{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:16:57Z","timestamp":1781623017972,"version":"3.54.5"},"reference-count":47,"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"}],"funder":[{"DOI":"10.13039\/100007270","name":"University of Michigan","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007270","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01859","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19989-19998","source":"Crossref","is-referenced-by-count":1,"title":["Visual Test-Time Scaling for GUI Agent Grounding"],"prefix":"10.1109","author":[{"given":"Tiange","family":"Luo","sequence":"first","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lajanugen","family":"Logeswaran","sequence":"additional","affiliation":[{"name":"LG AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Johnson","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honglak","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","year":"2025","journal-title":"Developing a computer use model"},{"key":"ref3","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3421"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"ref7","first-page":"143","article-title":"The complexity of theorem-proving procedures","author":"Cook","year":"2023","journal-title":"Logic, automata, and computational complexity: The works of Stephen A. Cook"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1220"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00122"},{"key":"ref10","article-title":"Vision-language model for object detection and segmentation: A review and evaluation","author":"Feng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Navigating the digital world as humans do: Universal visual grounding for gui agents","author":"Gou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.371"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1723"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.50"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755688"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755688"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.12968\/pnur.2009.20.7.43180"},{"key":"ref21","article-title":"Visualagentbench: Towards large multimodal models as visual foundation agents","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","author":"Lu","year":"2024","journal-title":"Omniparser for pure vision based gui agent"},{"key":"ref23","article-title":"Recurrent models of visual attention","author":"Mnih","year":"2014","journal-title":"Advances in neural information processing systems, 27"},{"key":"ref24","author":"Murty","year":"2025","journal-title":"Nnetnav: Unsupervised learning of browser agents through environment interaction in the wild"},{"key":"ref25","article-title":"Webgpt: Browser-assisted question-answering with human feedback","author":"Nakano","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Pivot: Iterative visual prompting elicits actionable knowledge for vlms","author":"Nasiriany","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.326"},{"key":"ref28","article-title":"Ui-tars: Pioneering automated gui interaction with native agents","author":"Qin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1490"},{"key":"ref30","article-title":"All roads lead to likelihood: The value of reinforcement learning in fine-tuning","author":"Swamy","year":"2025","journal-title":"arXiv preprint"},{"key":"ref31","author":"Trabucco","year":"2025","journal-title":"Towards internet-scale training for agents"},{"key":"ref32","first-page":"arXiv","article-title":"Learning to stop overthinking at test time","author":"Tran Bao","year":"2025","journal-title":"arXiv e-prints"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0088"},{"key":"ref34","article-title":"Mobile-agent: Autonomous multi-modal mobile device agent with visual perception","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref36","first-page":"52040","article-title":"Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments","volume":"37","author":"Xie","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref38","article-title":"Gpt-4v in wonderland: Large multimodal models for zero-shot smartphone gui navigation","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","author":"Yang","year":"2024","journal-title":"Agentoccam: A simple yet strong baseline for 11 m -based web agents"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1508"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref42","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yao","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3677075"},{"key":"ref44","article-title":"Exact: Teaching ai agents to explore with reflective-mcts and exploratory learning","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"You only look at screens: Multimodal chain-of-action agents","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Gpt-4v (ision) is a generalist web agent, if grounded","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Webarena: A realistic web environment for building autonomous agents","author":"Zhou","year":"2024","journal-title":"ICLR"}],"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\/11444463.pdf?arnumber=11444463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:35Z","timestamp":1777613375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444463\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01859","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}