用百万真实用户和大模型代理构建社会仿真世界
SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users
- 基于1000万真实用户与大模型代理构建社会仿真系统
- 在政治、新闻、经济领域均实现高保真群体行为模拟
- 无需大量人工干预即可保证结果多样性与可信度
社会仿真正通过虚拟个体与环境的互动，变革传统社会科学。随着大语言模型（LLM）的发展，该方法在捕捉个体差异和预测群体行为方面展现出巨大潜力。然而，现有方法在环境对齐、目标用户匹配、交互机制及行为模式一致性方面仍存在挑战。为此，我们提出SocioVerse——一个由大模型代理驱动的社会仿真世界模型。其包含四大对齐组件，并集成1000万真实个体组成的用户池。为验证有效性，我们在政治、新闻、经济三个领域开展大规模仿真实验。结果表明，SocioVerse能准确反映大规模人口动态，在标准化流程下保持多样性、可信度与代表性，且仅需最少的人工调整。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。