Large Language Model-Based Social Simulation

Follow this topic Ask about this topic

Momentum

34 papers in the last four weeks, up 467% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 120

All topics

Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling
Jul 17, 2026Gurkan OzkanHuman Behavior Simulation Large Language Model-Based Social Simulation
Istanbul Technical University
Step-Level Preference Learning for Generative Agents in Social Simulations
Jul 16, 2026Wenchang Gao, Pingyue Sheng, Lanlan Qiu +7Human Preference Modeling Human Behavior Simulation
Shanghai Qi Zhi Institute · Tsinghua University · Xiongan AI Institute +3
Social Simulations: from Agent-Based Modeling to Digital Twins
Jul 15, 2026Erica Cau, Andrea Failla, Valentina Pansanella +1Human Behavior Simulation Agent-Based Modeling
Department of Computer Science, University of Pisa · ISTI-CNR
CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platform
Jul 13, 2026Gustavo H. Santos, Aline Viana, Thiago H SilvaHuman Behavior Simulation Agent-Based Modeling
UTFPR, Brazil · Inria, France · University of Toronto, Canada
Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation
Jul 12, 2026Song-Ze Yu, Joseph Suh, Serina Chang +1Human Behavior Simulation Large Language Model-Based Social Simulation
University of California, Berkeley
A Large Language Model-Driven Agent-Based Modeling Framework with Multi-Round Communication for Simulating Vaccine Opinion Dynamics
Jul 8, 2026Bo Zhang, Na JiangOpinion Dynamics Cognitive Modeling
Thrust of Urban Governance and Design, The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, Guangdong, CHINA · Jinhe Center for Economic Research, Xi’an Jiaotong University Xi’an, Shaanxi, CHINA
LLM-powered reasoning in agent-based modeling
Jul 7, 2026Sifat Afroj Moon, Dakotah Maguire, Adam Spannaus +5Agent-Based Modeling Large Language Model-Based Social Simulation
Oak Ridge National Laboratory · Computational Science and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA · Geospatial Science and Human Security Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA +1
AgoraSim: A Hybrid Agent-Based Modeling Framework
Jul 7, 2026Chung-Chi ChenHuman Behavior Simulation LLM Agent Orchestration
Human-Agent Ally Lab (HAA Lab) National Institute of Informatics, Japan
Will Scaling Improve Social Simulation with LLMs?
Jul 2, 2026Caleb Ziems, William Held, Su Doga Karaca +3Opinion Dynamics Language Model Scaling Laws
Stanford University · Open Athena
SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments
Jul 1, 2026Ziyue Lin, Xinhang Xie, Kangyi Wang +1Pedestrian Behavior Modeling Trajectory Generation
School of Data Science, Fudan University · Shanghai, China
Collective cooperation without individual fidelity in LLM agents
Jun 29, 2026Henrique Ferraz de Arruda, Carlos Gracia Lázaro, Alberto Aleta +1Multi-Agent LLM Systems Human Behavior Simulation
ARAID Foundation, Zaragoza, Spain. · Institute for Biocomputation and Physics of Complex Systems, University of Zaragoza, Zaragoza, Spain. · Universidad San Jorge (USJ), Zaragoza, Spain. +1
Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data
Jun 27, 2026Eun Cheol Choi, Youngrae Kim, Prabhu Pugalenthi +2LLM Alignment LLM Fine-Tuning
University of Southern California, CA, USA.
GenWorld: Empirically Grounded Urban Simulation Infrastructure for Scalable LLM-Agent Studies
Jun 26, 2026Gen Li, Jieyuan Lan, Pengcheng Xu +3Human Behavior Simulation Synthetic Data Generation
Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi-Hiroshima, Japan · Jiangxi Polytechnic University, Jiangxi, China · College of Urban Development and Modern Transportation, Xi’an University of Architecture and Technology, Xi’an, China +1
Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games
Jun 16, 2026Zirui Cheng, Zeyu Shen, Thomas L. Griffiths +1RL for Language Models Cognitive Modeling
1Princeton University
OdysSim: Building Foundation Models for Human Behavior Simulation
Jun 12, 2026Xuhui Zhou, Weiwei Sun, Weihua Du +6Human Behavior Simulation AI Agent Benchmarks
Carnegie Mellon University, Language Technologies Institute
When Plausible Is Not Realistic: Evaluating Human Mobility in LLM-Based Urban Simulation
Jun 11, 2026Gustavo H. Santos, Aline Carneiro Viana, Thiago H. SilvaHuman Behavior Simulation LLM Agent Evaluation
UTFPR, Brazil · Inria, France · U. of Toronto, Canada
AgentSociety 2: An Integrated Research Environment for Executable Social Science
Jun 11, 2026Jinghua Piao, Jun Zhang, Haoyu Huang +16Multi-Agent LLM Systems AI Agents for Scientific Discovery
Department of Electronic Engineering, Tsinghua University · School of Environment, Tsinghua University · School of Public Policy and Management, Tsinghua University +2
MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation
Jun 8, 2026Yongrui Liu, Deyi XiongHuman Behavior Simulation Large Language Model-Based Social Simulation
The International Joint Institute of Tianjin University, Fuzhou, Tianjin University, China · TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China
Agentopia: Long-Term Life Simulation and Learning in Agent Societies
Jun 5, 2026Xintao Wang, Sirui Zheng, Hongqiu Wu +10Multi-Agent LLM Systems Human Behavior Simulation
Fudan University · Independent Researcher · Johns Hopkins University +1
Comparing Sentiment Contagion in AI-Agent and Human Social Networks: Evidence from MOLTBOOK
Jun 4, 2026Elyes Ben chaabane, Savindu Herath, Yash Raj ShresthaSocial Media Analysis Opinion Dynamics
UNIL · ETH Zurich
Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions
Jun 4, 2026Xinnong Zhang, Wanting Shan, Hanjia Lyu +2Counterfactual Evaluation LLM Auditing
1Fudan University · 3Shanghai Innovation Institute · University of Rochester
Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation
Jun 2, 2026Kaiqi Yang, Tai-Quan Peng, Sanguk Lee +1Human Behavior Simulation Multi-Agent Systems
Michigan State University East Lansing, MI, USA · Hankuk University of Foreign Studies Seoul, Republic of Korea
Can LLM Agents Sustain Long-Horizon Organizational Dynamics?
May 31, 2026Xuancheng Zhu, Yang Yue, Shuaibing Wan +4Multi-Agent Coordination Human Behavior Simulation
Beijing University of Posts and Telecommunications, Beijing, China
EASE Configuration Facilitates A Reproducible Science of LLM Social Simulations
May 28, 2026Sneheel Sarangi, Maximilian Puelma Touzel, Aurélien Bück-Kaeffer +3Multi-Agent LLM Systems Human Behavior Simulation
McGill University · Mila - Quebec Artificial Intelligence Institute · Université de Montréal +1
AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
May 28, 2026Yulei Ye, Wenhao Li, Zhong Wen +23Multi-Agent LLM Systems Human Behavior Simulation
Shanghai Institute of AI for Education, East China Normal University · School of Computer Science and Technology, Tongji University · School of Computer Science and Technology, East China Normal University +3
Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News
May 27, 2026Alejandro Buitrago López, Alberto Ortega Pastor, Javier Pastor-Galindo +1LLM Agent Evaluation Large Language Model-Based Social Simulation
Faculty of Computer Science, University of Murcia, Murcia (Spain)
Human-like in-group bias in instruction-tuned language model agents
May 27, 2026Messi H. J. LeeSocial Bias in Language Models Large Language Model-Based Social Simulation
Independent Researcher · Seoul, South Korea
The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Study
May 20, 2026Victoria Lin, Taedong Yun, Maja Matarić +3Human Behavior Simulation Large Language Model-Based Social Simulation
Google DeepMind · Carnegie Mellon University
Reinforcing Human Behavior Simulation via Verbal Feedback
May 19, 2026Weiwei Sun, Xuhui Zhou, Jiarui Liu +13RL for Language Models Human Behavior Simulation
1Carnegie Mellon University · 2Microsoft
APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents
May 19, 2026Quan Zheng, Yan Gao, Shaobin He +6Human Behavior Simulation Adaptive Sampling
1Beijing Normal University · 2Zhongguancun Academy, Beijing, China · 3Zhongguancun Institute of Artificial Intelligence

Jul 17, 2026, physics.soc-phJ/K move · Enter open · S save

Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling

Gurkan Ozkan

Istanbul Technical University

Human Behavior Simulation Large Language Model-Based Social Simulation Synthetic Data Generation for Language Models Persona-Conditioned Generation

Open paper AskPDF arXiv

Synthetic-population tools increasingly run every individual as an independent large language model (LLM) agent. Using real survey microdata, we show that this paradigm has a basic failure mode, and we set a distribution-first corrective against it, all measured with a deterministic, construct-validated verifier on non-WEIRD (Turkey-first) data. First, N independent LLM agents grounded on 2,414 real World Values Survey respondents fail to reproduce the population's response distribution: they pile onto a modal default (four scenarios x five seeds: concentration 0.36->0.69, entropy 1.46->0.77, 85% collapse, TVD=0.44), and the collapse is a predictable function of scenario structure (r=0.55 with a single-answer structure). Second, Verbalized Sampling (VS) fixes the field's chronic under-dispersion without training in three model families (fidelity +7 to +10; significant on Qwen, p=0.002, d=6.2), yet the same move universally overshoots into over-dispersion (SD-ratio 0.4-0.56 -> 1.26-1.37), a structural property of VS. Third, survey fidelity transfers only weakly to agentic behavior: in a single-model, single-domain booking task, a persona is dominated by a cheapest-default (~80%) that income modulates but does not override (comfort choice 0%->7%->32% across income bands). Fourth, a placebo-controlled memorization attack and an election backtest show VS keeps aggregate strength while subgroup and individual claims are contaminated by recall and underdetermination. We close with the corrective: model the distribution once (VS) and assign it to grounded characters at O(1) cost, with a budget-aware router whose honest AUC is 0.805, not the tautological 1.0 of a code-derived oracle. The central contribution needs no realism claim: it measures the internal inconsistency of the independent-agent route and the conditions under which the distribution-first route calibrates.

Momentum

Related topics

Latest papers 120