Social simulation through large language model (LLM) agents is a promising approach to explore and validate hypotheses related to social science questions and LLM agents behavior. We present SOTOPIA-S4, a fast, flexible, and scalable social simulation system that addresses the technical barriers of current frameworks while enabling practitioners to generate multi-turn and multi-party LLM-based interactions with customizable evaluation metrics for hypothesis testing. SOTOPIA-S4 comes as a pip package that contains a simulation engine, an API server with flexible RESTful APIs for simulation management, and a web interface that enables both technical and non-technical users to design, run, and analyze simulations without programming. We demonstrate the usefulness of SOTOPIA-S4 with two use cases involving dyadic hiring negotiation and multi-party planning scenarios.
@article{arxiv.2504.16122,
title = {SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation},
author = {Xuhui Zhou and Zhe Su and Sophie Feng and Jiaxu Zhou and Jen-tse Huang and Hsien-Te Kao and Spencer Lynch and Svitlana Volkova and Tongshuang Sherry Wu and Anita Woolley and Hao Zhu and Maarten Sap},
journal= {arXiv preprint arXiv:2504.16122},
year = {2025}
}
Comments
The first author and the second author contributed equally