Large Language Model-Based Social Simulation

Follow this topic Ask about this topic

This field uses language-model agents to model people interacting through networks, institutions, and shared environments, studying outcomes such as opinion change, cooperation, norms, mobility, and policy responses. Common approaches ground agents in surveys, interviews, behavioral histories, or psychological profiles, then combine prompting or fine-tuning with agent-based models, games, memory, and network dynamics. Researchers validate simulations against human surveys, experiments, and real-world traces, measuring both individual response distributions and collective patterns over time. A central challenge is that plausible dialogue or accurate averages do not ensure faithful individual behavior, diverse populations, causal conclusions, or robust results across models and settings.

Latest papers

261 papers53 papers in the last four weeks, up 66% on the four weeks before. 0.3% of all new papers.

This human study did not involve human subjects: Validating LLM simulations as behavioral evidence
Feb 17, 2026Jessica Hullman, David Broska, Huaman Sun +1Large Language Model-Based Social Simulation Human Behavior Simulation
Northwestern University · Stanford University
Bridging Individual and Collective Realism in LLM-Based Human Mobility Simulation via Mobility Scaling-Law Guidance
Feb 17, 2026Hua Yan, Heng Tan, Yu YangHuman Behavior Simulation Large Language Model-Based Social Simulation
Lehigh University · Bethlehem, USA
Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models
Feb 17, 2026Victor De Lima, Jiqun Liu, Grace Hui YangFraming Effects in Language Models Human Behavior Simulation
Georgetown InfoSense Washington, D.C., USA · University of Oklahoma Norman, Oklahoma, USA
AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises
Feb 16, 2026Kenneth PayneStrategic Reasoning Risks in Language Models Large Language Model-Based Social Simulation
King’s College London
Synthetic Reader Panels: Tournament-Based Ideation with LLM Personas for Autonomous Publishing
Feb 16, 2026Fred ZimmermanLLM-as-a-Judge User Simulation
Nimble Books LLC / Big Five Killer LLC.
Large language models replicate and predict human cooperation across experiments in game theory
Nov 6, 2025Andrea Cera Palatsi, Samuel Martin-Gutierrez, Ana S. Cardenal +1LLM Evaluation Game Theory
Department for Computational Social Sciences and Humanities, Barcelona Supercomputing Center · Grupo de Sistemas Complejos, Universidad Polit´ecnica de Madrid · School of Law and Political Science, Universitat Oberta de Catalunya +1
DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents
Oct 29, 2025Yun-Shiuan Chuang, Ruixuan Tu, Chengtao Dai +9Opinion Dynamics Large Language Model-Based Social Simulation
University of Wisconsin–Madison · Google DeepMind · Stanford University
Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management
Sep 30, 2025Runze Zhang, Xiaowei Zhang, Mingyang ZhaoLLM Evaluation Human Behavior Simulation
Department of Industrial Engineering and Decision Analytics, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong
Generalized Multi-agent Social Simulation Framework
Sep 26, 2025Gang Li, Jie Lin, Yining Tang +6Multi-Agent LLM Systems Large Language Model-Based Social Simulation
Zhejiang University, China
The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies
Sep 22, 2025Jiaxu Zhou, Jen-tse Huang, Xuhui Zhou +5LLM Evaluation LLM Auditing
CUHK · JHU · CMU +3
Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
Sep 14, 2025Bingchen Wang, Zi-Yu Khoo, Jingtan WangPreference Modeling Computational Social Science
Independent Researcher, China · AI Singapore, Singapore · School of Computing, National University of Singapore, Singapore
Are LLM Agents Behaviorally Coherent? A Latent Profiling Approach for Social Simulation
Sep 3, 2025James Mooney, Josef Woldense, Zheng Robert Jia +4Behavioral Consistency of LLM Agents LLM Agent Evaluation
Department of Computer Science and Engineering, University of Minnesota · Department of African American & African Studies, University of Minnesota · Department of Sociology, University of Chicago +1
Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative Agents
Aug 24, 2025Hanzhong Zhang, Muhua Huang, Jindong WangComputational Social Science Agent-Based Modeling
William & Mary, Williamsburg, VA, USA · Stanford University, Stanford, CA, USA
Exploring the Limits of Large Language Models as a Reflection of Human Cognition: An Illustration in the Context of Moral Judgement
Aug 9, 2025Sarah Schröder, Thekla Morgenroth, Ulrike Kuhl +2LLM Reliability Large Language Model-Based Social Simulation
Faculty of Technology, Bielefeld University · Department of Psychological Sciences, Purdue University
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 Simulation Computational Social Science
UR MIAT, University of Toulouse, INRAE, Castanet-Tolosan, France · UMI UMMISCO, IRD, Sorbonne University, Bondy, France · UMR IRIT, University Toulouse Capitole, Toulouse, France +2
CoCre-Sam (Kokkuri-san): Modeling Ouija Board as Collective Langevin Dynamics Sampling from Fused Language Models
Jul 16, 2025Tadahiro Taniguchi, Masatoshi Nagano, Haruumi Omoto +1Emergent Communication Large Language Model-Based Social Simulation
Graduate School of Informatics, Kyoto University, Japan · Ritsumeikan University, Japan · University of Reading, UK
LLM-Based Social Simulations Require a Boundary
Jun 24, 2025Zengqing Wu, Run Peng, Takayuki Ito +2LLM Evaluation Human Behavior Simulation
University of Osaka · University of Michigan · Kyoto University +1
Modeling Earth-Scale Human-Like Societies with One Billion Agents
Jun 7, 2025Haoxiang Guan, Jiyan He, Liyang Fan +10Human Behavior Simulation Computational Social Science
University of Science and Technology of China, Hefei, China. · Zhongguancun Academy, Beijing, China. · Zhongguancun Institute of Artificial Intelligence, Beijing, China. +4
Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games
May 30, 2025Neemesh Yadav, Yihuai Lan, Shan Dong +4Theory of Mind Large Language Model-Based Social Simulation
Singapore Management University · Australian National University
LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
Nov 15, 2024Joon Sung Park, Carolyn Q. Zou, Jonne Kamphorst +8Personality Modeling in Language Models Human Behavior Simulation
1Computer Science Department, Stanford University; Stanford, CA, 94305, USA. · Department of Communication Studies, Northwestern University; Evanston, IL 60208, USA. · 7CDSP and CEE, Sciences Po; Paris, 75007, France. +4
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 Simulation Multi-Agent LLM Systems
New York Univeristy, New York, New York, USA · University of illinois at Urbana-Champaign, Urnana, llinois, USA · New York University, New York, New York, USA +1

Feb 17, 2026J/K move · Enter open · S save

This human study did not involve human subjects: Validating LLM simulations as behavioral evidence

Jessica Hullman, David Broska, Huaman Sun, Aaron Shaw

Northwestern University · Stanford University

Large Language Model-Based Social Simulation Human Behavior Simulation Causal Inference

Open paper AskPDF arXiv

A growing literature uses large language models (LLMs) as synthetic participants to generate cost-effective and nearly instantaneous responses in social science experiments. However, there is limited guidance on when such simulations support valid inference about human behavior. We contrast two strategies for obtaining valid estimates of causal effects and clarify the assumptions under which each is suitable for exploratory versus confirmatory research. Heuristic approaches seek to establish that simulated and observed human behavior are interchangeable through prompt engineering, model fine-tuning, and other repair strategies designed to reduce LLM-induced inaccuracies. While useful for many exploratory tasks, heuristic approaches lack the formal statistical guarantees typically required for confirmatory research. In contrast, statistical calibration combines auxiliary human data with statistical adjustments to account for discrepancies between observed and simulated responses. Under explicit assumptions, statistical calibration preserves validity and provides more precise estimates of causal effects at lower cost than experiments that rely solely on human participants. Yet the potential of both approaches depends on how well LLMs approximate the relevant populations. We consider what opportunities are overlooked when researchers focus myopically on substituting LLMs for human participants in a study.