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

TL;DR

AgentSociety is a large-scale LLM-driven social simulation platform that models complex human behaviors and societal issues, enabling scalable experiments and insights into social dynamics.

Contribution

It introduces a novel large-scale social simulator integrating LLM agents, environmental realism, and a simulation engine for studying social phenomena.

Findings

Simulated social lives for over 10,000 agents with 5 million interactions.

Demonstrated alignment of simulation outcomes with real-world social experiments.

Showcased the platform's utility in analyzing issues like polarization and policy impacts.

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 five key social issues: polarization, the spread of inflammatory messages, the effects of universal basic income policies, the impact of external shocks such as hurricanes, and urban sustainability. These five 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.