SocioVerse：一個由LLM代理驅動的社會模擬世界模型，擁有千萬真實用戶池

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

社會模擬正通過虛擬個體與其環境之間的互動來建模人類行為，從而革新傳統的社會科學研究。隨著大型語言模型（LLMs）的最新進展，這種方法在捕捉個體差異和預測群體行為方面展現出日益增長的潛力。然而，現有方法在環境、目標用戶、互動機制和行為模式方面面臨著對齊挑戰。為此，我們引入了SocioVerse，這是一個基於LLM代理驅動的社會模擬世界模型。我們的框架具備四個強大的對齊組件和一個包含1000萬真實個體的用戶池。為驗證其有效性，我們在政治、新聞和經濟三個不同領域進行了大規模模擬實驗。結果表明，SocioVerse能夠反映大規模人口動態，同時通過標準化程序和最少的手動調整確保多樣性、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.