{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:13:45Z","timestamp":1776680025233,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570775","type":"print"},{"value":"9789819570782","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\/978-981-95-7078-2_6","type":"book-chapter","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:31:48Z","timestamp":1776677508000},"page":"84-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["IB-ToM: Human-AI Coordination for\u00a0Unseen Partners with\u00a0Evolving Strategies"],"prefix":"10.1007","author":[{"given":"Zheng","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihang","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingkai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixiao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyin","family":"Piao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"6_CR1","unstructured":"Bansal, T., Pachocki, J., Sidor, S., Sutskever, I., Mordatch, I.: Emergent complexity via multi-agent competition. CoRR arxiv:1710.03748 (2017)"},{"key":"6_CR2","unstructured":"Bernstein, D.S., Zilberstein, S., Immerman, N.: The complexity of decentralized control of markov decision processes. CoRR arxiv:1301.3836 (2013)"},{"key":"6_CR3","unstructured":"Carroll, M., et al.: On the utility of learning about humans for human-ai coordination. CoRR arxiv:1910.05789 (2019)"},{"key":"6_CR4","unstructured":"Chung, J., G\u00fcl\u00e7ehre, \u00c7., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR arxiv:1412.3555 (2014)"},{"key":"6_CR5","unstructured":"Cross, L., Xiang, V., Bhatia, A., Yamins, D.L., Haber, N.: Hypothetical minds: scaffolding theory of mind for multi-agent tasks with large language models (2024)"},{"key":"6_CR6","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Advances in Neural Information Processing Systems (2016)"},{"key":"6_CR7","unstructured":"Hu, H., Lerer, A., Foerster, J., Brown, N.: \u201cother-play\u201d for zero-shot coordination. In: International Conference on Machine Learning (ICML), pp. 4399\u20134410 (2020)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Hussein, A., et\u00a0al.: Imitation learning: a survey of learning methods. ACM Comput. Surv. (2017)","DOI":"10.1145\/3054912"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Jin, Y., Wei, S., Yuan, J., Zhang, X.: Information-bottleneck-based behavior representation learning for multi-agent reinforcement learning. CoRR arxiv:2109.14188 (2021)","DOI":"10.1109\/ICAS49788.2021.9551171"},{"key":"6_CR10","unstructured":"Li, Y., et al.: Cooperative open-ended learning framework for zero-shot coordination (2024)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Liang, Y., Chen, D., Gupta, A., Du, S.S., Jaques, N.: Learning to cooperate with humans using generative agents. In: Globerson, A., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a037, pp. 60061\u201360087. Curran Associates, Inc. (2024)","DOI":"10.52202\/079017-1918"},{"key":"6_CR12","unstructured":"Lupu, A., Cui, B., Hu, H., Foerster, J.: Trajectory diversity for zero-shot coordination. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 7204\u20137213. PMLR (2021)"},{"issue":"86","key":"6_CR13","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(86), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR14","unstructured":"Ng, A.Y., Russell, S., et\u00a0al.: Algorithms for inverse reinforcement learning. In: ICML, vol.\u00a01, p.\u00a02 (2000)"},{"key":"6_CR15","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. CoRR arxiv:1807.03748 (2018)"},{"key":"6_CR16","unstructured":"Pomerleau, D.A.: Alvinn: an autonomous land vehicle in a neural network. In: Advances in Neural Information Processing Systems, vol. 1 (1988)"},{"key":"6_CR17","unstructured":"Raileanu, R., Denton, E., Szlam, A., Fergus, R.: Modeling others using oneself in multi-agent reinforcement learning. In: International Conference on Machine Learning (ICML), pp. 4257\u20134266 (2018)"},{"key":"6_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR arxiv:1707.06347 (2017)"},{"key":"6_CR19","unstructured":"Strouse, D., McKee, K.R., Botvinick, M., Hughes, E., Everett, R.: Collaborating with humans without human data (2022)"},{"key":"6_CR20","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. arXiv preprint physics\/0004057 (2000)"},{"key":"6_CR21","unstructured":"Wang, Y., Zhong, F., Xu, J., Wang, Y.: Tom2c: target-oriented multi-agent communication and cooperation with theory of mind. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Zhao, R., et al.: Maximum entropy population-based training for zero-shot human-ai coordination. In: AAAI Conference on Artificial Intelligence (AAAI), pp. 9125\u20139133 (2023)","DOI":"10.1609\/aaai.v37i5.25758"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7078-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:32:00Z","timestamp":1776677520000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7078-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570775","9789819570782"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7078-2_6","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":"21 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}