{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:17:12Z","timestamp":1783401432704,"version":"3.54.6"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science London","doi-asserted-by":"publisher","award":["23K28064,25K15290"],"award-info":[{"award-number":["23K28064,25K15290"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJSP2128"],"award-info":[{"award-number":["JPMJSP2128"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Comput Soc Sc"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Social media platforms frequently impose restrictive policies to moderate user content, prompting the emergence of creative evasion language strategies. This paper presents a multi-agent framework based on Large Language Models (LLMs) to simulate the iterative evolution of language strategies under regulatory constraints. In this framework, participant agents, as social media users, continuously evolve their language expression, while supervisory agents emulate platform-level regulation by assessing policy violations. To achieve a more faithful simulation, we employ a dual design of language strategies (constraint and expression) to differentiate conflicting goals and utilize an LLM-driven GA (Genetic Algorithm) for the selection, mutation, and crossover of language strategies. The framework is evaluated using two distinct scenarios: an abstract password game and a realistic simulated illicit pet trade scenario. Experimental results demonstrate that as the number of dialogue rounds increases, both the number of uninterrupted dialogue turns and the accuracy of information transmission improve significantly. Furthermore, a user study with 40 participants validates the real-world relevance of the generated dialogues and strategies. Moreover, ablation studies validate the importance of the GA, emphasizing its contribution to long-term adaptability and improved overall results.<\/jats:p>","DOI":"10.1007\/s42001-026-00481-4","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T04:43:36Z","timestamp":1783399416000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Simulation of language evolution under regulated social media platforms: a synergistic approach of large language models and genetic algorithms"],"prefix":"10.1007","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9715-8143","authenticated-orcid":false,"given":"Jinyu","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusei","family":"Ishimizu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Munan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenji","family":"Tei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"issue":"1","key":"481_CR1","doi-asserted-by":"publisher","first-page":"265","DOI":"10.5465\/annals.2022.0188","volume":"19","author":"RA Hunt","year":"2025","unstructured":"Hunt, R. A., Townsend, D. M., Simpson, J. J., Nugent, R., Stallkamp, M., & Bozdag, E. (2025). Digital battlegrounds: The power dynamics and governance of contemporary platforms. Academy of Management Annals, 19(1), 265\u2013297.","journal-title":"Academy of Management Annals"},{"key":"481_CR2","volume-title":"War and peace","author":"W Hua","year":"2023","unstructured":"Hua, W., Fan, L., Li, L., Mei, K., Ji, J., Ge, Y., Hemphill, L., & Zhang, Y. (2023). War and peace. Large Language Model-based Multi-Agent Simulation of World Wars: WarAgent."},{"key":"481_CR3","doi-asserted-by":"publisher","unstructured":"Park, J.S., O\u2019Brien, J., Cai, C.J., Morris, M.R., Liang, P., & Bernstein, M.S. (2023). Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual ACM symposium on user interface software and technology. UIST \u201923. Association for computing machinery. New York, NY, USA. https:\/\/doi.org\/10.1145\/3586183.3606763","DOI":"10.1145\/3586183.3606763"},{"key":"481_CR4","unstructured":"Gao, C., Lan, X., Lu, Z., Mao, J., Piao, J., Wang, H., Jin, D., & Li, Y. (2023). S3: Social-network simulation system with large language model-empowered agents."},{"key":"481_CR5","unstructured":"Fu, Y., Peng, H., Khot, T., & Lapata, M. (2023). Improving language model negotiation with self-play and in-context learning from AI feedback."},{"key":"481_CR6","unstructured":"Xu, Y., Wang, S., Li, P., Luo, F., Wang, X., Liu, W., & Liu, Y. (2023). Exploring large language models for communication games: An empirical study on werewolf."},{"key":"481_CR7","doi-asserted-by":"publisher","unstructured":"Cai, J., Li, J., Zhang, M., Li, M., Wang, C.-S., & Tei, K. (2024). Language evolution for evading social media regulation via LLM-based multi-agent simulation. In: 2024 IEEE Congress on evolutionary computation (CEC) (pp. 1\u201310). https:\/\/doi.org\/10.1109\/CEC60901.2024.10612015","DOI":"10.1109\/CEC60901.2024.10612015"},{"key":"481_CR8","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., & Anadkat, S. (2023). Gpt-4 technical report arXiv:2303.08774 arXiv preprint."},{"key":"481_CR9","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., & Lample, G. (2023). LLaMA: Open and efficient foundation language models."},{"key":"481_CR10","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30."},{"key":"481_CR11","doi-asserted-by":"publisher","unstructured":"Li, J., Zhang, M., Li, N., Weyns, D., Jin, Z., & Tei, K. (2024). Exploring the potential of large language models in self-adaptive systems. In Proceedings of the 19th international symposium on software engineering for adaptive and self-managing systems. SEAMS \u201924 (pp. 77\u201383). Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3643915.3644088","DOI":"10.1145\/3643915.3644088"},{"key":"481_CR12","unstructured":"Zhao, W.X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Liu, Z., Liu, P., Nie, J., & Wen, J.-r. (2023). A survey of large language models. arXiv:abs\/2303.18223"},{"key":"481_CR13","doi-asserted-by":"crossref","unstructured":"Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H.-r., Zhang, J., Chen, Z.-Y., Tang, J., Chen, X., Lin, Y., Zhao, W.X., Wei, Z., &Wen, J.-r. (2023). A survey on large language model based autonomous agents. arXiv:abs\/2308.11432","DOI":"10.1007\/s11704-024-40231-1"},{"key":"481_CR14","doi-asserted-by":"publisher","unstructured":"Li, J., Zhang, M., Li, N., Weyns, D., Jin, Z., & Tei, K. (2024). Generative ai for self-adaptive systems: State of the art and research roadmap. ACM Transactions on Autonomous and Adaptive Systems, 19(3). https:\/\/doi.org\/10.1145\/3686803","DOI":"10.1145\/3686803"},{"key":"481_CR15","doi-asserted-by":"crossref","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., & Ray, A. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730\u201327744. https:\/\/doi.org\/10.48550\/arXiv.2203.02155. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/b1efde53be364a73914f58805a001731-Paper-Conference.pdf","DOI":"10.52202\/068431-2011"},{"key":"481_CR16","doi-asserted-by":"publisher","unstructured":"Wang, C.-S., Yang, H.-L., Li, B.-Y., & Chen, H.-Y. (2023). Can generative ai eliminate speech harms? A study on detection of abusive and hate speech during the covid-19 pandemic. In 2023 IEEE international conference on consumer electronics-Asia (ICCE-Asia) (pp. 1\u20134). https:\/\/doi.org\/10.1109\/ICCE-Asia59966.2023.10326404","DOI":"10.1109\/ICCE-Asia59966.2023.10326404"},{"key":"481_CR17","doi-asserted-by":"publisher","unstructured":"Rothe, M., Lath, R., Kumar, D., Yadav, P., & Aylani, A. (2023). Slang language detection and identification in text. In 2023 14th International conference on computing communication and networking technologies (ICCCNT) (pp. 1\u20135). https:\/\/doi.org\/10.1109\/ICCCNT56998.2023.10308036","DOI":"10.1109\/ICCCNT56998.2023.10308036"},{"key":"481_CR18","doi-asserted-by":"publisher","unstructured":"Seki, Y., & Liu, Y. (2022). Multi-task learning model for detecting internet slang words with two-layer annotation. In 2022 International conference on asian language processing (IALP) (pp. 212\u2013218). https:\/\/doi.org\/10.1109\/IALP57159.2022.9961254","DOI":"10.1109\/IALP57159.2022.9961254"},{"key":"481_CR19","unstructured":"Sun, Z., Zemel, R. S., & Xu, Y. (2019). Slang generation as categorization (pp. 2898\u20132904). CogSci."},{"key":"481_CR20","doi-asserted-by":"crossref","unstructured":"Sun, Z., Zemel, R., & Xu, Y. (2022). Semantically informed slang interpretation arXiv:2205.00616 arXiv preprint.","DOI":"10.18653\/v1\/2022.naacl-main.383"},{"key":"481_CR21","unstructured":"Xu, Z., Yu, C., Fang, F., Wang, Y., & Wu, Y. (2023). Language agents with reinforcement learning for strategic play in the werewolf game."},{"key":"481_CR22","doi-asserted-by":"crossref","unstructured":"Park, J.S., O\u2019Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., & Bernstein, M.S. (2023). Generative agents: Interactive simulacra of human behavior. Proceedings of the 36th annual ACM symposium on user interface software and technology.","DOI":"10.1145\/3586183.3606763"},{"key":"481_CR23","doi-asserted-by":"publisher","unstructured":"Tang, J., Gao, H., Pan, X., Wang, L., Tan, H., Gao, D., Chen, Y., Chen, X., Lin, Y., Li, Y., Ding, B., Zhou, J., Wang, J., & Wen, J.-R. (2025). GenSim: A general social simulation platform with large language model based agents. In N. Dziri, S. X. Ren, & S. Diao (Eds.), Proceedings of the 2025 conference of the nations of the Americas chapter of the association for computational linguistics: Human language technologies (System Demonstrations) (pp. 143\u2013150). Association for Computational Linguistics, Albuquerque, New Mexico. https:\/\/doi.org\/10.18653\/v1\/2025.naacl-demo.15","DOI":"10.18653\/v1\/2025.naacl-demo.15"},{"key":"481_CR24","unstructured":"Yang, Z., Zhang, Z., Zheng, Z., Jiang, Y., Gan, Z., Wang, Z., Ling, Z., Chen, J., Ma, M., & Dong, B. (2024). Oasis: Open agents social interaction simulations on one million agents arXiv:2411.11581 arXiv preprint."},{"key":"481_CR25","doi-asserted-by":"crossref","unstructured":"Atkinson, R.C., & Shiffrin, R.M. (1968). Human memory: A proposed system and its control processes. Psychology of Learning and Motivation, 2, 89\u2013195. Academic Press. https:\/\/doi.org\/10.1016\/S0079-7421(08)60422-3 . https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0079742108604223","DOI":"10.1016\/S0079-7421(08)60422-3"},{"key":"481_CR26","unstructured":"Shi, F., Chen, X., Misra, K., Scales, N., Dohan, D., Chi, E. H., Sch\u00e4rli, N., & Zhou, D. (2023). Large language models can be easily distracted by irrelevant context. International conference on machine learning (pp. 31210\u201331227) PMLR."},{"issue":"3","key":"481_CR27","doi-asserted-by":"publisher","first-page":"494","DOI":"10.6633\/IJNS.201905_21(3).16","volume":"21","author":"X Wang","year":"2019","unstructured":"Wang, X. (2019). Two number-guessing problems plus applications in cryptography. International Journal of Network Security, 21(3), 494\u2013500. https:\/\/doi.org\/10.6633\/IJNS.201905_21(3).16","journal-title":"International Journal of Network Security"},{"key":"481_CR28","doi-asserted-by":"publisher","unstructured":"Bahamazava, K., & Nanda, R. (2022). The shift of darknet illegal drug trade preferences in cryptocurrency: The question of traceability and deterrence. Forensic Science International: Digital Investigation, 40, 301377. https:\/\/doi.org\/10.1016\/j.fsidi.2022.301377","DOI":"10.1016\/j.fsidi.2022.301377"},{"key":"481_CR29","doi-asserted-by":"publisher","unstructured":"Basu, K., & Sen, A. (2020). Monitoring individuals in drug trafficking organizations: A social network analysis. In Proceedings of the 2019 IEEE\/ACM international conference on advances in social networks analysis and mining. ASONAM \u201919 (pp. 480\u2013483). Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3341161.3342938","DOI":"10.1145\/3341161.3342938"},{"key":"481_CR30","doi-asserted-by":"publisher","unstructured":"Tsai, F.-C., Hsu, M.-C., Chen, C.-T., Kao, & D.-Y. (2019). Exploring drug-related crimes with social network analysis. Procedia Computer Science, 159, 1907\u20131917. https:\/\/doi.org\/10.1016\/j.procs.2019.09.363. Knowledge-based and intelligent information & engineering systems: proceedings of the 23rd international conference KES2019","DOI":"10.1016\/j.procs.2019.09.363"},{"key":"481_CR31","doi-asserted-by":"publisher","unstructured":"Wu, J. (2025). \u201chigh energy ahead!\u201d: Exploring chinese adolescents\u2019 pragmatic identities in bullet-screen discourse. Humanities and Social Sciences Communications, 12(1), 167. https:\/\/doi.org\/10.1057\/s41599-025-04475-x","DOI":"10.1057\/s41599-025-04475-x"},{"key":"481_CR32","unstructured":"Research\u00a0Ethics, W.U. (2025). Ethics review procedures concerning research with human subjects. https:\/\/www.waseda.jp\/inst\/ore\/en\/procedures\/human\/. Accessed: 2025-11-05"}],"container-title":["Journal of Computational Social Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42001-026-00481-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42001-026-00481-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42001-026-00481-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T04:44:47Z","timestamp":1783399487000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42001-026-00481-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":32,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["481"],"URL":"https:\/\/doi.org\/10.1007\/s42001-026-00481-4","relation":{},"ISSN":["2432-2717","2432-2725"],"issn-type":[{"value":"2432-2717","type":"print"},{"value":"2432-2725","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]},"assertion":[{"value":"15 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This research received an Institutional Review Board (IRB) exemption under the regulations of the authors\u2019 institution due to its low risk and did not require additional independent review [\n                      \n                      ].","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"This study involved human participants in a low-risk user study conducted in accordance with institutional ethical guidelines. No animal subjects were involved.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human participants or animals"}},{"value":"All participants provided written informed consent before taking part in the study. The consent form detailed the purpose, data usage, and privacy policy of the experiment. No personally identifiable information was collected, and all data will be securely stored and destroyed after three years.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}],"article-number":"50"}}