{"aliases": [], "authors": ["Sabrina Haque", "Christoph Csallner"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2d927b7644f0c6b3a49fbdf1aa976a00f2409adf9a72e1c04333438f66f1014b", "submitted_at": "2024-09-26T17:01:33Z", "updated_at": "2024-10-07T19:04:38Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2409.18060v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:45:04Z", "role": "primary", "sha256": "bab88dfed88ca440c231aa768530374a0f19498777a70921481a904fddd46bb8", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://export.arxiv.org/api/query?id_list=2303.17760%2C2310.03720%2C2312.11190%2C2403.02502%2C2406.12639%2C2409.18060%2C2410.00201%2C2501.01702%2C2501.11425%2C2502.02533%2C2502.02955%2C2502.12110%2C2502.15760%2C2502.17110%2C2502.19328%2C2503.02197%2C2503.02403%2C2503.02682%2C2503.06580%2C2503.07365%2C2503.09572%2C2503.14021%2C2503.24180%2C2504.02357%2C2504.11675%2C2504.13936&max_results=26"}], "id": "arxiv:2409.18060", "identifiers": {"arxiv": "2409.18060"}, "kind": "paper", "last_verified_at": "2026-10-16T06:45:04Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2409.18060"}], "name": "Inferring Alt-text For UI Icons With Large Language Models During App Development", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental findings and artifact availability have not been independently reproduced. This is a UI accessibility and element-description method; autonomous GUI control is not evaluated.", "published_at": "2024-09-26", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Introduces IconDesc, which generates mobile icon alt-text from partial UI context such as element identifiers, bounds, nearby text and hierarchy. Model evaluation and a user study examine the resulting accessibility descriptions.", "topics": ["screen-understanding", "ui-design", "evaluation"], "updated_at": "2024-10-07", "url": "https://arxiv.org/abs/2409.18060"}
{"aliases": [], "authors": ["Jaehyun Jeon", "Min Soo Kim", "Jang Han Yoon", "Sumin Shim", "Yejin Choi", "Hanbin Kim", "Dae Hyun Kim", "Youngjae Yu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3f65cd2856c554584baab9b1cbf9c5250b5c01d4f31980d69aefab727427ded2", "submitted_at": "2025-05-08T08:00:32Z", "updated_at": "2026-06-04T06:58:13Z", "version": 5, "versioned_url": "https://arxiv.org/abs/2505.05026v5"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T07:57:47Z", "role": "primary", "sha256": "27144160e8981bb9f36b60c391689774913ff3f026eeeffc2923154c404a6529", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2504.03206%2C2504.03601%2C2504.06821%2C2504.09723%2C2504.11301%2C2504.11543%2C2504.12609%2C2504.14233%2C2504.14348%2C2504.14603%2C2504.16073%2C2504.16419%2C2504.17892%2C2504.18580%2C2504.20965%2C2505.00019%2C2505.00693%2C2505.01578%2C2505.02094%2C2505.03570%2C2505.03574%2C2505.05026%2C2505.05849%2C2505.06507%2C2505.07003%2C2505.07473%2C2505.10468%2C2505.10887%2C2505.12053%2C2505.12490%2C2505.12728%2C2505.13291%2C2505.14030%2C2505.14454%2C2505.14646%2C2505.15801%2C2505.15816%2C2505.17020%2C2505.18746%2C2505.19095%2C2505.19713%2C2505.20023%2C2505.20732%2C2505.20795%2C2505.21055%2C2505.22304%2C2505.22429%2C2505.23450%2C2505.23559%2C2506.00641&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:20:21Z", "role": "primary", "sha256": "1220bb1498a7f9c68cff0fbbd8eee209dfed138e771dfd6eb946fc0639c49cd1", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "url": "https://arxiv.org/abs/2505.05026v5"}], "id": "arxiv:2505.05026", "identifiers": {"arxiv": "2505.05026"}, "kind": "paper", "last_verified_at": "2026-10-17T11:20:21Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2505.05026"}], "name": "Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding", "notes": "Reviewed against the exact-version official arXiv abstract page; its complete title, ordered author list, visible version, and normalized abstract SHA match the retained snapshot. The original API response body was not locally available. Experimental results and artifact availability have not been independently reproduced. This benchmark measures UI/UX design understanding from static image pairs; it does not measure autonomous GUI action execution.", "published_at": "2025-05-08", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Introduces WiserUI-Bench, pairing real UI variants from industry A/B tests with observed behavioral winners and expert explanations. It evaluates models’ ability to predict the more effective interface and explain its effect on user behavior.", "topics": ["screen-understanding", "ui-design", "evaluation"], "updated_at": "2026-06-04", "url": "https://arxiv.org/abs/2505.05026"}
{"aliases": [], "authors": ["Joel Nitu", "Heidrun Mühle", "Andreas Stöckl"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9fe2d9d877a0666d46a065bd8b673c282c879ef0a2620e3b267793a91858b519", "submitted_at": "2025-07-17T07:10:27Z", "updated_at": "2025-11-12T13:34:24Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2507.12844v2"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "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=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:50Z", "role": "primary", "sha256": "26fb4922c4c0bb5c9069935ed0aef0a9f56938cf8ae1af9724894fa1409955fb", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "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=600&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2507.12844", "identifiers": {"arxiv": "2507.12844"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:50Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2507.12844"}], "name": "Machine-Readable Ads: Accessibility and Trust Patterns for AI Web Agents interacting with Online Advertisements", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2025-07-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "Compares DOM-based and pixel-based web agents on a cloned news site containing advertisements, consent dialogs and paywalls. The study examines how interface presentation affects ad interaction and consequential subscription choices.", "topics": ["evaluation", "ui-design", "safety-security"], "updated_at": "2025-11-12", "url": "https://arxiv.org/abs/2507.12844"}
{"aliases": [], "authors": ["Longjie Guo", "Chenjie Yuan", "Mingyuan Zhong", "Robert Wolfe", "Ruican Zhong", "Yue Xu", "Bingbing Wen", "Hua Shen", "Lucy Lu Wang", "Alexis Hiniker"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e6152a61f81c435e76a432bc10086827c0cf0d2f44026bac03d6b80ebae8ca77", "submitted_at": "2025-10-13T06:12:03Z", "updated_at": "2026-02-23T08:31:13Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.11035v2"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "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=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "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=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2510.11035", "identifiers": {"arxiv": "2510.11035"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.11035"}], "name": "SusBench: An Online Benchmark for Evaluating Dark Pattern Susceptibility of Computer-Use Agents", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2025-10-13", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces SusBench, an online benchmark that inserts dark-pattern designs into consumer websites for agent evaluation. A human study checks the realism of the interventions, and agent trials compare susceptibility across pattern types.", "topics": ["ui-design", "safety-security", "evaluation"], "updated_at": "2026-02-23", "url": "https://arxiv.org/abs/2510.11035"}
{"aliases": [], "authors": ["Devin Ersoy", "Brandon Lee", "Ananth Shreekumar", "Arjun Arunasalam", "Muhammad Ibrahim", "Antonio Bianchi", "Z. Berkay Celik"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "db3c25ba55221ca3d7c45ce4243a4a37b56a698909c0ea3eaaabdcd37388a1ec", "submitted_at": "2025-10-20T21:26:26Z", "updated_at": "2025-10-20T21:26:26Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2510.18113v1"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "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=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "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=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2510.18113", "identifiers": {"arxiv": "2510.18113"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2510.18113"}], "name": "Investigating the Impact of Dark Patterns on LLM-Based Web Agents", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2025-10-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "Presents LiteAgent for recording web-agent interactions and TrickyArena for enabling or disabling dark patterns in controlled websites. Experiments compare how individual patterns, combined patterns and visual or HTML changes affect agent decisions.", "topics": ["safety-security", "ui-design", "evaluation"], "updated_at": "2025-10-20", "url": "https://arxiv.org/abs/2510.18113"}
{"aliases": [], "authors": ["Kevin Qinghong Lin", "Siyuan Hu", "Linjie Li", "Zhengyuan Yang", "Lijuan Wang", "Philip Torr", "Mike Zheng Shou"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7d63831bc0ff00979615415ce94abc140b646a4375cb33b950c4a7ccf00bf166", "submitted_at": "2025-11-19T16:00:02Z", "updated_at": "2025-11-19T16:00:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.15567v1"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "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=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "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=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2511.15567", "identifiers": {"arxiv": "2511.15567"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2511.15567"}], "name": "Computer-Use Agents as Judges for Generative User Interface", "notes": "The annotation was reviewed against the complete retained primary abstract. Experiments and released artifacts have not been independently reproduced.", "published_at": "2025-11-19", "relations": [], "review_status": "curated", "scope": "core", "summary": "AUI-Gym evaluates generated websites by having computer-use agents attempt tasks whose executability is checked programmatically. A feedback dashboard condenses navigation histories into visual summaries that a coding agent can use to revise an interface.", "topics": ["evaluation", "ui-design", "observability"], "updated_at": "2025-11-19", "url": "https://arxiv.org/abs/2511.15567"}
{"aliases": [], "authors": ["Karolina Korgul", "Yushi Yang", "Arkadiusz Drohomirecki", "Piotr Błaszczyk", "Will Howard", "Lukas Aichberger", "Chris Russell", "Philip H. S. Torr", "Adam Mahdi", "Adel Bibi"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "a255cccbe3f16f498918126724c391911e1d745c093189790cbab715fd28a2d2", "submitted_at": "2025-12-29T01:09:10Z", "updated_at": "2026-07-02T16:12:04Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2512.23128v3"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "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=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:47Z", "role": "primary", "sha256": "ae98e77b8bb125e45277aacec768a047e7bb0e13f33ca9ff6ca7c19e29e56cca", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "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=500&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2512.23128", "identifiers": {"arxiv": "2512.23128"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:47Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2512.23128"}], "name": "It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2025-12-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces TRAP, which evaluates task-redirection attacks embedded in realistic web interfaces. Controlled website clones and a modular injection framework support comparisons of persuasion techniques and contextual changes across agents.", "topics": ["safety-security", "evaluation", "ui-design"], "updated_at": "2026-07-02", "url": "https://arxiv.org/abs/2512.23128"}
{"aliases": [], "authors": ["Simret Araya Gebreegziabher", "Yukun Yang", "Charles Chiang", "Hojun Yoo", "Chaoran Chen", "Hyo Jin Do", "Zahra Ashktorab", "Werner Geyer", "Diego Gómez-Zará", "Toby Jia-Jun Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1bdc29648446cd79e0c0b9f72814457b55258d501283ce2fa2dedcd8262f885b", "submitted_at": "2026-01-22T22:42:40Z", "updated_at": "2026-01-22T22:42:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.16356v1"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "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=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "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=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2601.16356", "identifiers": {"arxiv": "2601.16356"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2601.16356"}], "name": "The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-01-22", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces a controlled web-task testbed for studying how stated preferences and human values influence GUI-agent decisions. It analyzes how personas alter navigation and how prominent interface cues can override the intended preference guidance.", "topics": ["evaluation", "ui-design", "human-in-the-loop"], "updated_at": "2026-01-22", "url": "https://arxiv.org/abs/2601.16356"}
{"aliases": [], "authors": ["Kuai Yu", "Naicheng Yu", "Han Wang", "Rui Yang", "Huan Zhang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "1380697158d3a91334427cf067f3f91a751bd89d31103edecfa68171b28b8d66", "submitted_at": "2026-01-29T16:40:15Z", "updated_at": "2026-02-27T16:47:40Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.21961v2"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "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=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "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=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2601.21961", "identifiers": {"arxiv": "2601.21961"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2601.21961"}], "name": "How do Visual Attributes Influence Web Agents? A Comprehensive Evaluation of User Interface Design Factors", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-01-29", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces VAF, a controlled pipeline that varies webpage appearance while retaining item semantics. It measures both agent clicks and reasoning references to study which visual design factors change browsing decisions.", "topics": ["ui-design", "evaluation", "web-navigation"], "updated_at": "2026-02-27", "url": "https://arxiv.org/abs/2601.21961"}
{"aliases": [], "authors": ["Ruijia Cheng", "Jenny T. Liang", "Eldon Schoop", "Jeffrey Nichols"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d556ebbfbf4fc5875395b449a92b8ff27a7ed59d41bc062ac60fcf175f9064f8", "submitted_at": "2026-02-07T00:19:08Z", "updated_at": "2026-02-07T00:19:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.07283v1"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "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=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "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=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2602.07283", "identifiers": {"arxiv": "2602.07283"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2602.07283"}], "name": "Mapping the Design Space of User Experience for Computer Use Agents", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-02-07", "relations": [], "review_status": "curated", "scope": "core", "summary": "Develops a taxonomy of computer-use-agent interaction design through system review and practitioner interviews. A Wizard-of-Oz study then examines how users respond to normal, erroneous, and risky web-based execution, focusing on control, explanation, prompts, and mental models.", "topics": ["human-in-the-loop", "ui-design", "evaluation"], "updated_at": "2026-02-07", "url": "https://arxiv.org/abs/2602.07283"}
{"aliases": [], "authors": ["Alexandre De Masi"], "details": {"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"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:16Z", "role": "primary", "sha256": "9289bc047b59e93f75703b72f5e92d9277e115238427519c343df550220e351b", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2602.19870%2C2602.22769%2C2602.23166%2C2602.23320%2C2603.00198%2C2603.00842%2C2603.00991%2C2603.01050%2C2603.01145%2C2603.02236%2C2603.02795%2C2603.03278%2C2603.04549%2C2603.06713%2C2603.07106%2C2603.07670%2C2603.07853%2C2603.08706%2C2603.09716%2C2603.10002%2C2603.10664%2C2603.11139%2C2603.11320%2C2603.12483%2C2603.13026%2C2603.13247%2C2603.15714%2C2603.16065%2C2603.16289%2C2603.16839%2C2603.17216%2C2603.17378%2C2603.19313%2C2603.19685%2C2603.21489%2C2603.22527%2C2603.23638%2C2603.24157%2C2603.24639%2C2603.27646%2C2603.28069%2C2603.28407%2C2603.29418%2C2603.29847%2C2604.00528%2C2604.00886%2C2604.01194%2C2604.01438%2C2604.01560%2C2604.02985&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:16Z", "role": "primary", "sha256": "9289bc047b59e93f75703b72f5e92d9277e115238427519c343df550220e351b", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2602.19870%2C2602.22769%2C2602.23166%2C2602.23320%2C2603.00198%2C2603.00842%2C2603.00991%2C2603.01050%2C2603.01145%2C2603.02236%2C2603.02795%2C2603.03278%2C2603.04549%2C2603.06713%2C2603.07106%2C2603.07670%2C2603.07853%2C2603.08706%2C2603.09716%2C2603.10002%2C2603.10664%2C2603.11139%2C2603.11320%2C2603.12483%2C2603.13026%2C2603.13247%2C2603.15714%2C2603.16065%2C2603.16289%2C2603.16839%2C2603.17216%2C2603.17378%2C2603.19313%2C2603.19685%2C2603.21489%2C2603.22527%2C2603.23638%2C2603.24157%2C2603.24639%2C2603.27646%2C2603.28069%2C2603.28407%2C2603.29418%2C2603.29847%2C2604.00528%2C2604.00886%2C2604.01194%2C2604.01438%2C2604.01560%2C2604.02985&max_results=50"}], "id": "arxiv:2603.10664", "identifiers": {"arxiv": "2603.10664"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:16Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2603.10664"}], "name": "Terminal Is All You Need: Design Properties for Human-AI Agent Collaboration", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified. Adjacent conceptual HCI work about agent-facing interfaces; the abstract does not report GUI task experiments or a new evaluated CUA.", "published_at": "2026-03-11", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "This position paper derives interface design principles from terminal-based human-agent collaboration: representational compatibility, transparent actions and low participation barriers. It argues that graphical and other agent-facing modalities should provide these properties explicitly.", "topics": ["human-in-the-loop", "ui-design", "observability", "tool-integration"], "updated_at": "2026-03-11", "url": "https://arxiv.org/abs/2603.10664"}
{"aliases": [], "authors": ["Wee Joe Tan", "Zi Rui Lucas Lim", "Shashank Durgad", "Karim Obegi", "Aiden Yiliu Li"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "445e520a60e0e3cc0c3c519e21bfa8eebfa33d4fe4320c437e67b94a02d84504", "submitted_at": "2026-02-25T18:59:42Z", "updated_at": "2026-04-14T20:54:46Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2604.09581v2"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "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=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:43Z", "role": "primary", "sha256": "c432f419481a105a8ce71174ec4aea23c4f0d36ddf89cfe1d0974fa349f6cb59", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "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=400&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2604.09581", "identifiers": {"arxiv": "2604.09581"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:43Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.09581"}], "name": "Avenir-UX: Automated UX Evaluation via Simulated Human Web Interaction with GUI Grounding", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-02-25", "relations": [], "review_status": "curated", "scope": "core", "summary": "Avenir-UX combines grounded web interaction with simulated user profiles and structured usability measures to produce evaluations of website journeys. The paper describes its architecture and use of SUS, step-wise ease questions and think-aloud traces for automated UX reporting.", "topics": ["automation", "evaluation", "ui-design", "grounding"], "updated_at": "2026-04-14", "url": "https://arxiv.org/abs/2604.09581"}
{"aliases": [], "authors": ["Pan Hao", "Rishi Selvakumaran", "Jacob Sun", "Qianwen Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bd3b5e5b9a607023c82150673255eaf2f90c22db86d3c049b2a2fd536aaef17f", "submitted_at": "2026-04-16T06:22:48Z", "updated_at": "2026-04-16T06:22:48Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.14668v1"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "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=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "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=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2604.14668", "identifiers": {"arxiv": "2604.14668"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:39Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.14668"}], "name": "Beyond Chat and Clicks: GUI Agents for In-Situ Assistance via Live Interface Transformation", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experiments, reported performance and artifact availability have not been independently reproduced.", "published_at": "2026-04-16", "relations": [], "review_status": "curated", "scope": "core", "summary": "DOMSteer translates help requests and live page context into reversible DOM changes such as control highlighting, contextual tooltips and layout reorganization. The work evaluates in-place GUI assistance with interface tests, use cases and a comparative user study.", "topics": ["human-in-the-loop", "ui-design", "grounding", "evaluation"], "updated_at": "2026-04-16", "url": "https://arxiv.org/abs/2604.14668"}
{"aliases": [], "authors": ["Zhiyuan Peng", "Wei Tao", "Xin Yin", "Chenhao Ying", "Yuan Luo", "Yiwen Guo"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "74ec7a508a815781cc7e721aa6c5e351f086f6cab46da48e22c2b58f52af8ce0", "submitted_at": "2026-04-21T17:59:16Z", "updated_at": "2026-09-29T10:11:48Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2604.19742v2"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:19Z", "role": "primary", "sha256": "05ec5d668ac75d3d7c5b71ea7d6e76a3fbf5ebeb742e0843db2329e5e41aa208", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2604.03598%2C2604.04759%2C2604.05547%2C2604.06170%2C2604.07340%2C2604.10547%2C2604.10938%2C2604.11978%2C2604.12282%2C2604.13018%2C2604.13346%2C2604.13954%2C2604.15579%2C2604.15671%2C2604.15715%2C2604.16520%2C2604.18240%2C2604.18934%2C2604.19572%2C2604.19667%2C2604.19742%2C2604.20841%2C2604.20987%2C2604.22436%2C2604.23781%2C2604.24479%2C2604.26148%2C2604.27621%2C2604.27996%2C2604.28093%2C2604.28139%2C2604.28181%2C2605.00425%2C2605.01462%2C2605.02240%2C2605.03042%2C2605.03242%2C2605.04811%2C2605.05191%2C2605.05811%2C2605.06110%2C2605.07073%2C2605.07358%2C2605.08374%2C2605.08985%2C2605.10912%2C2605.10966%2C2605.11363%2C2605.11732%2C2605.11817&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:19Z", "role": "primary", "sha256": "05ec5d668ac75d3d7c5b71ea7d6e76a3fbf5ebeb742e0843db2329e5e41aa208", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2604.03598%2C2604.04759%2C2604.05547%2C2604.06170%2C2604.07340%2C2604.10547%2C2604.10938%2C2604.11978%2C2604.12282%2C2604.13018%2C2604.13346%2C2604.13954%2C2604.15579%2C2604.15671%2C2604.15715%2C2604.16520%2C2604.18240%2C2604.18934%2C2604.19572%2C2604.19667%2C2604.19742%2C2604.20841%2C2604.20987%2C2604.22436%2C2604.23781%2C2604.24479%2C2604.26148%2C2604.27621%2C2604.27996%2C2604.28093%2C2604.28139%2C2604.28181%2C2605.00425%2C2605.01462%2C2605.02240%2C2605.03042%2C2605.03242%2C2605.04811%2C2605.05191%2C2605.05811%2C2605.06110%2C2605.07073%2C2605.07358%2C2605.08374%2C2605.08985%2C2605.10912%2C2605.10966%2C2605.11363%2C2605.11732%2C2605.11817&max_results=50"}], "id": "arxiv:2604.19742", "identifiers": {"arxiv": "2604.19742"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:19Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.19742"}], "name": "PlayCoder: Making LLM-Generated GUI Code Playable", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified.", "published_at": "2026-04-21", "relations": [], "review_status": "curated", "scope": "core", "summary": "PlayEval measures whether generated GUI applications remain logically playable, using PlayTester to execute task-oriented GUI playthroughs. PlayCoder closes the loop between repository-aware generation, interactive testing and targeted code repair.", "topics": ["evaluation", "automation", "ui-design", "workflow"], "updated_at": "2026-09-29", "url": "https://arxiv.org/abs/2604.19742"}
{"aliases": [], "authors": ["Alice Gao", "Weixi Tong", "Rishab Vempati", "Katharina Reinecke", "R. Benjamin Shapiro", "Tianyi Zhang", "Jason Wu"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bb6d24f7dc38921da883c4850b37f1c7eb48a03de920356d4ec2e095dbb44b04", "submitted_at": "2026-04-28T18:04:11Z", "updated_at": "2026-04-28T18:04:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.26020v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "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=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:39Z", "role": "primary", "sha256": "27c33576ed43c7bc63d4b290f6558553bd1d3aa112a7358138f4045e1bc14918", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "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=300&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2604.26020", "identifiers": {"arxiv": "2604.26020"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:39Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.26020"}], "name": "Training Computer Use Agents to Assess the Usability of Graphical User Interfaces", "notes": "The annotation was reviewed against the complete retained official abstract. Experimental findings and artifact availability have not been independently reproduced.", "published_at": "2026-04-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "uxCUA learns to assess interface usability by choosing interaction flows, executing them and predicting a numerical usability score. Training uses interactive UIs with usability labels and human preferences, with evaluations on synthetic and real interfaces.", "topics": ["ui-design", "evaluation", "automation"], "updated_at": "2026-04-28", "url": "https://arxiv.org/abs/2604.26020"}
{"aliases": [], "authors": ["Chen Liang", "Xirui Jiang", "Naihao Deng", "Eytan Adar", "Anhong Guo"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "5b572e37eefab40a6a21fa4e4589324380ad9f66873a4da5746fc0f46aaeb1f6", "submitted_at": "2026-04-28T22:15:06Z", "updated_at": "2026-08-11T15:48:53Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2604.26148v3"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:19Z", "role": "primary", "sha256": "05ec5d668ac75d3d7c5b71ea7d6e76a3fbf5ebeb742e0843db2329e5e41aa208", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2604.03598%2C2604.04759%2C2604.05547%2C2604.06170%2C2604.07340%2C2604.10547%2C2604.10938%2C2604.11978%2C2604.12282%2C2604.13018%2C2604.13346%2C2604.13954%2C2604.15579%2C2604.15671%2C2604.15715%2C2604.16520%2C2604.18240%2C2604.18934%2C2604.19572%2C2604.19667%2C2604.19742%2C2604.20841%2C2604.20987%2C2604.22436%2C2604.23781%2C2604.24479%2C2604.26148%2C2604.27621%2C2604.27996%2C2604.28093%2C2604.28139%2C2604.28181%2C2605.00425%2C2605.01462%2C2605.02240%2C2605.03042%2C2605.03242%2C2605.04811%2C2605.05191%2C2605.05811%2C2605.06110%2C2605.07073%2C2605.07358%2C2605.08374%2C2605.08985%2C2605.10912%2C2605.10966%2C2605.11363%2C2605.11732%2C2605.11817&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:19Z", "role": "primary", "sha256": "05ec5d668ac75d3d7c5b71ea7d6e76a3fbf5ebeb742e0843db2329e5e41aa208", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2604.03598%2C2604.04759%2C2604.05547%2C2604.06170%2C2604.07340%2C2604.10547%2C2604.10938%2C2604.11978%2C2604.12282%2C2604.13018%2C2604.13346%2C2604.13954%2C2604.15579%2C2604.15671%2C2604.15715%2C2604.16520%2C2604.18240%2C2604.18934%2C2604.19572%2C2604.19667%2C2604.19742%2C2604.20841%2C2604.20987%2C2604.22436%2C2604.23781%2C2604.24479%2C2604.26148%2C2604.27621%2C2604.27996%2C2604.28093%2C2604.28139%2C2604.28181%2C2605.00425%2C2605.01462%2C2605.02240%2C2605.03042%2C2605.03242%2C2605.04811%2C2605.05191%2C2605.05811%2C2605.06110%2C2605.07073%2C2605.07358%2C2605.08374%2C2605.08985%2C2605.10912%2C2605.10966%2C2605.11363%2C2605.11732%2C2605.11817&max_results=50"}], "id": "arxiv:2604.26148", "identifiers": {"arxiv": "2604.26148"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:19Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2604.26148"}], "name": "Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified.", "published_at": "2026-04-28", "relations": [], "review_status": "curated", "scope": "core", "summary": "AniMINT evaluates how VLMs perceive, explain and interpret UI animations using densely annotated videos. The study distinguishes basic motion recognition from higher-level animation meaning and probes motion, context and perceptual cues.", "topics": ["evaluation", "screen-understanding", "video", "ui-design"], "updated_at": "2026-08-11", "url": "https://arxiv.org/abs/2604.26148"}
{"aliases": [], "authors": ["JunJia Guo", "Yuhang Yao", "Chang Li", "Zimeng Pan", "Jiawei", "Zhou", "Jingdi Chen"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "64f8e09fc62f080a75aec1928b82187063cfc3ad8467290608347622410b6460", "submitted_at": "2026-05-22T20:29:12Z", "updated_at": "2026-09-29T00:12:17Z", "version": 4, "versioned_url": "https://arxiv.org/abs/2605.26144v4"}}, "environments": ["web", "android"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-17T12:31:23Z", "role": "primary", "sha256": "9a71e95803ce58c462c84e2b45a891555e31d1fb409e643bb3ca4675a44c96e6", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?id_list=2605.12233%2C2605.12493%2C2605.12978%2C2605.13119%2C2605.14133%2C2605.16909%2C2605.17260%2C2605.17324%2C2605.17448%2C2605.17656%2C2605.17721%2C2605.19447%2C2605.19587%2C2605.20894%2C2605.22642%2C2605.23204%2C2605.25233%2C2605.25901%2C2605.26086%2C2605.26144%2C2605.26252%2C2605.26646%2C2605.27209%2C2605.27705%2C2605.27898%2C2605.28158%2C2605.28255%2C2605.29341%2C2605.29463%2C2605.29801%2C2605.30010%2C2605.30052%2C2605.30126%2C2605.30434%2C2605.30907%2C2605.30914%2C2605.31264%2C2605.31557%2C2606.00530%2C2606.00543%2C2606.00856%2C2606.01057%2C2606.01961%2C2606.02540%2C2606.03103%2C2606.03889%2C2606.03895%2C2606.04315%2C2606.04455%2C2606.05525&max_results=50"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:31:23Z", "role": "primary", "sha256": "9a71e95803ce58c462c84e2b45a891555e31d1fb409e643bb3ca4675a44c96e6", "supports": ["name", "kind", "summary", "environments", "topics", "scope"], "url": "https://export.arxiv.org/api/query?id_list=2605.12233%2C2605.12493%2C2605.12978%2C2605.13119%2C2605.14133%2C2605.16909%2C2605.17260%2C2605.17324%2C2605.17448%2C2605.17656%2C2605.17721%2C2605.19447%2C2605.19587%2C2605.20894%2C2605.22642%2C2605.23204%2C2605.25233%2C2605.25901%2C2605.26086%2C2605.26144%2C2605.26252%2C2605.26646%2C2605.27209%2C2605.27705%2C2605.27898%2C2605.28158%2C2605.28255%2C2605.29341%2C2605.29463%2C2605.29801%2C2605.30010%2C2605.30052%2C2605.30126%2C2605.30434%2C2605.30907%2C2605.30914%2C2605.31264%2C2605.31557%2C2606.00530%2C2606.00543%2C2606.00856%2C2606.01057%2C2606.01961%2C2606.02540%2C2606.03103%2C2606.03889%2C2606.03895%2C2606.04315%2C2606.04455%2C2606.05525&max_results=50"}], "id": "arxiv:2605.26144", "identifiers": {"arxiv": "2605.26144"}, "kind": "paper", "last_verified_at": "2026-10-17T12:31:23Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2605.26144"}], "name": "VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents", "notes": "Reviewed against the complete retained official abstract. Experimental findings and release availability have not been independently reproduced or verified. Adjacent GUI-application generation benchmark with real component interaction probes; its main evaluated agents are application coders, not general GUI task executors.", "published_at": "2026-05-22", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "VISTA evaluates coding agents that turn design handoffs into working web and Android applications. Its evaluator locates annotated interactive components and probes their behavior, keeping visual localization distinct from functional correctness.", "topics": ["evaluation", "ui-design", "automation"], "updated_at": "2026-09-29", "url": "https://arxiv.org/abs/2605.26144"}
{"aliases": [], "authors": ["Lily Bundgaard Wanscher", "Markus Heidemann Lorensen", "Mohammed Ammad Shafiq", "Mahyar Tourchi Moghaddam", "Mina Alipour"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "046d93a43dd5a011809a780c7d998f98ee0abb3e931d733b8ad7807b86050ec7", "submitted_at": "2026-07-26T17:21:24Z", "updated_at": "2026-07-26T17:21:24Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.24913v1"}}, "environments": ["web"], "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"}], "id": "arxiv:2608.24913", "identifiers": {"arxiv": "2608.24913"}, "kind": "paper", "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/2608.24913"}], "name": "From Blind Edits to Verified Repair: Building Trustworthy User-Side LLM Agents for Web Accessibility", "notes": "The annotation and scope were reviewed against the primary paper abstract. Experimental results and released artifacts have not been independently reproduced.", "published_at": "2026-07-26", "relations": [], "review_status": "curated", "scope": "core", "summary": "Builds a local browser-extension agent that generates and verifies additive CSS repairs for WCAG web accessibility violations.", "topics": ["ui-design", "web-navigation", "safety-security"], "updated_at": "2026-07-26", "url": "https://arxiv.org/abs/2608.24913"}
{"aliases": [], "authors": ["Haya Halimeh", "Sascha Kaltenpoth", "Kevin Bösch", "Oliver Müller"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "70a7588abcf345418ed759fb2bdb96fc60c6e1444a3e0dc98766510c755f8478", "submitted_at": "2026-09-17T07:54:15Z", "updated_at": "2026-09-17T07:54:15Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.19843v1"}}, "environments": ["unspecified"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "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=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:29Z", "role": "primary", "sha256": "74e521e46c46489e48f9bad5d774625a85b5ccd32828969fd98e1a4c453b899f", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes"], "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=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2609.19843", "identifiers": {"arxiv": "2609.19843"}, "kind": "paper", "last_verified_at": "2026-10-16T06:36:29Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.19843"}], "name": "A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents", "notes": "The annotation and scope were reviewed against the complete retained original arXiv abstract. Experiments, reported performance and artifact availability have not been independently reproduced.", "published_at": "2026-09-17", "relations": [], "review_status": "curated", "scope": "core", "summary": "Studies how automatic defaults and reflective social-influence cues affect GUI-agent shopping decisions under different reasoning configurations. A randomized simulated-shopping experiment finds that reasoning changes the type of susceptibility rather than uniformly removing interface influence.", "topics": ["safety-security", "evaluation", "ui-design", "robustness"], "updated_at": "2026-09-17", "url": "https://arxiv.org/abs/2609.19843"}
{"aliases": [], "authors": ["Kiana Hooshanfar", "Amirhossein Kazerouni", "Alireza Hosseini", "Michael Brudno", "Babak Taati"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9ce76f34abe391289643321027a33ac3cac8b5bd64eaa901f9a5fbf7c5561362", "submitted_at": "2026-09-25T14:59:14Z", "updated_at": "2026-09-25T14:59:14Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.31364v1"}, "license_review": {"document": {"evidence_urls": ["https://arxiv.org/html/2609.31364v1"], "reason": "Document declaration only. The paper does not establish code, model-weight or underlying dataset permissions through this license."}}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-20T15:06:37Z", "role": "primary", "sha256": "a3d753815e82190ee2de6f322cd816c32f2dd391f862845305fc7e57300303a6", "supports": ["name", "authors", "published_at", "updated_at", "identifiers.arxiv", "details.arxiv_snapshot"], "url": "https://export.arxiv.org/api/query?search_query=%28abs%3A%22desktop+agent%22+OR+abs%3A%22computer+interaction%22+OR+abs%3A%22GUI+automation%22+OR+abs%3A%22web+navigation%22+OR+abs%3A%22browser+automation%22+OR+abs%3A%22visual+grounding%22+OR+abs%3A%22screen+understanding%22+OR+abs%3A%22mobile+agents%22%29+AND+submittedDate%3A%5B202609200000+TO+202610200000%5D&start=0&max_results=200&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-20T19:01:29.156954Z", "role": "primary", "sha256": "cd4ba28778b725c63f4a7329f683b2a287db2e46ed228a0d47006fcd95bbce80", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "notes", "licenses.document"], "url": "https://arxiv.org/html/2609.31364v1"}], "id": "arxiv:2609.31364", "identifiers": {"arxiv": "2609.31364"}, "kind": "paper", "last_verified_at": "2026-10-20T19:01:29.156954Z", "licenses": {"code": null, "data": null, "document": {"basis": "The exact-v1 arXiv HTML infobox (#license-tr) declares License: CC BY 4.0 for this paper document.", "declared": "CC-BY-4.0", "retrieved_at": "2026-10-20T19:01:29.156954Z", "url": "https://arxiv.org/html/2609.31364v1"}, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2609.31364"}], "name": "OpenVAM: Open-World Visual Attention Modeling with VLMs", "notes": "Static human-attention modeling on U-EYE webpage screenshots, with FIWI held out from training; no live-browser, agent-action or task-success evaluation. Gemini-generated reference rationales are expert-checked, and JScore compares generated text with references; human validation covers a separate 100-image subset. Reference text and heatmap alignment do not establish causal explanations of gaze or temporal scanpaths. Several baseline scores come from prior papers. Code/data/weight releases and licenses were not verified; no independent reproduction.", "published_at": "2026-09-25", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Combines dense saliency prediction with explanations of attended elements, including webpage layouts; evaluates human-attention agreement and textual rationales rather than agent actions.", "topics": ["screen-understanding", "ui-design", "evaluation", "data-generation"], "updated_at": "2026-09-25", "url": "https://arxiv.org/abs/2609.31364"}
{"aliases": [], "authors": ["Yun-Yun Tsai", "Yuning Mao", "Shiqi Wang", "Junfeng Yang", "Sinong Wang"], "details": {"arxiv_snapshot": {"abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7ed117876ece99f55e241e6365d0e785b907f9a7a24cceb01b1fd757191a35c9", "submitted_at": "2026-10-02T00:17:11Z", "updated_at": "2026-10-02T00:17:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.02617v1"}}, "environments": ["web"], "evidence": [{"method": "arxiv_api", "retrieved_at": "2026-10-18T10:00:31.520084+00:00", "role": "primary", "sha256": "f053c4c65f6443acbda26e25cf36f7b6e8ea45f2916535604229f7c4e62ed679", "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+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-18T10:00:31.520084+00:00", "role": "primary", "sha256": "f053c4c65f6443acbda26e25cf36f7b6e8ea45f2916535604229f7c4e62ed679", "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+OR+ti%3A%22mobile+agent%22+OR+ti%3A%22UI+agent%22+OR+ti%3A%22desktop+agent%22+OR+ti%3A%22screen+grounding%22%29+AND+submittedDate%3A%5B200001010000+TO+202610180000%5D&start=0&max_results=100&sortBy=submittedDate&sortOrder=descending"}], "id": "arxiv:2610.02617", "identifiers": {"arxiv": "2610.02617"}, "kind": "paper", "last_verified_at": "2026-10-18T10:00:31.520084+00:00", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://arxiv.org/abs/2610.02617"}], "name": "WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness", "notes": "Adjacent evaluation infrastructure: the target is generated WebUI functionality, not a general score for computer-use agents. This annotation is based on the complete retained abstract; released artifacts and experimental results were not independently inspected or reproduced.", "published_at": "2026-10-02", "relations": [], "review_status": "curated", "scope": "adjacent", "summary": "Introduces an execution-based benchmark for generated web interfaces, with a headless-browser UI-agent harness that checks DOM interactions and functional assertions.", "topics": ["evaluation", "web-navigation", "ui-design"], "updated_at": "2026-10-02", "url": "https://arxiv.org/abs/2610.02617"}
{"aliases": [], "authors": [], "details": {"dataset_profile": {"counts": [{"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/uicrit/HEAD/README.md", "population": "current three-annotator release", "qualifier": "exact", "unit": "mobile UI screens", "value": 1000}, {"basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/uicrit/HEAD/README.md", "population": "current three-annotator release", "qualifier": "exact", "unit": "design critiques", "value": 11344}], "evidence_urls": ["https://raw.githubusercontent.com/google-research-datasets/uicrit/HEAD/README.md"], "formats": ["CSV"], "modalities": ["text", "bounding boxes", "quality ratings"], "notes": "Publisher-reported current release, separate from the smaller original-paper population. Screenshot pixels are obtained through referenced RICO IDs.", "splits": [], "supervision": ["design critique", "region localization", "quality rating"]}}, "environments": ["unspecified"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:45Z", "role": "primary", "sha256": "345ff7003120f146016741099dd57b9b1a9ffc54ce1fc90f4d16d61e31d379e6", "supports": ["name", "kind", "summary", "environments", "topics", "scope", "relations", "details"], "url": "https://raw.githubusercontent.com/google-research-datasets/uicrit/HEAD/README.md"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:45Z", "role": "primary", "sha256": "5579bbbc622a2f9fa1f77b509c1ece17af023b8c14b53aa48dcc41288a5852f2", "supports": ["identity"], "url": "https://api.github.com/repos/google-research-datasets/uicrit"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:45Z", "role": "primary", "sha256": "8e790a53de8c40aa14f9e49aebf42b077e6a172a6841f38c7c6851af57b0617a", "supports": ["release_status"], "url": "https://api.github.com/repos/google-research-datasets/uicrit/contents"}], "id": "github:google-research-datasets/uicrit", "identifiers": {}, "kind": "dataset", "last_verified_at": "2026-10-17T02:02:45Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://github.com/google-research-datasets/uicrit"}], "name": "UICrit", "notes": "The published CSV contains critique text, normalized boxes, ratings and RICO IDs; screenshots are referenced through RICO. The README explicitly licenses the work CC-BY-4.0. Its current 1,000-screen, 11,344-critique release differs from the original paper population. The README cites an ACM DOI rather than an arXiv ID, so no paper relation is asserted here. Its README establishes mobile interfaces without naming an operating system.", "published_at": null, "relations": [], "review_status": "curated", "scope": "core", "summary": "Mobile-interface critiques and quality ratings with region coordinates and RICO screen references, including a larger three-annotator release than the original paper dataset.", "topics": ["screen-understanding", "ui-design", "evaluation"], "updated_at": null, "url": "https://github.com/google-research-datasets/uicrit"}
{"aliases": [], "authors": ["Biplab Deka", "Zifeng Huang", "Chad Franzen", "Joshua Hibschman", "Daniel Afergan", "Yang Li", "Jeffrey Nichols", "Ranjitha Kumar"], "details": {"publication": {"authors": ["Biplab Deka", "Zifeng Huang", "Chad Franzen", "Joshua Hibschman", "Daniel Afergan", "Yang Li", "Jeffrey Nichols", "Ranjitha Kumar"], "date_basis": "Supplied day precision: 2017-10-20. PDF cover, Published: 20 October 2017 The 18 January 2026 download date and October 22-25 conference dates are not publication dates.", "date_parts": [2017, 10, 20], "doi": "10.1145/3126594.3126651", "event_dates": null, "evidence_urls": ["https://danafergan.com/publications/deka2017rico.pdf", "https://dev.interactionmining.org/archive/rico"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The paper is a distinct resource from the already cataloged Rico dataset (url:0b134b082a7bd507fc6a). The publisher PDF describes 9.7k apps and 72k screens; the project page describes 9.3k apps and 66k screens. The annotation intentionally supplies no merged size claim. No volume number is supplied for this proceedings article.", "pages": "845-854", "pdf_url": "https://danafergan.com/publications/deka2017rico.pdf", "publisher": null, "series": null, "title": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications", "type": "conference-paper", "url": "https://doi.org/10.1145/3126594.3126651", "venue": "UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology", "volume": null}}, "environments": ["android"], "evidence": [{"method": "editorial_primary_review", "retrieved_at": "2026-10-17T10:01:32Z", "role": "primary", "sha256": "a1ec58c526b152c052c5c72f9a62725f1026b5f0e4f45c8fe85fce284295da84", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue"], "url": "https://danafergan.com/publications/deka2017rico.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:23Z", "role": "primary", "sha256": "fb00401fe531ca3aed078dccc57147bcaad33207dacf7cd4cfd4af14f1487ff5", "supports": ["details.publication.notes"], "url": "https://dev.interactionmining.org/archive/rico"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T10:01:32Z", "role": "primary", "sha256": "a1ec58c526b152c052c5c72f9a62725f1026b5f0e4f45c8fe85fce284295da84", "supports": ["details.publication.authors", "details.publication.date_basis", "details.publication.date_parts", "details.publication.doi", "details.publication.identity_basis", "details.publication.notes", "details.publication.pages", "details.publication.pdf_url", "details.publication.title", "details.publication.type", "details.publication.url", "details.publication.venue", "environments", "kind", "name", "scope", "summary", "topics"], "url": "https://danafergan.com/publications/deka2017rico.pdf"}, {"method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:53:23Z", "role": "primary", "sha256": "fb00401fe531ca3aed078dccc57147bcaad33207dacf7cd4cfd4af14f1487ff5", "supports": ["details.publication.notes"], "url": "https://dev.interactionmining.org/archive/rico"}], "id": "url:b560b5d6abaab98483f6", "identifiers": {"doi": "10.1145/3126594.3126651"}, "kind": "paper", "last_verified_at": "2026-10-17T10:01:32Z", "licenses": {"code": null, "data": null, "document": null, "weights": null}, "links": [{"rel": "primary", "url": "https://doi.org/10.1145/3126594.3126651"}, {"rel": "publication_pdf", "url": "https://danafergan.com/publications/deka2017rico.pdf"}], "name": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications", "notes": "The annotation was reviewed against retained primary publication sources. Experiments have not been independently reproduced. The paper is a distinct resource from the already cataloged Rico dataset (url:0b134b082a7bd507fc6a). The publisher PDF describes 9.7k apps and 72k screens; the project page describes 9.3k apps and 66k screens. The annotation intentionally supplies no merged size claim.", "published_at": "2017-10-20", "relations": [], "review_status": "curated", "scope": "core", "summary": "Introduces Rico, collecting Android interface designs and interaction traces through crowdsourced use followed by automated exploration. The paper demonstrates UI-layout retrieval using learned representations and describes visual, textual, structural, and interaction data.", "topics": ["data-generation", "screen-understanding", "ui-design"], "updated_at": null, "url": "https://doi.org/10.1145/3126594.3126651"}