{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:59:35Z","timestamp":1781197175621,"version":"3.54.1"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132180","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:21:14Z","timestamp":1774398074000},"page":"132180","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Adaptive cooperation in large-scale MARL via dynamic grouping and cooperation switching"],"prefix":"10.1016","volume":"320","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6657-7670","authenticated-orcid":false,"given":"Baichuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2823-1153","authenticated-orcid":false,"given":"Lun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sihang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianxing","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132180_b0005","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/s00245-010-9123-8","article-title":"A maximum principle for SDEs of mean-field type","volume":"63","author":"Andersson","year":"2011","journal-title":"Applied Mathematics & Optimization"},{"key":"10.1016\/j.eswa.2026.132180_b0010","unstructured":"Beltagy, I., Peters, M. E., & Cohan, A. (2020). Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150."},{"key":"10.1016\/j.eswa.2026.132180_b0015","unstructured":"B\u00f6hmer, W., Kurin, V., & Whiteson, S. (2020). Deep coordination graphs. Presented at the International Conference on Machine Learning, PMLR, pp. 980\u2013991."},{"key":"10.1016\/j.eswa.2026.132180_b0020","unstructured":"Brody, S., Alon, U., & Yahav, E. (2022). How attentive are graph attention networks? Doi: 10.48550\/arXiv.2105.14491."},{"key":"10.1016\/j.eswa.2026.132180_b0025","doi-asserted-by":"crossref","first-page":"5334","DOI":"10.1214\/23-AAP1949","article-title":"Model-free mean-field reinforcement learning: Mean-field MDP and mean-field Q-learning","volume":"33","author":"Carmona","year":"2023","journal-title":"The Annals of Applied Probability"},{"key":"10.1016\/j.eswa.2026.132180_b0030","unstructured":"Cui, K., Tahir, A., Ekinci, G., Elshamanhory, A., Eich, Y., Li, M., & Koeppl, H. (2022). A survey on large-population systems and scalable multi-agent reinforcement learning. Doi: 10.48550\/arXiv.2209.03859."},{"key":"10.1016\/j.eswa.2026.132180_b0035","doi-asserted-by":"crossref","first-page":"16344","DOI":"10.52202\/068431-1189","article-title":"Flashattention: Fast and memory-efficient exact attention with IO-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132180_b0040","unstructured":"Das, A., Gervet, T., Romoff, J., Batra, D., Parikh, D., Rabbat, M., & Pineau, J. (2019). Tarmac: targeted multi-agent communication. Presented at the International Conference on machine learning, PMLR, pp. 1538\u20131546."},{"key":"10.1016\/j.eswa.2026.132180_b0045","doi-asserted-by":"crossref","unstructured":"Duan, W., Lu, J., & Xuan, J. (2024). Group-aware coordination graph for multi-agent reinforcement learning. Presented at the Thirty-Third International Joint Conference on Artificial Intelligence, pp. 3926\u20133934. Doi: 10.24963\/ijcai.2024\/434.","DOI":"10.24963\/ijcai.2024\/434"},{"key":"10.1016\/j.eswa.2026.132180_b0050","doi-asserted-by":"crossref","first-page":"484","DOI":"10.3390\/drones9070484","article-title":"A survey on UAV control with multi-agent reinforcement learning","volume":"9","author":"Ekechi","year":"2025","journal-title":"Drones"},{"key":"10.1016\/j.eswa.2026.132180_b0055","doi-asserted-by":"crossref","unstructured":"Ellis, B., Cook, J., Moalla, S., Samvelyan, M., Sun, M., Mahajan, A., Foerster, J. N., & Whiteson, S. (2023). SMACv2: An improved benchmark for cooperative multi-agent reinforcement learning, in: Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS \u201923. Curran Associates Inc., Red Hook, NY, USA, pp. 37567\u201337593.","DOI":"10.52202\/075280-1634"},{"key":"10.1016\/j.eswa.2026.132180_b0060","doi-asserted-by":"crossref","unstructured":"Fu, Q., Qiu, T., Yi, J., Pu, Z., & Ai, X. (2024). Self-clustering hierarchical multi-agent reinforcement learning with extensible cooperation graph. Doi: 10.48550\/arXiv.2403.18056.","DOI":"10.1109\/TETCI.2024.3449873"},{"key":"10.1016\/j.eswa.2026.132180_b0065","first-page":"9341","article-title":"Concentration network for reinforcement learning of large-scale multi-agent systems","volume":"36","author":"Fu","year":"2022","journal-title":"Association for the Advancement of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132180_b0070","unstructured":"Fuente, N. D. L., Alonso, M. N. I, & Casadell\u00e0, G. (2024). Game theory and multi-agent reinforcement learning: From nash equilibria to evolutionary dynamics. Doi: 10.48550\/arXiv.2412.20523."},{"key":"10.1016\/j.eswa.2026.132180_b0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107658","article-title":"Adaptive receptive field graph neural networks","volume":"190","author":"Gao","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.eswa.2026.132180_b0080","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","article-title":"Multi-agent deep reinforcement learning: A survey","volume":"55","author":"Gronauer","year":"2022","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.eswa.2026.132180_b0085","unstructured":"Guan, C., Chen, F., Yuan, L., Wang, C., Yin, H., Zhang, Z., & Yu, Y. (n.d). Efficient multi-agent communication via self-supervised information aggregation."},{"key":"10.1016\/j.eswa.2026.132180_b0090","doi-asserted-by":"crossref","unstructured":"Gupta, N., Hare, J. Z., Milzman, J., Kannan, R., & Prasanna, V. (2026). Deep meta coordination graphs for multi-agent reinforcement learning. Doi: 10.48550\/arXiv.2502.04028.","DOI":"10.1109\/AAIML67890.2026.11498169"},{"key":"10.1016\/j.eswa.2026.132180_b0095","doi-asserted-by":"crossref","unstructured":"Hao, Q., Huang, W., Feng, T., Yuan, J., & Li, Y. (2023). GAT-MF: Graph attention mean field for very large scale multi-agent reinforcement learning, in: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD \u201923. Association for Computing Machinery, New York, NY, USA, pp. 685\u2013697. Doi: 10.1145\/3580305.3599359.","DOI":"10.1145\/3580305.3599359"},{"key":"10.1016\/j.eswa.2026.132180_b0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128015","article-title":"An overview: Attention mechanisms in multi-agent reinforcement learning","volume":"598","author":"Hu","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.132180_b0105","unstructured":"Jang, E., Gu, S., & Poole, B. (2017). Categorical reparameterization with gumbel-softmax, in: ICLR."},{"key":"10.1016\/j.eswa.2026.132180_b0110","unstructured":"Jiang, J., & Lu, Z. (2018). Learning attentional communication for multi-agent cooperation. Advances in neural information processing systems 31."},{"key":"10.1016\/j.eswa.2026.132180_b0115","unstructured":"Kapoor, A., Freed, B., Choset, H., & Schneider, J. (2025). Assigning credit with partial reward decoupling in multi-agent proximal policy optimization. Doi: 10.48550\/arXiv.2408.04295."},{"key":"10.1016\/j.eswa.2026.132180_b0120","doi-asserted-by":"crossref","first-page":"18368","DOI":"10.1609\/aaai.v39i17.34021","article-title":"GTDE: Grouped training with decentralized execution for multi-agent actor-critic","volume":"39","author":"Li","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132180_b0125","doi-asserted-by":"crossref","unstructured":"Li, S., Gupta, J. K., Morales, P., Allen, R., & Kochenderfer, M. J. (2020). Deep implicit coordination graphs for multi-agent reinforcement learning. arXiv preprint arXiv:2006.11438.","DOI":"10.65109\/CZOY2835"},{"key":"10.1016\/j.eswa.2026.132180_b0130","unstructured":"Li, W., Wang, X., Jin, B., Sheng, J., & Zha, H. (2021). Dealing with non-stationarity in marl via trust-region decomposition. arXiv preprint arXiv:2102.10616."},{"key":"10.1016\/j.eswa.2026.132180_b0135","first-page":"7825","article-title":"Multi-agent reinforcement learning in stochastic networked systems","volume":"34","author":"Lin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132180_b0140","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, W., Hu, Y., Hao, J., Chen, X., & Gao, Y. (2020). Multi-agent game abstraction via graph attention neural network. Presented at the Proceedings of the AAAI conference on artificial intelligence, pp. 7211\u20137218.","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"10.1016\/j.eswa.2026.132180_b0145","unstructured":"Liu, Z., Zhang, J., Shi, E., Liu, Zhilong, N. D., Ai, B., & Xuemin, S. (2024). Graph neural network meets multi-agent reinforcement learning: Fundamentals, applications, and future directions [WWW Document]. arXiv.org. URL https:\/\/arxiv.org\/abs\/2404.04898v1 (accessed 9.11.25)."},{"key":"10.1016\/j.eswa.2026.132180_b0150","first-page":"1006","article-title":"Efficient and scalable reinforcement learning for large-scale network control","volume":"6","author":"Ma","year":"2024","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132180_b0155","unstructured":"Mguni, D. H., Chen, H., Jafferjee, T., Wang, J., Yue, L., Feng, X., Mcaleer, S. M., Tong, F., Wang, J., & Yang, Y. (2023). MANSA: Learning fast and slow in multi-agent systems, in: Proceedings of the 40th International Conference on Machine Learning. Presented at the International Conference on Machine Learning, PMLR, pp. 24631\u201324658."},{"key":"10.1016\/j.eswa.2026.132180_b0160","first-page":"1","article-title":"On the approximation of cooperative heterogeneous multi-agent reinforcement learning (MARL) using mean field control (MFC)","volume":"23","author":"Mondal","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.eswa.2026.132180_b0165","first-page":"1","article-title":"Mean-field approximation of cooperative constrained multi-agent reinforcement learning (CMARL)","volume":"25","author":"Mondal","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.eswa.2026.132180_b0170","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.jai.2024.02.003","article-title":"A survey on multi-agent reinforcement learning and its application","volume":"3","author":"Ning","year":"2024","journal-title":"Journal of Automation and Intelligence"},{"key":"10.1016\/j.eswa.2026.132180_b0175","doi-asserted-by":"crossref","first-page":"13677","DOI":"10.1007\/s10489-022-04105-y","article-title":"A review of cooperative multi-agent deep reinforcement learning","volume":"53","author":"Oroojlooy","year":"2023","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.132180_b0180","first-page":"2074","article-title":"Scalable multi-agent reinforcement learning for networked systems with average reward","volume":"33","author":"Qu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132180_b0185","doi-asserted-by":"crossref","unstructured":"Samvelyan, M., Rashid, T., Schroeder de Witt, C., Farquhar, G., Nardelli, N., Rudner, T. G. J., Hung, C.-M., Torr, P. H. S., Foerster, J., & Whiteson, S. (2019). The starcraft multi-agent challenge, in: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS \u201919. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC, pp. 2186\u20132188.","DOI":"10.65109\/LVZZ5205"},{"key":"10.1016\/j.eswa.2026.132180_b0190","unstructured":"Siu, C., Traish, J., & Xu, R. Y. D. (2021). Dynamic coordination graph for cooperative multi-agent reinforcement learning, in: Proceedings of The 13th Asian Conference on Machine Learning. Presented at the Asian Conference on Machine Learning, PMLR, pp. 438\u2013453."},{"key":"10.1016\/j.eswa.2026.132180_b0195","doi-asserted-by":"crossref","unstructured":"Subramanian, J., & Mahajan, A. (2019). Reinforcement learning in stationary mean-field games. Presented at the Proceedings of the 18th international conference on autonomous agents and multiagent systems, pp. 251\u2013259.","DOI":"10.65109\/JVKR7103"},{"key":"10.1016\/j.eswa.2026.132180_b0200","article-title":"Diffuse and smooth: Beyond truncated receptive field for scalable and adaptive graph representation learning","author":"Hui","year":"2023","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"10.1016\/j.eswa.2026.132180_b0205","doi-asserted-by":"crossref","first-page":"318","DOI":"10.3390\/fi16090318","article-title":"Graph attention networks: A comprehensive review of methods and applications","volume":"16","author":"Vrahatis","year":"2024","journal-title":"Future Internet"},{"key":"10.1016\/j.eswa.2026.132180_b0210","unstructured":"Wang, T., Gupta, T., Mahajan, A., Peng, B., Whiteson, S., & Zhang, C. (2020). RODE: Learning roles to decompose multi-agent tasks. Doi: 10.48550\/arXiv.2010.01523."},{"key":"10.1016\/j.eswa.2026.132180_b0215","unstructured":"Wu, Q., Zhao, W., Yang, C., Zhang, H., Nie, F., Jiang, H., Bian, Y., & Yan, J. (2024). SGFormer: Simplifying and empowering transformers for large-graph representations. Doi: 10.48550\/arXiv.2306.10759."},{"key":"10.1016\/j.eswa.2026.132180_b0220","unstructured":"Wydma\u0144ski, W., & \u015amieja, M. (2025). GFSNetwork: Differentiable feature selection via gumbel-sigmoid relaxation. Doi: 10.48550\/arXiv.2503.13304."},{"key":"10.1016\/j.eswa.2026.132180_b0225","doi-asserted-by":"crossref","first-page":"5261","DOI":"10.1007\/s40747-024-01415-1","article-title":"GHQ: Grouped hybrid Q learning for heterogeneous cooperative multi-agent reinforcement learning","volume":"10","author":"Yu","year":"2024","journal-title":"Complex & Intelligent Systems"},{"key":"10.1016\/j.eswa.2026.132180_b0230","unstructured":"Yuan, L., Zhang, Z., Li, L., Guan, C., & Yu, Y. (2023). A survey of progress on cooperative multi-agent reinforcement learning in open environment. Doi: 10.48550\/arXiv.2312.01058."},{"key":"10.1016\/j.eswa.2026.132180_b0235","unstructured":"Zang, Y., He, J., Li, K., Fu, H., Fu, Q., Xing, J., & Cheng, J. (2023). Automatic grouping for efficient cooperative multi-agent reinforcement learning. Presented at the Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"10.1016\/j.eswa.2026.132180_b0240","unstructured":"Zhang, R., Hou, J., Walter, F., Gu, S., Guan, J., R\u00f6hrbein, F., Du, Y., Cai, P., Chen, G., & Knoll, A. (2024). Multi-agent reinforcement learning for autonomous driving: A survey. Doi: 10.48550\/arXiv.2408.09675."},{"key":"10.1016\/j.eswa.2026.132180_b0245","doi-asserted-by":"crossref","unstructured":"Zheng, L., Yang, J., Cai, H., Zhou, M., Zhang, W., Wang, J., & Yu, Y. (2018). MAgent: A many-agent reinforcement learning platform for artificial collective intelligence. Proceedings of the AAAI Conference on Artificial Intelligence 32. Doi: 10.1609\/aaai.v32i1.11371.","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"10.1016\/j.eswa.2026.132180_b0250","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhou, Y., Xu, F., Song, M., & Liu, S. (2025). Bi-level mean field: Dynamic grouping for large-scale MARL. Doi: 10.48550\/arXiv.2505.06706.","DOI":"10.3233\/FAIA251240"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426010936?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426010936?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:03:03Z","timestamp":1781193783000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426010936"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":50,"alternative-id":["S0957417426010936"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132180","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive cooperation in large-scale MARL via dynamic grouping and cooperation switching","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132180","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132180"}}