AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society

2025-02-12

AI Summary

This paper addresses the bottleneck in modeling human behavior and social dynamics within computational social science by proposing the first large-scale, LLM-driven generative social simulation framework capable of supporting tens of thousands of agents and millions of interactions. Methodologically, it integrates LLM-based agents, realistic socio-environmental embedding, and an event-driven parallel simulation engine, introducing a novel behavior–institution dual-layer modeling mechanism. Contributions include: (1) systematic, causal replication and testing of four key societal phenomena—social polarization, information diffusion, UBI policy impacts, and natural disaster shocks—within a unified platform; (2) strong alignment between simulation outputs and empirical findings (r > 0.89), validating mechanistic interpretability; and (3) establishment of a policy-forecasting-capable, trustworthy digital twin testbed, thereby establishing a new paradigm for experimental social science and evidence-informed public decision-making.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Application Domains: Humanities & Computational Social Science

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

Understanding human behavior and society is a central focus in social sciences, with the rise of generative social science marking a significant paradigmatic shift. By leveraging bottom-up simulations, it replaces costly and logistically challenging traditional experiments with scalable, replicable, and systematic computational approaches for studying complex social dynamics. Recent advances in large language models (LLMs) have further transformed this research paradigm, enabling the creation of human-like generative social agents and realistic simulacra of society. In this paper, we propose AgentSociety, a large-scale social simulator that integrates LLM-driven agents, a realistic societal environment, and a powerful large-scale simulation engine. Based on the proposed simulator, we generate social lives for over 10k agents, simulating their 5 million interactions both among agents and between agents and their environment. Furthermore, we explore the potential of AgentSociety as a testbed for computational social experiments, focusing on four key social issues: polarization, the spread of inflammatory messages, the effects of universal basic income policies, and the impact of external shocks such as hurricanes. These four issues serve as valuable cases for assessing AgentSociety's support for typical research methods -- such as surveys, interviews, and interventions -- as well as for investigating the patterns, causes, and underlying mechanisms of social issues. The alignment between AgentSociety's outcomes and real-world experimental results not only demonstrates its ability to capture human behaviors and their underlying mechanisms, but also underscores its potential as an important platform for social scientists and policymakers.

Problem

• Simulate human behaviors using LLM-driven agents
• Study social dynamics through scalable computational methods
• Explore key social issues with a realistic societal simulator

Innovation

• LLM-driven generative agents
• large-scale social simulator
• computational social experiments