SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users

Xinnong Zhang, Jiayu Lin, Xinyi Mou, Shiyue Yang, Xiawei Liu +16 more
4/14/2025
cs.CLcs.CY

No official code found. Best implementation: FudanDISC/SocioVerse (182 stars, Apache-2.0, last commit 2026-02-08).

Abstract

Social simulation is transforming traditional social science research by modeling human behavior through interactions between virtual individuals and their environments. With recent advances in large language models (LLMs), this approach has shown growing potential in capturing individual differences and predicting group behaviors. However, existing methods face alignment challenges related to the environment, target users, interaction mechanisms, and behavioral patterns. To this end, we introduce SocioVerse, an LLM-agent-driven world model for social simulation. Our framework features four powerful alignment components and a user pool of 10 million real individuals. To validate its effectiveness, we conducted large-scale simulation experiments across three distinct domains: politics, news, and economics. Results demonstrate that SocioVerse can reflect large-scale population dynamics while ensuring diversity, credibility, and representativeness through standardized procedures and minimal manual adjustments.

View on arXivView PDF

Code Implementations(1)

FudanDISC/SocioVerseCommunity100%
Apache-2.0
18216PythonFeb 25, 20258 months agoApache-2.0

Similar Papers

From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents

90% match1 repo2382024

Social Simulations with Large Language Model Risk Utopian Illusion

89% match2025

AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society

89% match2025

LLM Social Simulations Are a Promising Research Method

88% match2025

Modeling Earth-Scale Human-Like Societies with One Billion Agents

88% match2025

GenSim: A General Social Simulation Platform with Large Language Model based Agents

88% match1 repo872024

Cite this paper

@article{zhang2025socioverse,
  title  = {SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users},
  author = {Xinnong Zhang and Jiayu Lin and Xinyi Mou and Shiyue Yang and Xiawei Liu and Libo Sun and Hanjia Lyu and Yihang Yang and Weihong Qi and Yue Chen and Guanying Li and Ling Yan and Yao Hu and Siming Chen and Yu Wang and Xuanjing Huang and Jiebo Luo and Shiping Tang and Libo Wu and Baohua Zhou and Zhongyu Wei},
  year   = {2025},
  eprint = {2504.10157},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.10157v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.10157.svg)](https://codeofpaper.com/paper/2504.10157)

Discussion