mlsanityData to 13 Oct 2026

LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals

arXiv 2411.10109 ↗First posted 15 Nov 2024cs.AI cs.HC cs.LGcited by 244

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Machine learning can predict human behavior well when substantial structured data are available for well-defined outcomes. Such models are typically outcome-specific, however, requiring training data for each target outcome, limiting their applicability to new domains. We test whether large language models (LLMs) can relax these requirements by using self-report data to build attitudinal and behavioral simulations, or "generative agents," that can predict responses across outcomes without outcome-specific training data. Using data from a diverse national sample of 1,052 Americans, we built agents from (i) two-hour, semi-structured interviews elicited using the American Voices Project interview schedule, (ii) structured surveys including General Social Survey items and the Big Five personality inventory, or (iii) both sources combined. On held-out General Social Survey items, interview-only, survey-only, and combined agents achieved accuracies equal to 83%, 82%, and 86% of participants' own two-week test-retest consistency benchmark, respectively, compared with 74% for demographics-only agents. Combining interviews and surveys produced the highest accuracy, though gains over either source alone were modest, suggesting that predictive benefits from data begin to asymptote once the model has observed sufficient evidence within a domain. We find that these agents also predict personality traits, economic-game behavior, and experimental responses, while reducing accuracy disparities across racial and ideological groups relative to demographics-only agents. Together, these results show that LLM agents grounded in qualitative or quantitative self-reports can support general-purpose simulation of individuals across outcomes, without requiring task-specific training data.

Key facts. Cited by 244 papers in the map (data through 13 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. First posted on arXiv 15 Nov 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 6; 2025: 141; 2026: 97.

244 papers.

Sort:

By area:

  1. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 183
  2. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 129
  3. 2025Agentic Large Language Models, a surveycited by 107
  4. 2025LLM Social Simulations Are a Promising Research Methodcited by 98
  5. 2025Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinionscited by 65
  6. 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoningcited by 57
  7. 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Userscited by 54
  8. 2025SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviorscited by 52
  9. 2025Fully Autonomous AI Agents Should Not be Developedcited by 43
  10. 2025The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Modelscited by 41
  11. 2025UXAgent: An LLM Agent-Based Usability Testing Framework for Web Designcited by 40
  12. 2025Finetuning LLMs for Human Behavior Prediction in Social Science Experimentscited by 38
38 more
  1. 2026τ-Knowledge: Evaluating Conversational Agents over Unstructured Knowledgecited by 38
  2. 2026HumanLM: Simulating Users with State Alignment Beats Response Imitationcited by 35
  3. 2024Position: Theory of Mind Benchmarks are Broken for Large Language Modelscited by 31
  4. 2025Linear Representations of Political Perspective Emerge in Large Language Modelscited by 31
  5. 2025Value Profiles for Encoding Human Variationcited by 29
  6. 2025CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulationcited by 28
  7. 2026This human study did not involve human subjects: Validating LLM simulations as behavioral evidencecited by 28
  8. 2025OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulationcited by 27
  9. 2025MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulationscited by 26
  10. 2025Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentscited by 22
  11. 2025LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacracited by 21
  12. 2025Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questionscited by 20
  13. 2025Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errorscited by 20
  14. 2024Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Frameworkcited by 19
  15. 2025Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learningcited by 19
  16. 2025Large Language Models Do Not Simulate Human Psychologycited by 18
  17. 2025Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shoppingcited by 18
  18. 2025Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancycited by 16
  19. 2025Group size effects and collective misalignment in LLM multi-agent systemscited by 16
  20. 2024Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Studycited by 14
  21. 2025RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agentscited by 14
  22. 2025Technological folie `a deux: Feedback Loops Between AI Chatbots and Mental Illnesscited by 14
  23. 2025DeepPersona: A Generative Engine for Scaling Deep Synthetic Personascited by 14
  24. 2026The Need for a Socially-Grounded Persona Framework for User Simulationcited by 14
  25. 2024Exploring and Controlling Diversity in LLM-Agent Conversationcited by 12
  26. 2025Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspectivecited by 12
  27. 2025Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoningcited by 12
  28. 2025A Pragmatic View of AI Personhoodcited by 12
  29. 2025IMPersona: Evaluating Individual Level LM Impersonationcited by 11
  30. 2025LLM-Based Social Simulations Require a Boundarycited by 11
  31. 2025UXAgent: A System for Simulating Usability Testing of Web Design with LLM Agentscited by 10
  32. 2025SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulationcited by 10
  33. 2025Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agentscited by 10
  34. 2025GATSim: Urban Mobility Simulation with Generative Agentscited by 10
  35. 2026Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbookcited by 10
  36. 2024A Large-Scale Simulation on Large Language Models for Decision-Making in Political Sciencecited by 9
  37. 2025How Personality Traits Shape LLM Risk-Taking Behaviourcited by 9
  38. 2025Improving Language Model Personas via Rationalization with Psychological Scaffoldscited by 9

50 most cited of 244 All 244 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation
  2. 2025Exploring Large Language Model Agents for Piloting Social Experiments
  3. 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications
  4. 2025In Silico Development of Psychometric Scales: Feasibility of Representative Population Data Simulation with LLMs
  5. 2025Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?
  6. 2025Evaluating the Bias in LLMs for Surveying Opinion and Decision Making in Healthcare
  7. 2026Evaluating LLMs as Human Surrogates in Controlled Experiments
  8. 2024Systematic Biases in LLM Simulations of Debates