{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:11:12Z","timestamp":1777889472519,"version":"3.51.4"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02168","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23353-23363","source":"Crossref","is-referenced-by-count":0,"title":["UINavBench: A Framework for Comprehensive Evaluation of Interactive Digital Agents"],"prefix":"10.1109","author":[{"given":"Harsh","family":"Agrawal","sequence":"first","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eldon","family":"Schoop","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinlei","family":"Pan","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anuj","family":"Mahajan","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ari","family":"Seff","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Feng","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruijia","family":"Cheng","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andres Romero Mier Y","family":"Teran","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Esteban","family":"Gomez","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhishek","family":"Sundararajan","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Forrest","family":"Huang","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amanda","family":"Swearngin","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohana Prasad Sathya","family":"Moorthy","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeff","family":"Nichols","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Toshev","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Prescient agents: A Radar O\u2019Reilly for your desktop","author":"McGregor","year":"1991","journal-title":"The X Resource"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/176789.176792"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888900008122"},{"key":"ref4","article-title":"Jennings. Agent theories, architectures, and languages: A survey","volume-title":"ECAI Workshop on Agent Theories, Architectures, and Languages","author":"Wooldridge","year":"1995"},{"key":"ref5","article-title":"GPT-4V(ision) is a generalist web agent, if grounded","author":"Zheng","year":"2024","journal-title":"ICML"},{"key":"ref6","article-title":"A realworld webagent with planning, long context understanding, and program synthesis","author":"Gur","year":"2023","journal-title":"ArXiv"},{"key":"ref7","article-title":"Cogagent: A visual language model for gui agents","author":"Hong","year":"2023","journal-title":"ArXiv"},{"key":"ref8","article-title":"Appagent: Multimodal agents as smartphone users","author":"Zhang","year":"2023","journal-title":"ArXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.371"},{"key":"ref10","article-title":"Mobileagent: Autonomous multi-modal mobile device agent with visual perception","author":"Wang","year":"2024","journal-title":"ArXiv"},{"key":"ref11","volume-title":"Step: Stacked 11 m policies for web actions","author":"Paloma","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649379"},{"key":"ref13","article-title":"Language models can solve computer tasks","author":"Kim","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref14","article-title":"A data-driven approach for learning to control computers","author":"Peter","year":"2022","journal-title":"A data-driven approach for learning to control computers,"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1220"},{"key":"ref16","article-title":"Webshop: Towards scalable real-world web interaction with grounded language agents","author":"Yao","journal-title":"ArXiv, preprint"},{"key":"ref17","article-title":"Webarena: A realistic web environment for building autonomous agents","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.50"},{"key":"ref19","volume-title":"Android in the wild: A largescale dataset for android device control","author":"Rawles","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.702"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.702"},{"key":"ref22","article-title":"On the effects of data scale on computer control agents","author":"Li","year":"2024","journal-title":"ArXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676382"},{"key":"ref24","article-title":"Androidworld: A dynamic benchmarking environment for autonomous agents","author":"Rawles","year":"2024","journal-title":"ArXiv"},{"key":"ref25","article-title":"Mobile-env: an evaluation platform and benchmark for 11 m -gui interaction","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Os-copilot: Towards generalist computer agents with self-improvement","author":"Wu","year":"2024","journal-title":"ArXiv"},{"key":"ref27","volume-title":"Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments","author":"Xie","year":"2024"},{"key":"ref28","volume-title":"Windows agent arena: Evaluating multimodal os agents at scale.","author":"Bonatti","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref30","article-title":"On the effects of data scale on computer control agents","author":"Li","year":"2024","journal-title":"ArXiv"},{"key":"ref31","article-title":"Gui odyssey: A comprehensive dataset for cross-app gui navigation on mobile devices","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Amex: Android multi-annotation expo dataset for mobile gui agents","author":"Chai","year":"2024","journal-title":"ArXiv"},{"key":"ref33","volume-title":"Gpt-4 technical report","year":"2024"},{"key":"ref34","article-title":"React: Synergizing reasoning and acting in language models","author":"Yao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_18"},{"key":"ref37","article-title":"GPT-4V (ision) is a generalist web agent, if grounded","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"GUICourse: From general vision language models to versatile gui agents","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Gui-world: A dataset for gui-oriented multimodal 11 m -based agents","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1113"},{"key":"ref42","article-title":"AgentStudio: A toolkit for building general virtual agents","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zheng","year":"2024"},{"key":"ref43","volume-title":"Windows agent arena: Evaluating multi-modal os agents at scale","author":"Bonatti","year":"2024"},{"key":"ref44","article-title":"Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","volume-title":"Androidworld: A dynamic benchmarking environment for autonomous agents","author":"Rawles","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.850"},{"key":"ref47","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"GPT-4V in wonderland: Large multimodal models for zero-shot smartphone gui navigation","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Omniparser for pure vision based gui agent","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Appagent v2: Advanced agent for flexible mobile interactions","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Appagent: Multimodal agents as smartphone users","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Mobile-agent: Autonomous multi-modal mobile device agent with visual perception","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"OS-ATLAS: A foundation action model for generalist gui agents","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642777"},{"key":"ref55","article-title":"Navigating the digital world as humans do: Universal visual grounding for gui agents","author":"Gou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"OS- Copilot: towards generalist computer agents with self-improvement","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Agent S: An open agentic framework that uses computers like a human","author":"Agashe","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"You only look at screens: Multimodal chain-of-action agents","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref60","article-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices","author":"Chu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Mobilevlm v2: Faster and stronger baseline for vision language model","author":"Chu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Learning From Strangers: The Art and Method of Qualitative Interview Studies","author":"Weiss","year":"1995","journal-title":"Free Press"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139644082"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126651"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445186"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502073"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712153"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref69","article-title":"Navigating the digital world as humans do: Universal visual grounding for GUI agents","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Gou","year":"2025"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"ref71","article-title":"Ui-tars: Pioneering automated gui interaction with native agents","author":"Qin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"ArXiv"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755688"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444249.pdf?arnumber=11444249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:11:36Z","timestamp":1777612296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02168","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}