mlsanityData to 14 Oct 2026

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

arXiv 2502.08691 ↗First posted 12 Feb 2025cs.SI cs.AIcited by 186

On the map: World models → World models for language agents

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 186 papers in the map (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 43 of its 121 references that are in the map. First posted on arXiv 12 Feb 2025.

Builds on

43 of 121 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Project Sid: Many-agent simulations toward AI civilization31 Oct
  2. 2024GenSim: A General Social Simulation Platform with Large Language Model based Agents6 Oct
  3. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  4. 2023EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities16 Oct
  5. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf9 Sep
  6. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agents27 Jul
  7. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr
  8. 2023Evaluating Large Language Models in Theory of Mind Tasks4 Feb

Other references · 35

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  6. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  7. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  8. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  9. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  10. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  11. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 527
  12. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
23 more
  1. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 367
  2. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 289
  3. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
  4. 2024LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individualscited by 249
  5. 2024Large Language Model-Brained GUI Agents: A Surveycited by 162
  6. 2023User Behavior Simulation with Large Language Model based Agentscited by 140
  7. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 132
  8. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 121
  9. 2019CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenariocited by 115
  10. 2023On Generative Agents in Recommendationcited by 90
  11. 2023Training Socially Aligned Language Models on Simulated Social Interactionscited by 78
  12. 2024Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulationcited by 71
  13. 2024Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Informationcited by 49
  14. 2024Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulationcited by 46
  15. 2024ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agentscited by 35
  16. 2024OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agentscited by 35
  17. 2024Simulating Human-like Daily Activities with Desire-driven Autonomycited by 30
  18. 2024Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?cited by 26
  19. 2025Emergence of polarization in networks of large language model agentscited by 26
  20. 2023Empowering Working Memory for Large Language Model Agentscited by 18
  21. 2024Evolving AI Collectives to Enhance Human Diversity and Enable Self-Regulationcited by 13
  22. 2020Emergence of polarized ideological opinions in multidimensional topic spacescited by 9
  23. 2024Casevo: A Cognitive Agents and Social Evolution Simulatorcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 76; 2026: 110.

186 papers.

Sort:

By area:

  1. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 223
  2. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  3. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  4. 2025Agentic Large Language Models, a surveycited by 108
  5. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 94
  6. 2025GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulatorscited by 42
  7. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 29
  8. 2025MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulationscited by 27
  9. 2025Aegis: Automated Error Generation and Attribution for Multi-Agent Systemscited by 22
  10. 2025Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMscited by 19
  11. 2025RecoWorld: Building Simulated Environments for Agentic Recommender Systemscited by 19
  12. 2026A Survey on LLM-based Conversational User Simulationcited by 18
38 more
  1. 2025Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancycited by 17
  2. 2025TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applicationscited by 16
  3. 2025Group size effects and collective misalignment in LLM multi-agent systemscited by 16
  4. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Searchcited by 15
  5. 2026Does Socialization Emerge in AI Agent Society? A Case Study of Moltbookcited by 15
  6. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 14
  7. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 14
  8. 2025Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspectivecited by 13
  9. 2025Simulating Society Requires Simulating Thoughtcited by 13
  10. 2025MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Frameworkcited by 12
  11. 2025SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worldscited by 12
  12. 2025YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Modelscited by 11
  13. 2025Agent Guide: A Simple Agent Behavioral Watermarking Frameworkcited by 10
  14. 2025Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Researchcited by 10
  15. 2025From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulationcited by 10
  16. 2025Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicitycited by 9
  17. 2025Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulationcited by 9
  18. 2025Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Studycited by 8
  19. 2025Modeling Earth-Scale Human-Like Societies with One Billion Agentscited by 8
  20. 2025Emergent Social Dynamics of LLM Agents in the El Farol Bar Problemcited by 8
  21. 2026Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Auditscited by 8
  22. 2025Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AIcited by 7
  23. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7
  24. 2026AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networkscited by 7
  25. 2026More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaborationcited by 7
  26. 2026FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systemscited by 7
  27. 2026MatrAIx: Simulating the World with 8.3 Billion Persona Agentscited by 7
  28. 2025Agentic Services Computingcited by 6
  29. 2025textttBluePrint: A Social Media User Dataset for LLM Persona Evaluation and Trainingcited by 6
  30. 2025EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulationcited by 5
  31. 2025CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Modelscited by 5
  32. 2026Building Social World Models with Large Language Modelscited by 5
  33. 2025CAMS: A CityGPT-Powered Agentic Framework for Urban Human Mobility Simulationcited by 4
  34. 2025Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applicationscited by 4
  35. 2025Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulationscited by 4
  36. 2025Through the Lens of Human-Human Collaboration: A Configurable Research Platform for Exploring Human-Agent Collaborationcited by 4
  37. 2026TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agentscited by 4
  38. 2026SwarmWorld: Stigmergic technological evolution in societies of language-model agentscited by 4

50 most cited of 186 All 186 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents
  2. 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users
  3. 2025Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations
  4. 2024LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities
  5. 2024Sense and Sensitivity: Evaluating the simulation of social dynamics via Large Language Models
  6. 2026Social Simulations: from Agent-Based Modeling to Digital Twins
  7. 2023Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial Intelligence
  8. 2025Don't Trust Generative Agents to Mimic Communication on Social Networks Unless You Benchmarked their Empirical Realism