", "last_verified_at": "2026-10-16T06:31:49Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2508.04482"}], "name": "OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use", "notes": "", "published_at": "2025-08-06", "relations": [], "review_status": "curated", "scope": "core", "summary": "Surveys agents that operate computers and phones through operating-system interfaces, covering components, capabilities, foundation models, frameworks, and benchmarks.", "topics": ["survey"], "updated_at": "2025-08-06", "url": "https://arxiv.org/abs/2508.04482"}
{"aliases": [], "authors": ["Renjun Xu", "Yang Yan"], "details": {"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"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:12Z", "role": "primary", "sha256": "c8c95278aa5dcc6a8f2eda3f3b44d61ec1f35adcb6a4c6c9ab328691a1a4f102", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2601.13462%2C2601.14232%2C2601.15331%2C2601.17548%2C2601.18418%2C2601.18491%2C2601.18827%2C2601.20171%2C2601.20613%2C2601.20742%2C2601.21233%2C2601.21253%2C2601.22037%2C2601.22154%2C2601.22511%2C2601.22607%2C2602.01550%2C2602.03117%2C2602.03361%2C2602.05665%2C2602.05746%2C2602.05877%2C2602.06052%2C2602.07398%2C2602.07458%2C2602.07918%2C2602.09007%2C2602.09463%2C2602.09514%2C2602.10122%2C2602.10525%2C2602.11224%2C2602.12268%2C2602.12430%2C2602.13318%2C2602.13543%2C2602.13692%2C2602.14038%2C2602.14337%2C2602.14364%2C2602.16313%2C2602.16317%2C2602.16666%2C2602.16901%2C2602.16930%2C2602.17547%2C2602.17646%2C2602.18846%2C2602.19320%2C2602.19594&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:12Z", "role": "primary", "sha256": "c8c95278aa5dcc6a8f2eda3f3b44d61ec1f35adcb6a4c6c9ab328691a1a4f102", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2601.13462%2C2601.14232%2C2601.15331%2C2601.17548%2C2601.18418%2C2601.18491%2C2601.18827%2C2601.20171%2C2601.20613%2C2601.20742%2C2601.21233%2C2601.21253%2C2601.22037%2C2601.22154%2C2601.22511%2C2601.22607%2C2602.01550%2C2602.03117%2C2602.03361%2C2602.05665%2C2602.05746%2C2602.05877%2C2602.06052%2C2602.07398%2C2602.07458%2C2602.07918%2C2602.09007%2C2602.09463%2C2602.09514%2C2602.10122%2C2602.10525%2C2602.11224%2C2602.12268%2C2602.12430%2C2602.13318%2C2602.13543%2C2602.13692%2C2602.14038%2C2602.14337%2C2602.14364%2C2602.16313%2C2602.16317%2C2602.16666%2C2602.16901%2C2602.16930%2C2602.17547%2C2602.17646%2C2602.18846%2C2602.19320%2C2602.19594&max_results=50"}], "id": "arxiv:2602.12430", "identifiers": {"arxiv": "2602.12430"}, "kind": "survey", "last_verified_at": "2026-10-17T12:31:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.12430"}], "name": "Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified. Adjacent survey of the skill layer: CUA deployment and GUI grounding are explicit parts of the review, but its overall scope extends well beyond interface agents.", "published_at": "2026-02-12", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "This survey organizes agent skills by architecture, acquisition, deployment and security, including their role in computer-use systems and GUI grounding. It also proposes a permission and lifecycle governance framework for skill deployment.", "topics": ["survey", "tool-integration", "safety-security", "planning"], "updated_at": "2026-06-02", "url": "https://arxiv.org/abs/2602.12430"}
{"aliases": [], "authors": ["Zehao Lin", "Xixuan Hao", "Renyu Fu", "Shaobo Cui", "Kai Chen", "Chunyu Li", "Zhiyu Li", "Feiyu Xiong"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fb75ea30086ecf069d8adda1513a6e906cfcfcedcd4cab01d0986a850aa8009a", "submitted_at": "2026-04-17T06:28:22Z", "updated_at": "2026-09-22T07:33:24Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2604.16548v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T13:00:08.054642+00:00", "role": "primary", "sha256": "f795535d55a4def0f2ce7dfc41a9d1d22ad38eddf48fb4f1feed98b6b5b66721", "supports": ["summary", "scope", "notes"], "url": "https://arxiv.org/html/2604.16548v3"}], "id": "arxiv:2604.16548", "identifiers": {"arxiv": "2604.16548"}, "kind": "survey", "last_verified_at": "2026-10-18T10:54:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.16548"}], "name": "A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle", "notes": "Adjacent memory-security survey. Full-text Sections 3.1 and 3.3 discuss poisoned web observations persisted into later agent actions; the work is broader than GUI agents and does not establish a platform implementation.", "published_at": "2026-04-17", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Organizes security risks and defenses for persistent agent memory into six lifecycle phases and proposes five verifiable governance primitives.", "topics": ["memory", "safety-security", "survey"], "updated_at": "2026-09-22", "url": "https://arxiv.org/abs/2604.16548"}
{"aliases": [], "authors": ["Sanket Badhe", "Deep Shah", "Priyanka Tiwari", "Nehal Kathrotia"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "13b6833243a543eb156ce7f4d943f8a3c608b3b38b7eaa77605ca7484cdedc43", "submitted_at": "2026-08-30T06:36:42Z", "updated_at": "2026-09-28T17:25:01Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2608.29596v2"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:54:12Z", "role": "primary", "sha256": "5f5bae19420f79231516d4bcf604ea18d4f930fc7790cde5a3e7fcb8d41a1126", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?id_list=2508.19461%2C2508.19493%2C2509.21782%2C2509.25140%2C2510.03485%2C2510.07809%2C2510.14276%2C2510.27140%2C2510.27210%2C2511.13248%2C2512.08417%2C2601.07263%2C2602.13516%2C2603.00476%2C2603.11862%2C2603.18762%2C2603.23791%2C2604.00986%2C2604.16515%2C2604.16548%2C2604.24348%2C2605.05509%2C2605.08876%2C2605.20833%2C2605.24785%2C2607.00333%2C2607.18659%2C2607.25255%2C2608.00202%2C2608.08939%2C2608.24913%2C2608.29596&max_results=32"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T13:00:09.204016+00:00", "role": "primary", "sha256": "d112d0a83472b87de538d0290efdd2d0dd0d21e878acca5f383da5baa880fe88", "supports": ["scope", "environments", "notes"], "url": "https://arxiv.org/html/2608.29596v2"}], "id": "arxiv:2608.29596", "identifiers": {"arxiv": "2608.29596"}, "kind": "survey", "last_verified_at": "2026-10-18T10:54:12Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2608.29596"}], "name": "A Systematic Survey of Agentic Skills: Architecture, Lifecycle, and Security", "notes": "Adjacent broad survey of procedural agent skills. Full-text Section 4.4.2 explicitly covers desktop, mobile, and web interface skills; surveyed systems and their reported results are not independently reproduced.", "published_at": "2026-08-30", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Surveys modular agentic skill architectures, skill lifecycles, and security risks in autonomous tool- and interface-using agents.", "topics": ["survey", "workflow", "memory", "safety-security"], "updated_at": "2026-09-28", "url": "https://arxiv.org/abs/2608.29596"}
{"aliases": [], "authors": ["Bizhe Bai", "Jiakang Yuan", "Hongming Wu", "Xinyue Wang", "Jie Ren", "Siyao Chen", "Yuchen Ya", "Fan Bai", "Pai Peng", "Huafeng Qin", "Tao Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ec439fd2cfdf7319d77ef5ab58e50143bceb3f8205ccffa0d83555f10dece42a", "submitted_at": "2026-09-02T08:54:58Z", "updated_at": "2026-09-02T08:54:58Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.02309v1"}}, "environments": ["cross-platform"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:32Z", "role": "primary", "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations"], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.02309", "identifiers": {"arxiv": "2609.02309"}, "kind": "survey", "last_verified_at": "2026-10-16T06:36:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.02309"}], "name": "Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization", "notes": "", "published_at": "2026-09-02", "relations": [], "review_status": "curated", "scope": "core", "summary": "Surveys GUI-agent efficiency beyond task success: observation, context and memory, action, and planner or runtime cost.", "topics": ["survey"], "updated_at": "2026-09-02", "url": "https://arxiv.org/abs/2609.02309"}
{"aliases": [], "authors": ["Minghao Guo", "Qingyue Jiao", "Xiujin Liu", "Jianhong Pang", "Ruimeng Yang", "Naihao Xu", "Liwei Che", "Haochen Xue", "Ziqi Wang", "Xinying Cai", "Jiaxuan Luo", "Jiaxin Deng", "Xuesong Ye", "Jintao Qu", "Wenyao Gao", "Jingwen Gu", "Chenyang Zhao", "Shichun Liu", "Guibin Zhang", "Zefang Liu", "Siyin Wang", "Wujiang Xu", "Danrui Li", "Zeru Shi", "Woongyeong Yeo", "Shuang Liu", "Wei-Chieh Huang", "Weizhi Zhang", "Tianyu Yang", "Kangsan Kim", "Yebowen Hu", "Bowen Wen", "Bowen Jiang", "Haohao Su", "Ming Yin", "Sheldon Yu", "Mian Zhang", "Yuyan Chen", "Hanrong Zhang", "Kai Mei", "Zihao Zhang", "Mingyu Jin", "Xi Zhu", "Hengyi Wang", "Tianxin Wei", "Linyong Nan", "Zhenwen Liang", "Zhendong Chu", "Ziqi Huang", "Yongye Su", "Sixun Dong", "Shujian Liu", "Kaiqu Liang", "Jiaojiao Han", "Zhaoye Fei", "Kun Wang", "Shihan Dou", "Zhichun Guo", "Xingjian Diao", "Zeqi Gu", "Heng Wang", "Tao Feng", "Cheng Qian", "Hamid Palangi", "Silei Xu", "Xi Yun", "Yi Zhu", "Shilong Liu", "Qingsong Wen", "Sung Ju Hwang", "Zuxuan Wu", "Yu-Gang Jiang", "Yiyu Shi", "Dimitris N. Metaxas", "Jiaxuan You", "Julian McAuley", "Mengdi Wang", "Jiawei Han", "Philip S. Yu", "Ziyi Ye"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7f1a48aa4b89fb97e8e1a186ba7345826a8b9efc9aa7b82e0dd1f5ce17d42b73", "submitted_at": "2026-10-14T01:11:57Z", "updated_at": "2026-10-14T01:11:57Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.19366v1"}, "license_review": {"document": {"evidence_urls": ["https://arxiv.org/html/2610.19366v1"], "reason": "Paper-specific document declaration only; no code, data or weights permissions are inferred."}}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:39Z", "role": "primary", "sha256": "c52e4e283e0dae88ef8b3ce67b7424b1d4b48e8f41015d872f4da69f98782eaa", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2609.39924%2C2610.00346%2C2610.00583%2C2610.01939%2C2610.05099%2C2610.09127%2C2610.09484%2C2610.09633%2C2610.11251%2C2610.11922%2C2610.13098%2C2610.13166%2C2610.13361%2C2610.13623%2C2610.16117%2C2610.17953%2C2610.18067%2C2610.19366%2C2610.20424&max_results=19"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T19:02:22.864948+00:00", "role": "primary", "sha256": "308796868bf9b1cb042bc6008e1e6f4ba6e776a2d4e13d40ad5684b477861563", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "licenses.document"], "url": "https://arxiv.org/html/2610.19366v1"}], "id": "arxiv:2610.19366", "identifiers": {"arxiv": "2610.19366"}, "kind": "survey", "last_verified_at": "2026-10-20T19:02:22.864948+00:00", "licenses": {"code": null, "data": null, "document": {"basis": "The retained exact-v1 arXiv HTML infobox explicitly declares License: CC BY 4.0 for this document.", "declared": "CC-BY-4.0", "retrieved_at": "2026-10-20T19:02:22.864948+00:00", "url": "https://arxiv.org/html/2610.19366v1"}, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.19366"}], "name": "Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory", "notes": "A broad literature synthesis spanning images, video, audio, GUI and embodied settings. Its GUI section compares interface-state retention, action outcomes, cross-session reuse and visual evidence, but the paper does not provide a new GUI-agent experiment. Taxonomy corpus counts and benchmark classifications are authors' annotations, not independently audited field coverage. Updating stored content alone does not establish the survey's self-evolving-policy tier; endpoint task success does not isolate memory use. Lifecycle, resource-budget and provenance recommendations are proposed evaluation directions rather than demonstrated guarantees. Platform facets stay unspecified; cited systems and releases were not independently verified.", "published_at": "2026-10-14", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Surveys multimodal memory using representation and management axes, distinguishing fixed-policy updates from policy evolution and comparing GUI memory evaluation with other modalities.", "topics": ["survey", "memory", "evaluation", "interaction-history"], "updated_at": "2026-10-14", "url": "https://arxiv.org/abs/2610.19366"}