{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T21:03:51Z","timestamp":1776891831207,"version":"3.51.2"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303209"],"award-info":[{"award-number":["62303209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010909","name":"Excellent Young Scientists Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.neucom.2026.133447","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:14:37Z","timestamp":1774599277000},"page":"133447","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Leader-follower communication graph optimization method for multi-agent reinforcement learning via transformer"],"prefix":"10.1016","volume":"682","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8422-5084","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xiang","family":"Xu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133447_bib0005","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","volume":"abs\/2011.00583","author":"Yang","year":"2020","journal-title":"CoRR"},{"key":"10.1016\/j.neucom.2026.133447_bib0010","article-title":"On the complexity of computing markov perfect equilibrium in general-sum stochastic games","volume":"10","author":"Deng","year":"2023","journal-title":"Natl. Sci. Rev."},{"key":"10.1016\/j.neucom.2026.133447_bib0015","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"nature"},{"key":"10.1016\/j.neucom.2026.133447_bib0020","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1017\/pds.2021.17","article-title":"A multi-agent reinforcement learning framework for intelligent manufacturing with autonomous mobile robots","volume":"1","author":"Agrawal","year":"2021","journal-title":"Proc. Des. Soc."},{"key":"10.1016\/j.neucom.2026.133447_bib0025","series-title":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","first-page":"448","article-title":"Multi-agent reinforcement learning in dynamic industrial context","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133447_bib0030","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","article-title":"Multi-agent reinforcement learning as a rehearsal for decentralized planning","volume":"190","author":"Kraemer","year":"2016","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133447_bib0035","series-title":"The Twelfth International Conference on Learning Representations, ICLR","article-title":"Learning multi-agent communication with contrastive learning","author":"Lo","year":"2024"},{"key":"10.1016\/j.neucom.2026.133447_bib0040","series-title":"AAMAS \u201921: 20th International Conference on Autonomous Agents and Multiagent Systems","first-page":"844","article-title":"Contrasting centralized and decentralized critics in multi-agent reinforcement learning","author":"Lyu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133447_bib0045","series-title":"Machine Learning, Proceedings of the Eleventh International Conference","first-page":"157","article-title":"Markov games as a framework for multi-agent reinforcement learning","author":"Littman","year":"1994"},{"key":"10.1016\/j.neucom.2026.133447_bib0050","series-title":"The Twelfth International Conference on Learning Representations, ICLR","article-title":"Learning multi-agent communication from graph modeling perspective","author":"Hu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133447_bib0055","series-title":"7th International Conference on Learning Representations, ICLR","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","author":"Singh","year":"2019"},{"key":"10.1016\/j.neucom.2026.133447_bib0060","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume":"33","author":"Ding","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133447_bib0065","series-title":"International Conference on Machine Learning","first-page":"1538","article-title":"Tarmac: targeted multi-agent communication","author":"Das","year":"2019"},{"key":"10.1016\/j.neucom.2026.133447_bib0070","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s10458-023-09633-6","article-title":"A survey of multi-agent deep reinforcement learning with communication","volume":"38","author":"Zhu","year":"2024","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"10.1016\/j.neucom.2026.133447_bib0075","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1136\/amiajnl-2011-000464","article-title":"Natural language processing: an introduction","volume":"18","author":"Nadkarni","year":"2011","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.neucom.2026.133447_bib0080","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133447_bib0085","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neucom.2026.133447_bib0090","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","author":"Wen","year":"2022"},{"key":"10.1016\/j.neucom.2026.133447_bib0095","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","author":"Yu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133447_bib0100","series-title":"The Tenth International Conference on Learning Representations, ICLR","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","author":"Kuba","year":"2022"},{"key":"10.1016\/j.neucom.2026.133447_bib0105","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133447_bib0110","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Counterfactual multi-agent policy gradients","volume":"vol. 32","author":"Foerster","year":"2018"},{"key":"10.1016\/j.neucom.2026.133447_bib0115","series-title":"AAMAS \u201921: 20th International Conference on Autonomous Agents and Multiagent Systems","first-page":"764","article-title":"Deep implicit coordination graphs for multi-agent reinforcement learning","author":"Li","year":"2021"},{"key":"10.1016\/j.neucom.2026.133447_bib0120","author":"Jiang"},{"key":"10.1016\/j.neucom.2026.133447_bib0125","article-title":"Learning attentional communication for multi-agent cooperation","volume":"31","author":"Jiang","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133447_bib0130","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106432","article-title":"Hypercomm: hypergraph-based communication in multi-agent reinforcement learning","volume":"178","author":"Zhu","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neucom.2026.133447_bib0135","series-title":"The Tenth International Conference on Learning Representations, ICLR","article-title":"Tom2c: target-oriented multi-agent communication and cooperation with theory of mind","author":"Wang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133447_bib0140","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128817","article-title":"Secure bipartite consensus of leader\u2013follower multi-agent systems under denial-of-service attacks via observer-based dynamic event-triggered control","volume":"614","author":"Xu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133447_bib0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119074","article-title":"A graph neural network based deep reinforcement learning algorithm for multi-agent leader-follower flocking","volume":"641","author":"Xiao","year":"2023","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133447_bib0150","doi-asserted-by":"crossref","first-page":"13336","DOI":"10.1109\/TCYB.2021.3115124","article-title":"Leader-following consensus of heterogeneous linear multiagent systems with communication time-delays via adaptive distributed observers","volume":"52","author":"Luo","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.neucom.2026.133447_bib0155","series-title":"Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96)","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"Ester","year":"1996"},{"key":"10.1016\/j.neucom.2026.133447_bib0160","author":"Yang"},{"key":"10.1016\/j.neucom.2026.133447_bib0165","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"642","article-title":"Hierarchical consensus-based multi-agent reinforcement learning for multi-robot cooperation tasks","author":"Feng","year":"2024"},{"key":"10.1016\/j.neucom.2026.133447_bib0170","author":"Schulman"},{"key":"10.1016\/j.neucom.2026.133447_bib0175","series-title":"Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS \u201919","first-page":"2186","article-title":"The Starcraft multi-agent Challenge","author":"Samvelyan","year":"2019"},{"key":"10.1016\/j.neucom.2026.133447_bib0180","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Emergence of grounded compositional language in multi-agent populations","volume":"vol. 32","author":"Mordatch","year":"2018"},{"key":"10.1016\/j.neucom.2026.133447_bib0185","series-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","article-title":"Weighted QMIX: expanding monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2020"},{"key":"10.1016\/j.neucom.2026.133447_bib0190","series-title":"Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"Sukhbaatar","year":"2016"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008441?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008441?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:29:19Z","timestamp":1776889759000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226008441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":38,"alternative-id":["S0925231226008441"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133447","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Leader-follower communication graph optimization method for multi-agent reinforcement learning via transformer","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133447","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133447"}}