Tutorial: LLM-based Agentic Simulations for
Social Science

ICWSM 2026 Tutorial

Los Angeles, CA, USA · 26 May, 2026

Overview

← Check Out Our Workshop
Tutorial Type Lecture, case study, and hands-on
Duration 4 hours
Technical Equipment Internet access is required for online demos. Participants are encouraged to bring laptops to engage with the hands-on sessions.

Schedule

Session Topic
Session 1 LLM Simulation for Decision-Making
Hands-on 1 Interactive Exercise
Session 2 Multi-Agent Systems for Social Simulation
Hands-on 2 Interactive Exercise

Suggested Reading

  1. Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation. Abdelnabi, S.; Gomaa, A.; Sivaprasad, S.; Schönherr, L.; and Fritz, M. 2024. NeurIPS 2024 Datasets and Benchmarks Track.
  2. LLMCoordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models. Agashe, S.; Fan, Y.; Reyna, A.; and Wang, X. E. 2025. Findings of ACL: NAACL 2025.
  3. Emergent social conventions and collective bias in LLM populations. Ashery, A. F.; Aiello, L. M.; and Baronchelli, A. 2025. Science Advances, 11(20): eadu9368.
  4. The moral machine experiment. Awad, E.; Dsouza, S.; Kim, R.; Schulz, J.; Henrich, J.; Shariff, A.; Bonnefon, J.-F.; and Rahwan, I. 2018. Nature, 563(7729): 59–64.
  5. Large language models show amplified cognitive biases in moral decision-making. Cheung, V.; Maier, M.; and Lieder, F. 2025. Proceedings of the National Academy of Sciences.
  6. Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions. de Araujo, P. H. L.; Hedderich, M. A.; Modarressi, A.; Schuetze, H.; and Roth, B. 2025.
  7. Improving Factuality and Reasoning in Language Models through Multiagent Debate. Du, Y.; Li, S.; Torralba, A.; Tenenbaum, J. B.; and Mordatch, I. 2024. ICML 2024.
  8. Growing Artificial Societies: Social Science from the Bottom Up. Epstein, J. M.; and Axtell, R. 1996. Brookings Institution Press.
  9. Large language models empowered agent-based modeling and simulation: A survey and perspectives. Gao, C.; Lan, X.; Li, N.; Yuan, Y.; Ding, J.; Zhou, Z.; Xu, F.; and Li, Y. 2024. Humanities and Social Sciences Communications.
  10. From factors to actors: Computational sociology and agent-based modeling. Macy, M. W.; and Willer, R. 2002. Annual Review of Sociology, 28(1): 143–166.
  11. Automated social science: Language models as scientist and subjects. Manning, B. S.; Zhu, K.; and Horton, J. J. 2024. Technical report, National Bureau of Economic Research.
  12. Generative Agents: Interactive Simulacra of Human Behavior. Park, J. S.; O'Brien, J.; Cai, C. J.; Morris, M. R.; Liang, P.; and Bernstein, M. S. 2023. UIST 2023, 1–22.
  13. Generative agent simulations of 1,000 people. Park, J. S.; Zou, C. Q.; Shaw, A.; Hill, B. M.; Cai, C.; Morris, M. R.; Willer, R.; Liang, P.; and Bernstein, M. S. 2024.
  14. Towards Understanding Sycophancy in Language Models. Sharma, M.; Tong, M.; Korbak, T.; Duvenaud, D.; Askell, A.; Bowman, S. R.; et al. 2024. ICLR 2024.
  15. The moral machine experiment on large language models. Takemoto, K. 2024. Royal Society Open Science.
  16. LLM-Based Social Simulations Require a Boundary. Wu, Z.; Peng, R.; Ito, T.; and Xiao, C. 2025.