{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T21:37:09Z","timestamp":1782941829903,"version":"3.54.5"},"reference-count":56,"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\/501100002402","name":"Sun Yat-sen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002402","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\/iccv51701.2025.00939","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10075-10085","source":"Crossref","is-referenced-by-count":1,"title":["RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints"],"prefix":"10.1109","author":[{"given":"Yiran","family":"Qin","sequence":"first","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Kang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiufeng","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenfei","family":"Yin","sequence":"additional","affiliation":[{"name":"Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"HKU"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruimao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Bai","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/AIM55361.2024.10637173"},{"key":"ref4","article-title":"On the utility of learning about humans for human-ai coordination","volume":"32","author":"Carroll","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Partnr: A benchmark for planning and reasoning in embodied multi-agent tasks","author":"Chang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"3909","article-title":"Q-transformer: Scalable offline reinforcement learning via autoregressive q-functions","volume-title":"Conference on Robot Learning","author":"Chebotar","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610676"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref9","article-title":"Visual programming for text-to-image generation and evaluation","volume-title":"NeurIPS","author":"Cho","year":"2023"},{"key":"ref10","article-title":"Imitating task and motion planning with visuomotor transformers","volume-title":"Conference on Robot Learning","author":"Dalal","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"issue":"4","key":"ref13","first-page":"6","article-title":"Metagpt: Meta programming for multi-agent collaborative framework","volume":"3","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Dynamic handover: Throw and catch with bimanual hands","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"How far are we on the decision-making of 11 ms ? evaluating llms\u2019 gaming ability in multi-agent environments","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Story3d-agent: Exploring 3d storytelling visualization with large language models","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref18","first-page":"9911002","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang","year":"2022"},{"key":"ref19","article-title":"Vima: General robot manipulation with multimodal prompts","volume-title":"Fortieth International Conference on Machine Learning","author":"Jiang","year":"2023"},{"key":"ref20","article-title":"Mt-opt: Continuous multitask robotic reinforcement learning at scale","author":"Kalashnikov","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Openvla: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2264"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref25","article-title":"Contrastive imitation learning for languageguided multi-task robotic manipulation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610855"},{"key":"ref27","first-page":"879","article-title":"Roboturk: A crowdsourcing platform for robotic skill learning through imitation","volume-title":"Conference on Robot Learning","author":"Mandlekar","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2025.3569192"},{"key":"ref30","article-title":"Robocodex: Multimodal code generation for robotic behavior synthesis","author":"Mu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_17"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2024.10.173"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.050"},{"key":"ref34","article-title":"Watch-and-help: A challenge for social perception and human-ai collaboration","author":"Puig","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Worldsimbench: Towards video generation models as world simulators","author":"Qin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01543"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127507"},{"key":"ref38","article-title":"Maniskill3: Gpu parallelized robotics simulation and rendering for generalizable embodied ai","author":"Tao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"ref42","article-title":"Code as reward: Empowering reinforcement learning with vlms","author":"Venuto","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Sibyl: Simple yet effective agent framework for complex real-world reasoning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Autogen: Enabling next-gen llm applications via multi-agent conversation","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref48","article-title":"Oasis: Open agents social interaction simulations on one million agents","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Mineland: Simulating large-scale multi-agent interactions with limited multimodal senses and physical needs","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref51","article-title":"Building cooperative embodied agents modularly with large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29936"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref54","article-title":"Minedreamer: Learning to follow instructions via chain-ofimagination for simulated-world control","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00649"},{"key":"ref56","article-title":"Webarena: A realistic web environment for building autonomous agents","author":"Zhou","year":"2023","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\/11445239.pdf?arnumber=11445239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:18:35Z","timestamp":1777612715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00939","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}