{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:13:35Z","timestamp":1780636415223,"version":"3.54.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127486","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1240-1246","source":"Crossref","is-referenced-by-count":5,"title":["Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-Based Planner and Graph-Based Policy"],"prefix":"10.1109","author":[{"given":"Ziqi","family":"Jia","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Li","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyang","family":"Qu","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3290449"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ACC55779.2023.10156237"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104314"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104492"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610676"},{"key":"ref6","article-title":"Multi-agent path finding for precedence-constrained goal sequences","volume-title":"International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS)","author":"Zhang","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610420"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00088"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3240173"},{"key":"ref12","first-page":"199","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref13","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Conference on Robot Learning (CoRL)","author":"Huang","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342169"},{"key":"ref19","article-title":"Language to rewards for robotic skill synthesis","volume-title":"Conference on Robot Learning (CoRL)","author":"Yu","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611163"},{"key":"ref21","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning (CoRL)","author":"Irpan","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610578"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610855"},{"key":"ref24","article-title":"Dynamic llm-agent network: An llm-agent collaboration framework with agent team optimization","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02482"},{"key":"ref26","article-title":"Multi-agent consensus seeking via large language models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Building cooperative embodied agents modularly with large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhang","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"ref29","article-title":"Large language models as generalizable policies for embodied tasks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Szot","year":"2024"},{"key":"ref30","article-title":"Spring: Studying papers and reasoning to play games","volume":"36","author":"Wu","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref31","first-page":"3676","article-title":"Grounding large language models in interactive environments with online reinforcement learning","volume-title":"International Conference on Machine Learning (ICML).","author":"Carta","year":"2023"},{"key":"ref32","article-title":"Plan4mc: Skill reinforcement learning and planning for open-world minecraft tasks","author":"Baai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ma","year":"2024"},{"key":"ref34","article-title":"Text2reward: Automated dense reward function generation for reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Xie","year":"2024"},{"key":"ref35","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"Kolve","year":"2017","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Gcs: Graph-based coordination strategy for multi-agent reinforcement learning","volume-title":"International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS)","author":"Ruan","year":"2022"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127486.pdf?arnumber=11127486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:45:44Z","timestamp":1756881944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127486\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127486","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}