{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T07:02:34Z","timestamp":1780729354785,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819214617","type":"print"},{"value":"9789819214624","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-92-1462-4_36","type":"book-chapter","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:46:43Z","timestamp":1780728403000},"page":"458-469","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM-Guided Role Assignment and\u00a0Coordination in\u00a0Multi-Agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Wei","family":"Xiong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingrui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Heng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiebo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengze","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,7]]},"reference":[{"key":"36_CR1","unstructured":"Albrecht, S.V., Ramamoorthy, S.: A game-theoretic model and best-response learning method for ad hoc coordination in multiagent systems (2015). arXiv:1506.01170 arXiv preprint"},{"key":"36_CR2","unstructured":"Christianos, F., Papoudakis, G., Rahman, M.A., Albrecht, S.V.: Scaling multi-agent reinforcement learning with selective parameter sharing. In: International Conference on Machine Learning, pp. 1989\u20131998 (2021) PMLR"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Dastani, M., Dignum, V., Dignum, F.: Role-assignment in open agent societies. In: Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 489\u2013496 (2003)","DOI":"10.1145\/860575.860654"},{"issue":"2","key":"36_CR4","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","volume":"55","author":"S Gronauer","year":"2022","unstructured":"Gronauer, S., Diepold, K.: Multi-agent deep reinforcement learning: a survey. Artif. Intell. Rev. 55(2), 895\u2013943 (2022)","journal-title":"Artif. Intell. Rev."},{"key":"36_CR5","unstructured":"Hu, S., Xie, C., Liang, X., Chang, X.: Policy diagnosis via measuring role diversity in cooperative multi-agent RL. In: International Conference on Machine Learning, pp. 9041\u20139071 (2022) PMLR"},{"key":"36_CR6","unstructured":"Hu, Z., Zhang, Z., Li, H., Chen, C., Ding, H., Wang, Z.: Attention-guided contrastive role representations for multi-agent reinforcement learning, (2023). arXiv:2312.04819 arXiv preprint"},{"key":"36_CR7","unstructured":"H\u00fcttenrauch, M., \u0160o\u0161i\u0107, A., Neumann, G.: Guided deep reinforcement learning for swarm systems (2017). arXiv:1709.06011 arXiv preprint"},{"key":"36_CR8","unstructured":"Kim, W., Sung, Y.: An adaptive entropy-regularization framework for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 16829\u201316852 (2023) PMLR"},{"issue":"01","key":"36_CR9","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1142\/S0218194018500043","volume":"28","author":"KM Lhaksmana","year":"2018","unstructured":"Lhaksmana, K.M., Murakami, Y., Ishida, T.: Role-based modeling for designing agent behavior in self-organizing multi-agent systems. Int. J. Software Eng. Knowl. Eng. 28(01), 79\u201396 (2018)","journal-title":"Int. J. Software Eng. Knowl. Eng."},{"key":"36_CR10","first-page":"3991","volume":"34","author":"C Li","year":"2021","unstructured":"Li, C., Wang, T., Wu, C., Zhao, Q., Yang, J., Zhang, C.: Celebrating diversity in shared multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 34, 3991\u20134002 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR11","first-page":"87908","volume":"37","author":"H Li","year":"2024","unstructured":"Li, H., et al.: Language grounded multi-agent reinforcement learning with human-interpretable communication. Adv. Neural. Inf. Process. Syst. 37, 87908\u201387933 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR12","unstructured":"Lin, M., et al.: Speaking the language of teamwork: LLM-guided credit assignment in multi-agent reinforcement learning (2025). arXiv:2502.03723 arXiv preprint"},{"key":"36_CR13","unstructured":"Liu, B., Liu, Q., Stone, P., Garg, A., Zhu, Y., Anandkumar, A.: Coach-player multi-agent reinforcement learning for dynamic team composition. In: International Conference on Machine Learning, pp. 6860\u20136870. PMLR (2021)"},{"key":"36_CR14","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, p. 30. (2017)"},{"key":"36_CR15","unstructured":"Matsuyama, K., Su, K., Wang, J., Ye, D., Lu, Z.: Cord: Generalizable cooperation via role diversity (2025). arXiv:2501.02221 arXiv preprint"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Nagpal, K., Dong, D., Bouvier, J.B., Mehr, N.: Leveraging large language models for effective and explainable multi-agent credit assignment, (2025). arXiv:2502.16863 arXiv preprint","DOI":"10.65109\/NOKW1037"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A., Amato, C.: A concise introduction to decentralized POMDPs 1 (2016) Springer","DOI":"10.1007\/978-3-319-28929-8_1"},{"key":"36_CR18","unstructured":"Qu, Y., et al.: Choices are more important than efforts: Llm enables efficient multi-agent exploration. arXiv preprint arXiv:2410.02511 (2024)"},{"key":"36_CR19","first-page":"22166","volume":"36","author":"Y Qu","year":"2023","unstructured":"Qu, Y., et al.: Hokoff: real game dataset from honor of kings and its offline reinforcement learning benchmarks. Adv. Neural. Inf. Process. Syst. 36, 22166\u201322190 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"178","key":"36_CR20","first-page":"1","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Samvelyan, M., De Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21(178), 1\u201351 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"36_CR21","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge (2019). arXiv:1902.04043 arXiv preprint"},{"key":"36_CR22","first-page":"5711","volume":"35","author":"J Shao","year":"2022","unstructured":"Shao, J., Lou, Z., Zhang, H., Jiang, Y., He, S., Ji, X.: Self-organized group for cooperative multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 5711\u20135723 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"36_CR23","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10458-007-9023-8","volume":"16","author":"M Sims","year":"2008","unstructured":"Sims, M., Corkill, D., Lesser, V.: Automated organization design for multi-agent systems. Auton. Agent. Multi-Agent Syst. 16(2), 151\u2013185 (2008)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"36_CR24","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5887\u20135896 (2019) PMLR"},{"key":"36_CR25","unstructured":"Sun, C., Huang, S., Pompili, D.: LLM-based multi-agent reinforcement learning: Current and future directions (2024). arXiv:2405.11106 arXiv preprint"},{"key":"36_CR26","unstructured":"Wang, T., Dong, H., Lesser, V., Zhang, C.: Roma: Multi-agent reinforcement learning with emergent roles (2020). arXiv:2003.08039 arXiv preprint"},{"key":"36_CR27","unstructured":"Wang, T., Gupta, T., Mahajan, A., Peng, B., Whiteson, S., Zhang, C.: Rode: Learning roles to decompose multi-agent tasks (2020). arXiv:2010.01523 arXiv preprint"},{"issue":"8","key":"36_CR28","doi-asserted-by":"publisher","first-page":"8243","DOI":"10.1109\/TVT.2020.2997896","volume":"69","author":"T Wu","year":"2020","unstructured":"Wu, T., et al.: Multi-agent deep reinforcement learning for urban traffic light control in vehicular networks. IEEE Trans. Veh. Technol. 69(8), 8243\u20138256 (2020)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Xu, Z., Lyu, Y., Pan, Q., Hu, J., Zhao, C., Liu, S.: Multi-vehicle flocking control with deep deterministic policy gradient method. In: IEEE 14th International Conference on Control and Automation (ICCA), pp. 306\u2013311. IEEE (2018)","DOI":"10.1109\/ICCA.2018.8444355"},{"key":"36_CR30","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"36_CR31","first-page":"1698","volume":"35","author":"M Yang","year":"2022","unstructured":"Yang, M., Zhao, J., Hu, X., Zhou, W., Zhu, J., Li, H.: LDSA: learning dynamic subtask assignment in cooperative multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 1698\u20131710 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR32","first-page":"24611","volume":"35","author":"C Yu","year":"2022","unstructured":"Yu, C., et al.: The surprising effectiveness of PPO in cooperative multi-agent games. Adv. Neural. Inf. Process. Syst. 35, 24611\u201324624 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR33","unstructured":"Zhang, Y., et\u00a0al.: LLM as a mastermind: A survey of strategic reasoning with large language models. arxiv 2024. arXiv preprint arXiv:2404.01230"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-1462-4_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:46:48Z","timestamp":1780728408000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-1462-4_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819214617","9789819214624"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-1462-4_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"7 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}