{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T08:15:29Z","timestamp":1783498529367,"version":"3.55.0"},"reference-count":72,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134438","type":"journal-article","created":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T15:16:04Z","timestamp":1783178164000},"page":"134438","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MeMAT: Multi-agent transformer with deep long-term memory, short-term memory, and persistent memory"],"prefix":"10.1016","volume":"699","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2921-7877","authenticated-orcid":false,"given":"Gege","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6656-6061","authenticated-orcid":false,"given":"Weiqiang","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9149-4576","authenticated-orcid":false,"given":"Guizhong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"178","key":"10.1016\/j.neucom.2026.134438_bib0005","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.134438_bib0010","doi-asserted-by":"crossref","first-page":"24611","DOI":"10.52202\/068431-1787","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134438_bib0015","author":"Kuba"},{"key":"10.1016\/j.neucom.2026.134438_bib0020","doi-asserted-by":"crossref","first-page":"16509","DOI":"10.52202\/068431-1201","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume":"35","author":"Wen","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134438_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102318","article-title":"Hierarchical relationship modeling in multi-agent reinforcement learning for mixed cooperative\u2013competitive environments","volume":"108","author":"Xie","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134438_bib0030","series-title":"Distributed Artificial Intelligence: Third International Conference, DAI 2021, Shanghai, China, December 17\u201318, 2021, Proceedings 3","first-page":"52","article-title":"BGC: multi-agent group belief with graph clustering","author":"Zhou","year":"2021"},{"key":"10.1016\/j.neucom.2026.134438_bib0035","author":"Zhang"},{"issue":"2","key":"10.1016\/j.neucom.2026.134438_bib0040","doi-asserted-by":"crossref","first-page":"203","DOI":"10.3233\/AIC-220316","article-title":"Multi-agent reinforcement learning for safe lane changes by connected and autonomous vehicles: a survey","volume":"37","author":"Hegde","year":"2024","journal-title":"AI Commun."},{"key":"10.1016\/j.neucom.2026.134438_bib0045","doi-asserted-by":"crossref","DOI":"10.1109\/TASE.2025.3574280","article-title":"Multi-agent reinforcement learning for connected and automated vehicles control: recent advancements and future prospects","author":"Hua","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.134438_bib0050","doi-asserted-by":"crossref","first-page":"14362","DOI":"10.1109\/JIOT.2025.3525640","article-title":"Graph-based cooperation multiagent reinforcement learning for intelligent traffic signal control","volume":"12","author":"Shang","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.neucom.2026.134438_bib0055","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.ins.2023.03.087","article-title":"Hierarchical graph multi-agent reinforcement learning for traffic signal control","volume":"634","author":"Yang","year":"2023","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.134438_bib0060","series-title":"2025 International Conference on Electronics and Renewable Systems (ICEARS)","first-page":"1975","article-title":"Intelligent traffic management system using multi-agent reinforcement learning","author":"Shaheen","year":"2025"},{"issue":"5","key":"10.1016\/j.neucom.2026.134438_bib0065","doi-asserted-by":"crossref","first-page":"2373","DOI":"10.3390\/s23052373","article-title":"Multi-agent reinforcement learning for traffic flow management of autonomous vehicles","volume":"23","author":"Mushtaq","year":"2023","journal-title":"Sensors"},{"issue":"2","key":"10.1016\/j.neucom.2026.134438_bib0070","doi-asserted-by":"crossref","DOI":"10.3390\/app12020610","article-title":"Multi-UAV conflict resolution with graph convolutional reinforcement learning","volume":"12","author":"Isufaj","year":"2022","journal-title":"Appl. Sci."},{"key":"10.1016\/j.neucom.2026.134438_bib0075","series-title":"Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.65109\/SKOP8447","article-title":"MA-MIX: value function decomposition for cooperative multiagent reinforcement learning based on multi-head attention mechanism","author":"Niu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134438_bib0080","series-title":"Lecture Notes in Computer Science","first-page":"113","article-title":"Abbreviated weighted graph in multi-agent reinforcement learning","author":"Wang","year":"2024"},{"issue":"7","key":"10.1016\/j.neucom.2026.134438_bib0085","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.neucom.2026.134438_bib0090","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1109\/LWC.2026.3663841","article-title":"Multi-agent reinforcement learning based on hybrid action representation for UAV swarms\u2019 integrated communication and control","volume":"15","author":"Sun","year":"2026","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"10.1016\/j.neucom.2026.134438_bib0095","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134438_bib0100","series-title":"International Conference on Neural Information Processing","first-page":"305","article-title":"Mastering complex coordination through attention-based dynamic graph","author":"Zhou","year":"2023"},{"key":"10.1016\/j.neucom.2026.134438_bib0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.131928","article-title":"Enhancing hotel recommendations with multi-agent reinforcement learning: a novel MADDPG approach","author":"Mastan","year":"2026","journal-title":"Expert Syst. Appl."},{"issue":"2","key":"10.1016\/j.neucom.2026.134438_bib0110","first-page":"73","article-title":"A survey on multi-agent reinforcement learning and its application","volume":"3","author":"Ning","year":"2024","journal-title":"J. Autom. Intell."},{"issue":"4","key":"10.1016\/j.neucom.2026.134438_bib0115","doi-asserted-by":"crossref","first-page":"820","DOI":"10.3390\/electronics14040820","article-title":"A review of multi-agent reinforcement learning algorithms","volume":"14","author":"Liang","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.neucom.2026.134438_bib0120","author":"Beikmohammadi"},{"key":"10.1016\/j.neucom.2026.134438_bib0125","series-title":"International Conference on Artificial Intelligence and Soft Computing","first-page":"92","article-title":"Memory augmented multi-agent reinforcement learning for cooperative environment","author":"Kia","year":"2024"},{"issue":"9","key":"10.1016\/j.neucom.2026.134438_bib0130","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.1007\/s10994-019-05864-5","article-title":"Improving coordination in small-scale multi-agent deep reinforcement learning through memory-driven communication","volume":"109","author":"Pesce","year":"2020","journal-title":"Mach. Learn."},{"key":"10.1016\/j.neucom.2026.134438_bib0135","author":"Zhou"},{"key":"10.1016\/j.neucom.2026.134438_bib0140","series-title":"Advances in Neural Information Processing Systems, 14","first-page":"1475","article-title":"Reinforcement learning with long short-term memory","author":"Bakker","year":"2002"},{"key":"10.1016\/j.neucom.2026.134438_bib0145","series-title":"2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI)","first-page":"1","article-title":"Cooperative multi-agent reinforcement learning with hierarchical relation graph under partial observability","author":"Li","year":"2020"},{"key":"10.1016\/j.neucom.2026.134438_bib0150","doi-asserted-by":"crossref","first-page":"34874","DOI":"10.52202\/068431-2527","article-title":"Transformer-based working memory for multiagent reinforcement learning with action parsing","volume":"35","author":"Yang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"10","key":"10.1016\/j.neucom.2026.134438_bib0155","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1038\/nrn1201","article-title":"Working memory: looking back and looking forward","volume":"4","author":"Baddeley","year":"2003","journal-title":"Nat. Rev. Neurosci."},{"key":"10.1016\/j.neucom.2026.134438_bib0160","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/S0079-6123(07)00020-9","article-title":"What are the differences between long-term, short-term, and working memory?","volume":"169","author":"Cowan","year":"2008","journal-title":"Prog. Brain Res."},{"key":"10.1016\/j.neucom.2026.134438_bib0165","author":"Ahilan"},{"key":"10.1016\/j.neucom.2026.134438_bib0170","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","article-title":"A learning algorithm for continually running fully recurrent neural networks","volume":"1","author":"Williams","year":"1989","journal-title":"Neural Comput."},{"key":"10.1016\/j.neucom.2026.134438_bib0175","author":"Sagirova"},{"key":"10.1016\/j.neucom.2026.134438_bib0180","author":"Behrouz"},{"key":"10.1016\/j.neucom.2026.134438_bib0185","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134438_bib0190","first-page":"11853","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume":"33","author":"Zhou","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"14","key":"10.1016\/j.neucom.2026.134438_bib0195","doi-asserted-by":"crossref","first-page":"6938","DOI":"10.3390\/app12146938","article-title":"Multi-level credit assignment for cooperative multi-agent reinforcement learning","volume":"12","author":"Feng","year":"2022","journal-title":"Appl. Sci."},{"key":"10.1016\/j.neucom.2026.134438_bib0200","series-title":"Autonomous Agents and Multi-Agent Systems Conference","doi-asserted-by":"crossref","first-page":"121","DOI":"10.65109\/ISIS9131","article-title":"Unifying temporal and structural credit assignment problems","author":"Agogino","year":"2004"},{"key":"10.1016\/j.neucom.2026.134438_bib0205","author":"Samvelyan"},{"key":"10.1016\/j.neucom.2026.134438_bib0210","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 34","first-page":"4501","article-title":"Google research football: a novel reinforcement learning environment","author":"Kurach","year":"2020"},{"key":"10.1016\/j.neucom.2026.134438_bib0215","series-title":"Machine Learning Proceedings 1994","first-page":"157","article-title":"Markov games as a framework for multi-agent reinforcement learning","author":"Littman","year":"1994"},{"key":"10.1016\/j.neucom.2026.134438_bib0220","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134438_bib0225","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1724","article-title":"Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.1016\/j.neucom.2026.134438_bib0230","series-title":"The Structure of Value: Accounting for Taste","first-page":"3","author":"Mandler","year":"2014"},{"key":"10.1016\/j.neucom.2026.134438_bib0235","author":"Morad"},{"key":"10.1016\/j.neucom.2026.134438_bib0240","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8162","article-title":"Recurrent model-free RL can be a strong baseline for many POMDPs","author":"Ni","year":"2021"},{"key":"10.1016\/j.neucom.2026.134438_bib0245","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 32","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"Foerster","year":"2018"},{"key":"10.1016\/j.neucom.2026.134438_bib0250","series-title":"International Conference on Machine Learning","first-page":"5887","article-title":"QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"Son","year":"2019"},{"key":"10.1016\/j.neucom.2026.134438_bib0255","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134438_bib0260","author":"Jiang"},{"key":"10.1016\/j.neucom.2026.134438_bib0265","series-title":"Proceedings of the 39th International Conference on Machine Learning, 162","first-page":"24963","article-title":"Self-organized polynomial-time coordination graphs","author":"Yang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134438_bib0270","author":"Shi"},{"key":"10.1016\/j.neucom.2026.134438_bib0275","series-title":"Proceedings of the Tenth International Conference on Machine Learning","first-page":"330","article-title":"Multi-agent reinforcement learning: independent vs. cooperative agents","author":"Tan","year":"1993"},{"key":"10.1016\/j.neucom.2026.134438_bib0280","author":"Sunehag"},{"key":"10.1016\/j.neucom.2026.134438_bib0285","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 34","first-page":"7211","article-title":"Multi-agent game abstraction via graph attention neural network","author":"Liu","year":"2020"},{"key":"10.1016\/j.neucom.2026.134438_bib0290","series-title":"Proceedings of the 37th International Conference on Machine Learning, 119 of Proceedings of Machine Learning Research","first-page":"980","article-title":"Deep coordination graphs","author":"Boehmer","year":"2020"},{"key":"10.1016\/j.neucom.2026.134438_bib0295","author":"Ruan"},{"key":"10.1016\/j.neucom.2026.134438_bib0300","author":"Hu"},{"key":"10.1016\/j.neucom.2026.134438_bib0305","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1007\/s11633-022-1383-7","article-title":"Offline pre-trained multi-agent decision transformer","volume":"20","author":"Meng","year":"2023","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.neucom.2026.134438_bib0310","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1038\/nature20101","article-title":"Hybrid computing using a neural network with dynamic external memory","volume":"538","author":"Graves","year":"2016","journal-title":"Nature"},{"key":"10.1016\/j.neucom.2026.134438_bib0315","article-title":"Optimizing agent behavior over long time scales by transporting value","volume":"10","author":"Hung","year":"2018","journal-title":"Nat. Commun."},{"key":"10.1016\/j.neucom.2026.134438_bib0320","author":"Ni"},{"key":"10.1016\/j.neucom.2026.134438_bib0325","author":"Kacham"},{"key":"10.1016\/j.neucom.2026.134438_bib0330","series-title":"Proceedings of the 37th International Conference on Machine Learning, 119 of Proceedings of Machine Learning Research","first-page":"5156","article-title":"Transformers are RNNs: fast autoregressive transformers with linear attention","author":"Katharopoulos","year":"2020"},{"key":"10.1016\/j.neucom.2026.134438_bib0335","series-title":"Proceedings of the 38th International Conference on Machine Learning, 139 of Proceedings of Machine Learning Research","first-page":"9355","article-title":"Linear transformers are secretly fast weight programmers","author":"Schlag","year":"2021"},{"key":"10.1016\/j.neucom.2026.134438_bib0340","series-title":"International Conference on Machine Learning","first-page":"6404","article-title":"Working memory graphs","author":"Loynd","year":"2020"},{"key":"10.1016\/j.neucom.2026.134438_bib0345","author":"Schulman"},{"key":"10.1016\/j.neucom.2026.134438_bib0350","author":"Schulman"},{"key":"10.1016\/j.neucom.2026.134438_bib0355","author":"Du"},{"key":"10.1016\/j.neucom.2026.134438_bib0360","article-title":"Heterogeneous multi-agent reinforcement learning for zero-shot scalable collaboration","author":"Guo","year":"2025","journal-title":"Neurocomputing"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018369?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018369?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T07:39:30Z","timestamp":1783496370000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226018369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":72,"alternative-id":["S0925231226018369"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134438","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MeMAT: Multi-agent transformer with deep long-term memory, short-term memory, and persistent memory","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134438","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":"134438"}}