{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T08:40:22Z","timestamp":1768466422724,"version":"3.49.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573322"],"award-info":[{"award-number":["62573322"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62495094"],"award-info":[{"award-number":["62495094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62103302"],"award-info":[{"award-number":["62103302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013105","name":"Shanghai Rising-Star Program","doi-asserted-by":"publisher","award":["24QA2709400"],"award-info":[{"award-number":["24QA2709400"]}],"id":[{"id":"10.13039\/501100013105","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Chenguang Program","award":["22CGA19"],"award-info":[{"award-number":["22CGA19"]}]},{"name":"Shanghai Municipal Science and Technology","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["22120240276"],"award-info":[{"award-number":["22120240276"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2025.3637862","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:43:18Z","timestamp":1765219398000},"page":"1009-1020","source":"Crossref","is-referenced-by-count":0,"title":["EALLMs: Environment-Aligned LLMs for Enhanced Exploration and Communication in Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5040-9654","authenticated-orcid":false,"given":"Zhuohui","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0281-4860","authenticated-orcid":false,"given":"Bin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-6269","authenticated-orcid":false,"given":"Bin","family":"He","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3385412"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3501580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3412188"},{"key":"ref4","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3563725"},{"key":"ref6","article-title":"PAGNet: Pluggable adaptive generative networks for information completion in multi-agent communication","author":"Zhang","year":"2025","journal-title":"arXiv:2502.03845"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3398712"},{"key":"ref9","article-title":"Efficient multi-agent reinforcement learning by planning","author":"Liu","year":"2024","journal-title":"arXiv:2405.11778"},{"key":"ref10","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NIPS","author":"Lowe"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3592721"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3563489"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3369592"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CAC63892.2024.10865512"},{"key":"ref15","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3382679"},{"key":"ref17","first-page":"4501","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref18","first-page":"5315","article-title":"HuggingGPT: Solving AI tasks with ChatGPT and its friends in hugging face","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref19","first-page":"8514","article-title":"Mapping language models to grounded conceptual spaces","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Patel"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.conll-1.9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.463"},{"key":"ref22","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv:2204.01691"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3524426"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34507"},{"key":"ref25","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref26","article-title":"The StarCraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"arXiv:1902.04043"},{"key":"ref27","first-page":"22361","article-title":"SMACv2: An improved benchmark for cooperative multi-agent reinforcement learning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Ellis"},{"key":"ref28","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref29","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref30","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref31","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref33","article-title":"ReAct: Synergizing reasoning and acting in language models","author":"Yao","year":"2022","journal-title":"arXiv:2210.03629"},{"key":"ref34","article-title":"Can Wikipedia help offline reinforcement learning?","author":"Reid","year":"2022","journal-title":"arXiv:2201.12122"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.775"},{"key":"ref36","first-page":"27042","article-title":"Online decision transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref37","article-title":"Why solving multi-agent path finding with large language model has not succeeded yet","author":"Chen","year":"2024","journal-title":"arXiv:2401.03630"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.448"},{"key":"ref39","article-title":"Large language models play StarCraft II: Benchmarks and a chain of summarization approach","author":"Ma","year":"2023","journal-title":"arXiv:2312.11865"},{"key":"ref40","article-title":"SMART-LLM: Smart multi-agent robot task planning using large language models","author":"Kannan","year":"2023","journal-title":"arXiv:2309.10062"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3151607"},{"key":"ref42","article-title":"Co-NavGPT: Multi-robot cooperative visual semantic navigation using vision language models","author":"Yu","year":"2023","journal-title":"arXiv:2310.07937"},{"key":"ref43","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"issue":"240","key":"ref44","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref46","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","author":"Singh","year":"2018","journal-title":"arXiv:1812.09755"},{"key":"ref47","first-page":"7254","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref48","article-title":"Graph convolutional reinforcement learning","author":"Jiang","year":"2018","journal-title":"arXiv:1810.09202"},{"key":"ref49","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Das"},{"key":"ref50","article-title":"Learning nearly decomposable value functions via communication minimization","author":"Wang","year":"2019","journal-title":"arXiv:1910.05366"},{"key":"ref51","first-page":"1020","article-title":"Efficient multi-agent communication via self-supervised information aggregation","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Guan"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3337534"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref55","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref56","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ouyang"},{"key":"ref57","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref58","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref60","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref61","first-page":"31199","article-title":"Pre-trained language models for interactive decision-making","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref62","article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","author":"Papoudakis","year":"2020","journal-title":"arXiv:2006.07869"},{"key":"ref63","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref64","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11281556.pdf?arnumber=11281556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:42:09Z","timestamp":1768423329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11281556\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3637862","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}