SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Xuhui, Su, Zhe, Feng, Sophie, Zhou, Jiaxu, Huang, Jen-tse, Kao, Hsien-Te, Lynch, Spencer, Volkova, Svitlana, Wu, Tongshuang Sherry, Woolley, Anita, Zhu, Hao, Sap, Maarten
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915253728575488
author Zhou, Xuhui
Su, Zhe
Feng, Sophie
Zhou, Jiaxu
Huang, Jen-tse
Kao, Hsien-Te
Lynch, Spencer
Volkova, Svitlana
Wu, Tongshuang Sherry
Woolley, Anita
Zhu, Hao
Sap, Maarten
author_facet Zhou, Xuhui
Su, Zhe
Feng, Sophie
Zhou, Jiaxu
Huang, Jen-tse
Kao, Hsien-Te
Lynch, Spencer
Volkova, Svitlana
Wu, Tongshuang Sherry
Woolley, Anita
Zhu, Hao
Sap, Maarten
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation
Zhou, Xuhui
Su, Zhe
Feng, Sophie
Zhou, Jiaxu
Huang, Jen-tse
Kao, Hsien-Te
Lynch, Spencer
Volkova, Svitlana
Wu, Tongshuang Sherry
Woolley, Anita
Zhu, Hao
Sap, Maarten
Computers and Society
Artificial Intelligence
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.
title SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2504.16122