{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:14:55Z","timestamp":1792782895154,"version":"4.5.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000275","name":"Leverhulme Trust","doi-asserted-by":"publisher","award":["RPG-2023-050"],"award-info":[{"award-number":["RPG-2023-050"]}],"id":[{"id":"10.13039\/501100000275","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000275","name":"Leverhulme Trust","doi-asserted-by":"publisher","award":["RPG-2023-050"],"award-info":[{"award-number":["RPG-2023-050"]}],"id":[{"id":"10.13039\/501100000275","id-type":"DOI","asserted-by":"publisher"}]},{"name":"TAILOR Connectivity Fund"},{"name":"European Union\u2019s Horizon 2020 research and innovation programme","award":["No 951847"],"award-info":[{"award-number":["No 951847"]}]},{"name":"Flemish Government","id":[{"id":"https:\/\/ror.org\/04qxsrb28","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2026,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In language games a speaker and a listener attempt to coordinate on a shared mapping between words and concepts. The usual approach in the literature is to study convention emergence in well-mixed populations, where pairs of agents are randomly matched to play the role of speaker and listener, respectively. This way of pairing agents can be shown to promote the emergence of a unifying common language in the long run. Despite the theoretical guarantee, convention emergence can be very slow and practically infeasible, especially in large populations with many words and concepts. Here, we propose an alternative approach, where we allow agents to selectively partner with other agents based on their past experience. To this aim, we study Boltzmann Q-learning agents that are curiosity-driven, i.e., more likely to choose partners they misunderstood in the past. We show that this selection method significantly accelerates convention emergence when compared against a random-matching baseline and is even more pronounced when restricting agents\u2019 communication channels or considering an imbalanced number of concepts and words. By inspecting the evolution of the agents\u2019 interaction frequency we see that partner selection induces low treewidth and high degree variance at the early stages of learning, to then converge to a regular graph, which allows for settling misunderstandings in the population at a faster rate than the traditional approaches.<\/jats:p>","DOI":"10.1007\/s10458-026-09771-7","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T03:12:06Z","timestamp":1789528326000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Curiosity-driven partner selection accelerates convention emergence in language games"],"prefix":"10.1007","volume":"40","author":[{"given":"Chin-wing","family":"Leung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Turrini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"9771_CR1","doi-asserted-by":"publisher","unstructured":"Nowak, M. A., & Komarova, N. L. (2001). Towards an evolutionary theory of language. Trends in Cognitive Sciences, 5(7), 288\u2013295. https:\/\/doi.org\/10.1016\/S1364-6613(00)01683-1","DOI":"10.1016\/S1364-6613(00)01683-1"},{"key":"9771_CR2","doi-asserted-by":"publisher","unstructured":"Nowak, M. A., & Krakauer, D. C. (1999). The evolution of language. Proceedings of the National Academy of Sciences, 96(14), 8028\u20138033. https:\/\/doi.org\/10.1073\/pnas.96.14.8028","DOI":"10.1073\/pnas.96.14.8028"},{"key":"9771_CR3","doi-asserted-by":"publisher","unstructured":"de Villiers, J. (2007). The interface of language and theory of mind. Lingua, 117(11), 1858\u20131878. https:\/\/doi.org\/10.1016\/j.lingua.2006.11.006","DOI":"10.1016\/j.lingua.2006.11.006"},{"key":"9771_CR4","volume-title":"Grooming","author":"R Dunbar","year":"1996","unstructured":"Dunbar, R. (1996). Grooming. Cambridge, MA: Gossip and the Evolution of Language. Harvard University Press."},{"key":"9771_CR5","doi-asserted-by":"publisher","unstructured":"Nowak, M. A. (2006). Five rules for the evolution of cooperation. Science, 314(5805), 1560\u20131563. https:\/\/doi.org\/10.1126\/science.1133755","DOI":"10.1126\/science.1133755"},{"key":"9771_CR6","unstructured":"Schieffelin, B., & Ochs, E. (1984). Language acquisition and socialization: Three developmental stories and their implications. In R. Shweder & R. Levine (Eds.), (pp. 276\u2013320). Cambridge University Press."},{"key":"9771_CR7","volume-title":"Origins of Human Communication","author":"M Tomasello","year":"2010","unstructured":"Tomasello, M. (2010). Origins of Human Communication. Mass.; London: MIT Press, Cambridge."},{"key":"9771_CR8","unstructured":"Claus, C., & Boutilier, C. (1998). The dynamics of reinforcement learning in cooperative multiagent systems. In Proceedings of the Fifteenth National\/Tenth Conference on Artificial Intelligence\/Innovative Applications of Artificial Intelligence (pp. 746\u2013752). AAAI \u201998\/IAAI \u201998. American Association for Artificial Intelligence, USA."},{"issue":"3","key":"9771_CR9","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1162\/artl.1995.2.3.319","volume":"2","author":"L Steels","year":"1995","unstructured":"Steels, L. (1995). A self-organizing spatial vocabulary. Artificial Life, 2(3), 319\u2013332.","journal-title":"Artificial Life"},{"issue":"supplement-3","key":"9771_CR10","doi-asserted-by":"publisher","first-page":"10873","DOI":"10.1073\/pnas.1400838111","volume":"111","author":"S Huttegger","year":"2014","unstructured":"Huttegger, S., Skyrms, B., Tarres, P., & Wagner, E. (2014). Some dynamics of signaling games. Proceedings of the National Academy of Sciences, 111(supplement-3), 10873\u201310880.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"9771_CR11","doi-asserted-by":"publisher","unstructured":"B\u00f6rgers, T., & Sarin, R. (1997). Learning through reinforcement and replicator dynamics. Journal of Economic Theory, 77(1), 1\u201314. https:\/\/doi.org\/10.1006\/jeth.1997.2319","DOI":"10.1006\/jeth.1997.2319"},{"key":"9771_CR12","doi-asserted-by":"crossref","unstructured":"Anastassacos, N., Hailes, S., & Musolesi, M. (2020). Partner selection for the emergence of cooperation in multi-agent systems using reinforcement learning. In The Thirty-Fourth AAAI Conference on Artificial Intelligence (pp. 7047\u20137054), AAAI 2020.","DOI":"10.1609\/aaai.v34i05.6190"},{"key":"9771_CR13","unstructured":"Bailey N. T. (1975). The Mathematical Theory of Infectious Diseases and Its Applications. vol. 2nd ediition."},{"issue":"4","key":"9771_CR14","doi-asserted-by":"publisher","first-page":"357","DOI":"10.3233\/AIC-2010-0479","volume":"23","author":"N Salazar","year":"2010","unstructured":"Salazar, N., Rodriguez-Aguilar, J. A., & Arcos, J. L. (2010). Robust coordination in large convention spaces. AI Communications, 23(4), 357\u2013372.","journal-title":"AI Communications"},{"key":"9771_CR15","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s10458-012-9193-x","volume":"26","author":"H Franks","year":"2013","unstructured":"Franks, H., Griffiths, N., & Jhumka, A. (2013). Manipulating convention emergence using influencer agents. Autonomous Agents and Multi-Agent Systems, 26, 315\u2013353.","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"9771_CR16","doi-asserted-by":"crossref","unstructured":"Hasan, M., Raja, A., & Bazzan, A. (2015). Fast convention formation in dynamic networks using topological knowledge. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 29).","DOI":"10.1609\/aaai.v29i1.9434"},{"issue":"1","key":"9771_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-018-9397-9","volume":"33","author":"MR Hasan","year":"2019","unstructured":"Hasan, M. R., Raja, A., & Bazzan, A. (2019). A context-aware convention formation framework for large-scale networks. Autonomous Agents and Multi-Agent Systems, 33(1), 1\u201334.","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"9771_CR18","unstructured":"van Hasselt, H. (2010). Double q-learning. Advances in Neural Information Processing Systems, 23."},{"key":"9771_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lu, W., Hao, J., Wei, J., & Leung, H.-F. (2018). Efficient convention emergence through decoupled reinforcement social learning with teacher-student mechanism. In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems (pp. 795\u2013803).","DOI":"10.65109\/BAZT2231"},{"issue":"5","key":"9771_CR20","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1177\/1059712310384282","volume":"18","author":"SV Segbroeck","year":"2010","unstructured":"Segbroeck, S. V., Jong, S., Now\u00e9, A., Santos, F. C., & Lenaerts, T. (2010). Learning to coordinate in complex networks. Adaptive Behavior, 18(5), 416\u2013427. https:\/\/doi.org\/10.1177\/1059712310384282","journal-title":"Adaptive Behavior"},{"issue":"2","key":"9771_CR21","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1093\/jole\/lzad001","volume":"7","author":"P Van Eecke","year":"2022","unstructured":"Van Eecke, P., Beuls, K., Botoko Ekila, J., & R\u0103dulescu, R. (2022). Language games meet multi-agent reinforcement learning: A case study for the naming game. Journal of Language Evolution, 7(2), 213\u2013223.","journal-title":"Journal of Language Evolution"},{"key":"9771_CR22","unstructured":"Rita, M., Strub, F., Grill, J.-B., Pietquin, O., & Dupoux, E. (2022). On the role of population heterogeneity in emergent communication arXiv:2204.12982 arXiv preprint."},{"key":"9771_CR23","unstructured":"Michel, P., Rita, M., Mathewson, K. W., Tieleman, O., & Lazaridou, A. (2023). Revisiting populations in multi-agent communication. In The Eleventh International Conference on Learning Representations."},{"key":"9771_CR24","first-page":"17579","volume":"34","author":"J Kim","year":"2021","unstructured":"Kim, J., & Oh, A. (2021). Emergent communication under varying sizes and connectivities. Advances in Neural Information Processing Systems, 34, 17579\u201317591.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"9771_CR25","unstructured":"Fitzgerald, N. (2019). To populate is to regulate arXiv:1911.04362 arXiv preprint."},{"key":"9771_CR26","doi-asserted-by":"crossref","unstructured":"Leung, C., & Turrini, P. (2024). Learning partner selection rules that sustain cooperation in social dilemmas with the option of opting out. In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. AAMAS.","DOI":"10.65109\/JTRB7413"},{"key":"9771_CR27","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A. A., & Darrell, T. (2017). Curiosity-driven exploration by self-supervised prediction. In International Conference on Machine Learning (pp. 2778\u20132787). PMLR.","DOI":"10.1109\/CVPRW.2017.70"},{"key":"9771_CR28","unstructured":"Cordova, C., Taverner, J., Del Val, E., & Argente, E. (2024). A systematic review of norm emergence in multi-agent systems. arXiv:2412.10609 arXiv preprint."},{"issue":"3","key":"9771_CR29","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C. J., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3), 279\u2013292.","journal-title":"Machine Learning"},{"issue":"4","key":"9771_CR30","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1017\/S0963548399003867","volume":"8","author":"A Steger","year":"1999","unstructured":"Steger, A., & Worlmald, N. C. (1999). Generating random regular graphs quickly. Combinatorics, Probability and Computing, 8(4), 377\u2013396.","journal-title":"Combinatorics, Probability and Computing"},{"key":"9771_CR31","doi-asserted-by":"crossref","unstructured":"Barab\u00e1si, A.-L., & Albert, R. (1999). Emergence of scaling in random networks. Science, 286(5439), 509\u2013512.","DOI":"10.1126\/science.286.5439.509"},{"key":"9771_CR32","doi-asserted-by":"crossref","unstructured":"Watts, D. J., & Strogatz, S. H. (1998). Collective dynamics of \u2018small-world\u2019networks. Nature, 393(6684), 440\u2013442.","DOI":"10.1038\/30918"},{"key":"9771_CR33","doi-asserted-by":"publisher","DOI":"10.25080\/TCWV9851","volume-title":"Exploring network structure, dynamics, and function using networkx","author":"A Hagberg","year":"2008","unstructured":"Hagberg, A., Swart, P. J., & Schult, D. A. (2008). Exploring network structure, dynamics, and function using networkx. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States): Technical report."},{"key":"9771_CR34","doi-asserted-by":"crossref","unstructured":"Bertele, U., & Brioschi, F. (1973). On non-serial dynamic programming. Journal of Combinatorial Theory, Series A, 14(2), 137\u2013148.","DOI":"10.1016\/0097-3165(73)90016-2"},{"issue":"3","key":"9771_CR35","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/j.ic.2009.03.008","volume":"208","author":"HL Bodlaender","year":"2010","unstructured":"Bodlaender, H. L., & Koster, A. M. (2010). Treewidth computations i. Upper bounds. Information and Computation, 208(3), 259\u2013275.","journal-title":"Information and Computation"},{"key":"9771_CR36","doi-asserted-by":"crossref","unstructured":"Diestel R. (2010). Graph Theory, 4th edn. Graduate Texts in Mathematics, (vol. 173). Springer, Heidelberg; New York.","DOI":"10.1007\/978-3-642-14279-6"},{"key":"9771_CR37","doi-asserted-by":"publisher","unstructured":"Roca, C. P., Cuesta, J. A., & S\u00e1nchez, A. (2009). Evolutionary game theory: Temporal and spatial effects beyond replicator dynamics. Physics of Life Reviews, 6(4), 208\u2013249. https:\/\/doi.org\/10.1016\/j.plrev.2009.08.001","DOI":"10.1016\/j.plrev.2009.08.001"},{"key":"9771_CR38","doi-asserted-by":"publisher","unstructured":"Traulsen, A., Hauert, C., Silva, H. D., Nowak, M. A., & Sigmund, K. (2009). Exploration dynamics in evolutionary games. Proceedings of the National Academy of Sciences, 106(3), 709\u2013712. https:\/\/doi.org\/10.1073\/pnas.0808450106","DOI":"10.1073\/pnas.0808450106"},{"key":"9771_CR39","doi-asserted-by":"crossref","unstructured":"Leung C.-w, Hu S, & Leung H.-f. (2024). The stochastic evolutionary dynamics of softmax policy gradient in games. In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (pp. 1101\u20131109). AAMAS \u201924. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC.","DOI":"10.65109\/MLSQ9433"},{"key":"9771_CR40","unstructured":"Leung, C., Lenaerts, T., & Turrini, P. (2024). To promote full cooperation in social dilemmas, agents need to unlearn loyalty. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (pp. 111\u2013119), IJCAI 2024. https:\/\/www.ijcai.org\/proceedings\/2024\/13"},{"key":"9771_CR41","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/j.artint.2015.08.003","volume":"229","author":"D Nunes","year":"2015","unstructured":"Nunes, D., & Antunes, L. (2015). Modelling structured societies: A multi-relational approach to context permeability. Artificial Intelligence, 229, 175\u2013199.","journal-title":"Artificial Intelligence"}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-026-09771-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10458-026-09771-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-026-09771-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T03:12:23Z","timestamp":1789528343000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10458-026-09771-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["9771"],"URL":"https:\/\/doi.org\/10.1007\/s10458-026-09771-7","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-9682718\/v1","asserted-by":"object"}]},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"assertion":[{"value":"11 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"45"}}