SocioVerse：基于LLM智能体与千万级真实用户池的社会模拟世界模型

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

April 14, 2025

作者: Xinnong Zhang, Jiayu Lin, Xinyi Mou, Shiyue Yang, Xiawei Liu, Libo Sun, Hanjia Lyu, Yihang Yang, Weihong Qi, Yue Chen, Guanying Li, Ling Yan, Yao Hu, Siming Chen, Yu Wang, Jingxuan Huang, Jiebo Luo, Shiping Tang, Libo Wu, Baohua Zhou, Zhongyu Wei

cs.AI

摘要

社会仿真正通过模拟虚拟个体与其环境之间的互动来建模人类行为，从而革新传统社会科学研究。随着大语言模型（LLMs）的最新进展，这一方法在捕捉个体差异和预测群体行为方面展现出日益增长的潜力。然而，现有方法在环境、目标用户、互动机制及行为模式等方面面临对齐挑战。为此，我们提出了SocioVerse，一个基于LLM智能体的社会仿真世界模型。我们的框架包含四个强大的对齐组件和一个包含1000万真实个体的用户池。为验证其有效性，我们在政治、新闻和经济三个不同领域进行了大规模仿真实验。结果表明，SocioVerse能够反映大规模人口动态，同时通过标准化程序和最小化人工调整，确保了多样性、可信度和代表性。

English

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.