{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:11Z","timestamp":1777888931616,"version":"3.51.4"},"reference-count":50,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276152"],"award-info":[{"award-number":["62276152"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00457","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4807-4817","source":"Crossref","is-referenced-by-count":0,"title":["How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in an Extensible Escape Game"],"prefix":"10.1109","author":[{"given":"Ziyue","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yurui","family":"Dong","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuwen","family":"Luo","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minyuan","family":"Ruan","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhili","family":"Cheng","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.omtn.2024.102255"},{"key":"ref3","author":"Chen","year":"2024","journal-title":"Can vlms play action role-playing games? take black myth wukong as a study case"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.32"},{"key":"ref5","article-title":"Embodiedeval: Evaluate multimodal 11 ms as embodied agents","author":"Cheng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24337-1_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2024.3497601"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0433"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70415-4_9"},{"key":"ref11","first-page":"1366813677","article-title":"Holistic autonomous driving understanding by bird\u2019s-eye-view injected multi-modal large models","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ding","year":"2024"},{"key":"ref12","article-title":"Palm-e: an embodied multimodal language model","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Driess","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ricai68060.2025.11385173"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3689171"},{"key":"ref15","first-page":"24422448","article-title":"Minerl: a large-scale dataset of minecraft demonstrations","volume-title":"Proceedings of the 28th International Joint Conference on Artificial Intelligence","author":"William","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124603"},{"key":"ref17","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"Kolve","year":"2017","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/0600000110"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01554"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1580"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/452"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref26","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"ArXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0558"},{"key":"ref28","volume-title":"OpenAI. Computer-using agent: Introducing a universal interface for ai to interact with the digital world","year":"2025"},{"key":"ref29","author":"Qian","year":"2024","journal-title":"Escapebench: Pushing language models to think outside the box"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01543"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref33","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","author":"Wang","year":"2025","journal-title":"Mobile-agent-v: Learning mobile device operation through video-guided multi-agent collaboration"},{"key":"ref35","article-title":"Gemini in reasoning: Unveiling commonsense in multimodal large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Exploring the reasoning abilities of multimodal large language models (mllms): A comprehensive survey on emerging trends in multimodal reasoning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Rat: Retrieval augmented thoughts elicit context-aware reasoning and verification in long-horizon generation","volume-title":"NeurIPS 2024 Workshop on Open-World Agents","author":"Wang"},{"key":"ref38","article-title":"Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3511593"},{"key":"ref40","article-title":"Mobile-agente: Self-evolving mobile assistant for complex tasks","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref41","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":"ref42","article-title":"Exploring large language models for communication games: An empirical study on werewolf","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Position: Multimodal large language models can significantly advance scientific reasoning","author":"Yan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1601"},{"key":"ref45","article-title":"Thinking in space: How multimodal large language models see, remember, and recall spaces","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Embodiedbench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref48","article-title":"Mm-react: Prompting chatgpt for multimodal reasoning and action","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01703"}],"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\/11445622.pdf?arnumber=11445622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:44Z","timestamp":1777611764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00457","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}