{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:55Z","timestamp":1777865395720,"version":"3.51.4"},"reference-count":46,"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\/iccv51701.2025.01016","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10919-10928","source":"Crossref","is-referenced-by-count":0,"title":["CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games"],"prefix":"10.1109","author":[{"given":"Peng","family":"Chen","sequence":"first","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pi","family":"Bu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingyao","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziming","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Guo","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingxiu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Song","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siran","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiamang","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Brohan","year":"2023","journal-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715259"},{"key":"ref3","volume-title":"Ai-wukong: Rl-based arpg gamebot","author":"Cat","year":"2024"},{"key":"ref4","author":"Cheang","year":"2024","journal-title":"Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation"},{"key":"ref5","author":"Chen","year":"2024","journal-title":"Can vlms play action role-playing games? take black myth wukong as a study case"},{"key":"ref6","author":"Chen","year":"2025","journal-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1220"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1634"},{"key":"ref9","author":"Fu","year":"2024","journal-title":"Mme: A compre-hensive evaluation benchmark for multimodal large language models"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.844"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127299"},{"key":"ref13","volume-title":"A realworld webagent with planning, long context understanding, and program synthesis","author":"Gur","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.371"},{"key":"ref15","author":"He","year":"2025","journal-title":"Analyzing and boosting the power of fine-grained visual recognition for multi-modal large language models"},{"key":"ref16","author":"Hu","year":"2024","journal-title":"Pokellmon: A human-parity agent for pokemon battles with large language models"},{"key":"ref17","author":"Jucys","year":"2024","journal-title":"Interpretability in action: Exploratory analysis of vpt, a minecraft agent"},{"key":"ref18","author":"Jin Kim","year":"2024","journal-title":"Openvla: An opensource vision-language-action model"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2026.3653303"},{"key":"ref20","author":"Li","year":"2025","journal-title":"Imagine while reasoning in space: Multimodal visualization-ofthought"},{"key":"ref21","author":"Li","year":"2024","journal-title":"Vision-language foundation models as effective robot imitators"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715232"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01816"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref27","author":"Pan","year":"2023","journal-title":"Do 11 ms possess a personality? making the mbti test an amazing evaluation for large language models"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3586183.3606763","article-title":"Generative agents: Interactive simulacra of human behavior","volume-title":"Proceedings of the 36th annual acm symposium on user interface software and technology","author":"Sung Park","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.810"},{"key":"ref30","article-title":"Ui-tars: Pioneering automated gui interaction with native agents","author":"Qin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"ref33","author":"Tan","year":"2024","journal-title":"Cradle: Empowering foundation agents towards general computer control"},{"key":"ref34","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","author":"Wang","year":"2023","journal-title":"Voyager: An open-ended embodied agent with large language models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0088"},{"key":"ref37","author":"Wang","year":"2024","journal-title":"Mobile-agent: Autonomous multi-modal mobile device agent with visual perception"},{"key":"ref38","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3511593"},{"key":"ref40","article-title":"Escapecraft: A 3d room escape environment for benchmarking complex multimodal reasoning ability","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref41","author":"Wei","year":"2023","journal-title":"Chain-of-thought prompting elicits reasoning in large language models"},{"key":"ref42","article-title":"Auto-gpt for online decision making: Benchmarks and additional opinions","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","author":"Yue","year":"2024","journal-title":"Deer-vla: Dynamic inference of multimodal large language models for efficient robot execution"},{"key":"ref44","author":"Zhai","year":"2024","journal-title":"Fine-tuning large vision-language models as decision-making agents via reinforcement learning"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713600"},{"key":"ref46","article-title":"Embodied-reasoner: Synergizing visual search, reasoning, and action for embodied interactive tasks","author":"Zhang","year":"2025","journal-title":"arXiv preprint"}],"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\/11443643.pdf?arnumber=11443643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:25:01Z","timestamp":1777530301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01016","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}