{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T20:21:45Z","timestamp":1778617305603,"version":"3.51.4"},"reference-count":39,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025YFF1505704"],"award-info":[{"award-number":["2025YFF1505704"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory of Complex and Critical Software Environment","award":["SKLCCSE"],"award-info":[{"award-number":["SKLCCSE"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306023"],"award-info":[{"award-number":["62306023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20240484490"],"award-info":[{"award-number":["20240484490"]}],"id":[{"id":"10.13039\/501100005090","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.2026.3689345","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:50:31Z","timestamp":1777578631000},"page":"8992-9006","source":"Crossref","is-referenced-by-count":0,"title":["Agents Trainer: Automatically Training Multi-Agent Reinforcement Learning Models for Drone Swarm Using Language Model-Based Agents"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2061-6120","authenticated-orcid":false,"given":"Jiabin","family":"Lou","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4298-9358","authenticated-orcid":false,"given":"Rongye","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4395-8046","authenticated-orcid":false,"given":"Haopeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5801-5174","authenticated-orcid":false,"given":"Ming-Ming","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6488-9862","authenticated-orcid":false,"given":"Yuanshuai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5260-1794","authenticated-orcid":false,"given":"Qunbo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligence, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2998-8828","authenticated-orcid":false,"given":"Wenjun","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jai.2024.12.003"},{"key":"ref2","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Mach. Learn. Res.","volume":"270","author":"Kim"},{"key":"ref3","first-page":"1","article-title":"Keypoint action tokens enable in-context imitation learning in robotics","volume-title":"Proc. 20th Robot., Sci. Syst. (RSS)","author":"Palo"},{"key":"ref4","first-page":"6695","article-title":"AutoTAMP: Autoregressive task and motion planning with LLMs as translators and checkers","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. (ICRA)","author":"Chen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/drones8060221"},{"key":"ref6","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023","journal-title":"arXiv:2303.12712"},{"key":"ref7","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kojima"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2025.01.001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CASE59546.2024.10711432"},{"key":"ref11","first-page":"51991","article-title":"CAMEL: Communicative agents for \u2019Mind\u2019 exploration of large language model society","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref12","first-page":"20094","article-title":"AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref13","first-page":"23247","article-title":"MetaGPT: Meta programming for a multi-agent collaborative framework","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Hong"},{"key":"ref14","article-title":"Multi-agent LLM actor-critic framework for social robot navigation","author":"Wang","year":"2025","journal-title":"arXiv:2503.09758"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1175"},{"key":"ref16","first-page":"57463","article-title":"LLaRA: Supercharging robot learning data for vision-language policy","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3382679"},{"key":"ref18","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Ichter"},{"key":"ref19","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Huang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CASE59546.2024.10711671"},{"key":"ref21","first-page":"34153","article-title":"Describe, explain, plan and select: Interactive planning with LLMs enables open-world multi-task agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cai"},{"key":"ref22","article-title":"AutoRT: Embodied foundation models for large scale orchestration of robotic agents","author":"Ahn","year":"2024","journal-title":"arXiv:2401.12963"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01005-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3511434"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.585"},{"key":"ref26","first-page":"35663","article-title":"Text2Reward: Reward shaping with language models for reinforcement learning","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref27","first-page":"26516","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Ma"},{"key":"ref28","first-page":"31120","article-title":"Reward design with language models","volume-title":"Proc. 11th Int. Conf. Learn. Represeny.","author":"Kwon"},{"key":"ref29","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref30","article-title":"QuadSwarm: A modular multi-quadrotor simulator for deep reinforcement learning with direct thrust control","author":"Huang","year":"2023","journal-title":"arXiv:2306.09537"},{"key":"ref31","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"Ackermann","year":"2019","journal-title":"arXiv:1910.01465"},{"key":"ref32","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Rashid"},{"key":"ref33","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"},{"key":"ref34","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":"ref35","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref36","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341405"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2026.3655308"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11501950.pdf?arnumber=11501950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:52:02Z","timestamp":1778615522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11501950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3689345","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}