SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users
This addresses social simulation problems for social science researchers, offering a scalable framework with real-world user data.
The paper tackles alignment challenges in social simulation by introducing SocioVerse, an LLM-agent-driven world model with four alignment components and a user pool of 10 million real individuals. Results from large-scale experiments in politics, news, and economics show it can reflect population dynamics while ensuring diversity, credibility, and representativeness.
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.