Recognition: unknown
AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 16 Pith papers
-
AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks
AgentSocialBench demonstrates that privacy preservation is fundamentally harder in human-centered agentic social networks than in single-agent cases due to cross-domain coordination pressures and an abstraction parado...
-
ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles
ScioMind combines anchoring-based belief updates, hierarchical memory, and dynamic profiles in LLM multi-agent systems to produce more stable, diverse, and psychologically aligned opinion trajectories than prior fixed...
-
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Proposes a levels x laws taxonomy for world models in AI agents, defining L1-L3 capabilities across physical, digital, social, and scientific regimes while reviewing over 400 works to outline a roadmap for advanced ag...
-
AI-Gram: When Visual Agents Interact in a Social Network
Autonomous visual AI agents spontaneously form image reply chains, maintain stable individual styles, and produce richer style-diverse conversations than single agents can achieve alone.
-
Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data
MALMAS is a memory-augmented multi-agent LLM system that generates diverse, high-quality features for tabular data via agent decomposition, routing, and iterative memory-guided refinement.
-
WhatIf: Interactive Exploration of LLM-Powered Social Simulations for Policy Reasoning
WhatIf provides an interactive platform for real-time exploration of LLM-driven social simulations, enabling policymakers to iteratively test plans, reflect on assumptions, and uncover vulnerabilities in emergency pre...
-
IntervenSim: Intervention-Aware Social Network Simulation for Opinion Dynamics
IntervenSim is an intervention-aware social network simulation that couples source interventions with crowd interactions in a feedback loop, improving MAPE by 41.6% and DTW by 66.9% over prior static frameworks on rea...
-
Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition
Market-Bench is a new multi-agent benchmark showing that LLMs display large performance gaps in economic tasks, with only a few consistently growing capital while most break even despite similar ad quality.
-
A Survey on LLM-based Conversational User Simulation
A survey that introduces a taxonomy for LLM-based conversational user simulation, analyzes core techniques and evaluation methods, and identifies open challenges in the field.
-
Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents
Large-scale experiments on two million agents reveal that collective intelligence does not emerge from scale alone due to sparse and shallow interactions.
-
Topology-Aware LLM-Driven Social Simulation: A Unified Framework for Efficient and Realistic Agent Dynamics
TopoSim integrates network topology into LLM agent simulations via backbone units and heterogeneous influence to cut token use 50-90% while improving fidelity to real-world structures.
-
TrafficClaw: Generalizable Urban Traffic Control via Unified Physical Environment Modeling
TrafficClaw creates a single runtime environment for heterogeneous urban traffic subsystems and deploys an LLM agent with spatiotemporal reasoning to deliver robust control that generalizes across unseen scenarios.
-
EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution
EvoSpark introduces Stratified Narrative Memory, Generative Mise-en-Scène, and a Unified Narrative Operation Engine to sustain coherent long-horizon narratives in LLM-based multi-agent societies.
-
Evaluating Cooperation in LLM Social Groups through Elected Leadership
Elected leadership in LLM multi-agent simulations of common-pool resource governance raises social welfare scores by 55.4% and survival time by 128.6%.
-
When simulations look right but causal effects go wrong: Large language models as behavioral simulators
LLMs reproduce observed attitudinal patterns in climate interventions reasonably well but diverge on causal effect estimates, with descriptive fit failing to predict causal accuracy across interventions and outcomes.
-
Agentic Microphysics: A Manifesto for Generative AI Safety
The authors introduce agentic microphysics and generative safety to link local agent interactions to population-level risks in agentic AI through a causally explicit framework.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.