{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:43:55Z","timestamp":1781797435073,"version":"3.54.5"},"reference-count":34,"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\/iros60139.2025.11247312","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"18700-18707","source":"Crossref","is-referenced-by-count":1,"title":["ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Control"],"prefix":"10.1109","author":[{"given":"Yoshiki","family":"Yano","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuki","family":"Shibata","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maarten","family":"Kokshoorn","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342169"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769891"},{"key":"ref4","article-title":"KALM: Knowledgeable agents by offline reinforcement learning from large language model rollouts","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Pang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487163"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461263"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SII59315.2025.10871115"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3102636"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3161699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611322"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802520"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202268"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561090"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342377"},{"key":"ref15","first-page":"6860","article-title":"Coach-player multi-agent reinforcement learning for dynamic team composition","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801665"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127288"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610855"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610676"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3504233"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3518105"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611163"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3645650"},{"key":"ref25","first-page":"330","article-title":"Multi-agent reinforcement learning: independent versus cooperative agents","volume-title":"Proceedings of the Tenth International Conference on International Conference on Machine Learning","author":"Tan"},{"key":"ref26","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Multi-agent common knowledge reinforcement learning","volume":"32","author":"Schroeder de Witt","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"178","key":"ref28","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Rakelly"},{"key":"ref30","article-title":"Chain of thought prompting elicits reasoning in large language models","volume-title":"Advances in Neural Information Processing Systems","author":"Wei"},{"key":"ref31","article-title":"Large language models are zero-shot reasoners","volume-title":"Advances in Neural Information Processing Systems","author":"Kojima"},{"key":"ref32","article-title":"gpt4o","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref34","first-page":"1162","article-title":"Active domain randomization","volume-title":"Conference on Robot Learning","author":"Mehta"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247312.pdf?arnumber=11247312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:40Z","timestamp":1766061640000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247312\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247312","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}