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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xinnong, Lin, Jiayu, Mou, Xinyi, Yang, Shiyue, Liu, Xiawei, Sun, Libo, Lyu, Hanjia, Yang, Yihang, Qi, Weihong, Chen, Yue, Li, Guanying, Yan, Ling, Hu, Yao, Chen, Siming, Wang, Yu, Huang, Xuanjing, Luo, Jiebo, Tang, Shiping, Wu, Libo, Zhou, Baohua, Wei, Zhongyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913941914910720
author Zhang, Xinnong
Lin, Jiayu
Mou, Xinyi
Yang, Shiyue
Liu, Xiawei
Sun, Libo
Lyu, Hanjia
Yang, Yihang
Qi, Weihong
Chen, Yue
Li, Guanying
Yan, Ling
Hu, Yao
Chen, Siming
Wang, Yu
Huang, Xuanjing
Luo, Jiebo
Tang, Shiping
Wu, Libo
Zhou, Baohua
Wei, Zhongyu
author_facet Zhang, Xinnong
Lin, Jiayu
Mou, Xinyi
Yang, Shiyue
Liu, Xiawei
Sun, Libo
Lyu, Hanjia
Yang, Yihang
Qi, Weihong
Chen, Yue
Li, Guanying
Yan, Ling
Hu, Yao
Chen, Siming
Wang, Yu
Huang, Xuanjing
Luo, Jiebo
Tang, Shiping
Wu, Libo
Zhou, Baohua
Wei, Zhongyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10157
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users
Zhang, Xinnong
Lin, Jiayu
Mou, Xinyi
Yang, Shiyue
Liu, Xiawei
Sun, Libo
Lyu, Hanjia
Yang, Yihang
Qi, Weihong
Chen, Yue
Li, Guanying
Yan, Ling
Hu, Yao
Chen, Siming
Wang, Yu
Huang, Xuanjing
Luo, Jiebo
Tang, Shiping
Wu, Libo
Zhou, Baohua
Wei, Zhongyu
Computation and Language
Computers and Society
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.
title SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users
topic Computation and Language
Computers and Society
url https://arxiv.org/abs/2504.10157