{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:00:57Z","timestamp":1780765257935,"version":"3.54.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/lra.2025.3551098","type":"journal-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T17:46:28Z","timestamp":1741887988000},"page":"4292-4299","source":"Crossref","is-referenced-by-count":13,"title":["<b>L<\/b>anguage-<b>D<\/b>riven <b>P<\/b>olicy <b>D<\/b>istillation for Cooperative Driving in Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6171-6155","authenticated-orcid":false,"given":"Jiaqi","family":"Liu","sequence":"first","affiliation":[{"name":"College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6714-3004","authenticated-orcid":false,"given":"Chengkai","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5843-0594","authenticated-orcid":false,"given":"Peng","family":"Hang","sequence":"additional","affiliation":[{"name":"College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5031-4938","authenticated-orcid":false,"given":"Jian","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6556-8359","authenticated-orcid":false,"given":"Mingyu","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1474-1200","authenticated-orcid":false,"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0206-6639","authenticated-orcid":false,"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3209607"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/itsc58415.2024.10919632"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2023.100091"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3069463"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3250704"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3503092"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"ref8","article-title":"Multi-agent reinforcement learning for autonomous driving: A survey","author":"Zhang","year":"2024"},{"key":"ref9","article-title":"Towards efficient LLM grounding for embodied multi-agent collaboration","author":"Zhang","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2025.3552922"},{"key":"ref11","article-title":"AgentsCoDriver: Large language model empowered collaborative driving with lifelong learning","author":"Hu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/627"},{"key":"ref13","article-title":"Real-time metering algorithm for centralized control","author":"Jacobson","year":"1989"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104833"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s23020559"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3411487"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3358299"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"ref20","article-title":"MAPPO-PIS: A multi-agent proximal policy optimization method with prior intent sharing for CAVs\u2019 cooperative decision-making","author":"Guo","year":"2024"},{"key":"ref21","article-title":"LLM-based multi-agent reinforcement learning: Current and future directions","author":"Sun","year":"2024"},{"key":"ref22","first-page":"78227","article-title":"Large language models are semi-parametric reinforcement learning agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhang","year":"2024"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/978-3-642-27645-3_12","article-title":"Partially observable Markov decision processes","volume-title":"Reinforcement Learning: State-of-the-Art","author":"Spaan","year":"2012"},{"key":"ref24","article-title":"REACT: Synergizing reasoning and acting in language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao","year":"2022"},{"issue":"2","key":"ref25","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevE.62.1805","article-title":"Congested traffic states in empirical observations and microscopic simulations","volume":"62","author":"Treiber","year":"2000","journal-title":"Phys. Rev. E"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref27","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018"},{"key":"ref28","first-page":"5285","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Wu","year":"2017"},{"key":"ref29","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"},{"key":"ref30","article-title":"Introducing ChatGPT","year":"2023"},{"key":"ref31","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref32","article-title":"DiLu: A knowledge-driven approach to autonomous driving with large language models","author":"Wen","year":"2023"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10935293\/10924758.pdf?arnumber=10924758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T17:07:58Z","timestamp":1745514478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10924758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":32,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3551098","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}