SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation (2504.16122v1)
Abstract: Social simulation through 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.
- Xuhui Zhou (33 papers)
- Zhe Su (33 papers)
- Sophie Feng (1 paper)
- Jiaxu Zhou (12 papers)
- Jen-tse Huang (46 papers)
- Hsien-Te Kao (5 papers)
- Spencer Lynch (3 papers)
- Svitlana Volkova (24 papers)
- Tongshuang Sherry Wu (1 paper)
- Anita Woolley (3 papers)
- Hao Zhu (212 papers)
- Maarten Sap (86 papers)