Overview

Human behavior simulation builds computational accounts of how people make decisions, interact, and change over time, from individual choices to crowd and population dynamics. Methods range from cognitive and game-theoretic models, agent-based modeling, and reinforcement learning to language-model agents grounded in surveys, interviews, behavioral traces, psychological traits, or memory. Applications include opinion and market dynamics, mobility and traffic, evacuation, education, healthcare, and testing interactive AI systems. A central challenge is validating more than plausible outputs or aggregate averages: simulations must reproduce human response distributions, individual differences, interaction-driven change, and remain robust across prompts, populations, and settings.

Latest papers

CardsList

251 papers18 papers in the last four weeks, up 13% on the four weeks before. 0.1% of all new papers.

  1. From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation

    Jul 25, 2025Patrick Taillandier, Jean Daniel Zucker, Arnaud Grignard +4Human Behavior SimulationComputational Social Science

  2. LLM-Based Social Simulations Require a Boundary

    Jun 24, 2025Zengqing Wu, Run Peng, Takayuki Ito +2LLM EvaluationHuman Behavior Simulation

  3. Modeling Earth-Scale Human-Like Societies with One Billion Agents

    Jun 7, 2025Haoxiang Guan, Jiyan He, Liyang Fan +10Human Behavior SimulationComputational Social Science

  4. SOCIA-∇\nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation

    May 17, 2025Yuncheng Hua, Sion Weatherhead, Mehdi Jafari +2Large Language Model-Based SimulationCode Generation

  5. AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations

    Apr 13, 2025Jenny Ma, Riya Sahni, Karthik Sreedhar +1Multi-Agent LLM SystemsHuman Behavior Simulation

  6. LLM-based Human Simulations Have Not Yet Been Reliable

    Jan 15, 2025Qian Wang, Jiaying Wu, Zichen Jiang +6Human Behavior Simulation

  7. AI Simulations Grounded in Rich Self-Reports Increase Accuracy and Reduce Distortion

    Nov 15, 2024Joon Sung Park, Carolyn Q. Zou, Jonne Kamphorst +8Personality Modeling in Language ModelsHuman Behavior Simulation

  8. When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments

    Jul 15, 2024Chong Zhang, Xinyi Liu, Zhongmou Zhang +10Multi-Agent LLM SystemsHuman Behavior Simulation

  9. Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory

    Jun 20, 2024Gordon Dai, Weijia Zhang, Jinhan Li +5Large Language Model-Based Social SimulationMulti-Agent LLM Systems

  10. Simulation of Crowd Egress with Environmental Stressors

    Jun 3, 2022Peng Wang, Xiaoda Wang, Peter Luh +4Pedestrian Behavior ModelingHuman Behavior Simulation