User Behavior Simulation with Large Language Model based Agents
On the map: LLM agents and tool use → Social simulation and multi-agent debate
Abstract (arXiv)
Simulating high quality user behavior data has always been a fundamental problem in human-centered applications, where the major difficulty originates from the intricate mechanism of human decision process. Recently, substantial evidences have suggested that by learning huge amounts of web knowledge, large language models (LLMs) can achieve human-like intelligence. We believe these models can provide significant opportunities to more believable user behavior simulation. To inspire such direction, we propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans. Concerning potential applications, we simulate and study two social phenomenons including (1) information cocoons and (2) user conformity behaviors. This research provides novel simulation paradigms for human-centered applications.
Key facts. Cited by 136 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 37 of its 100 references that are in the map. First posted on arXiv 5 Jun 2023.
Builds on
37 of 100 references.
Closest ancestors · 1
Same direction, newest first
Other references · 36
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2023A Survey of Large Language Modelscited by 2,537
- 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
- 2018Self-Attentive Sequential Recommendationcited by 1,169
- 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
- 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
- 2017Neural Collaborative Filteringcited by 1,108
- 2019Graph Neural Networks for Social Recommendationcited by 711
- 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
- 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
- 2023Self-collaboration Code Generation via ChatGPTcited by 255
24 more
- 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
- 2021Reinforcement learning based recommender systems: A surveycited by 187
- 2020Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthycited by 182
- 2018Conversational Recommender Systemcited by 115
- 2019Sequential Recommender Systems: Challenges, Progress and Prospectscited by 115
- 2017Adversarial Learning for Neural Dialogue Generationcited by 103
- 2019RecSim: A Configurable Simulation Platform for Recommender Systemscited by 91
- 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modellingcited by 88
- 2018Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learningcited by 80
- 2018RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertisingcited by 65
- 2018Generative Adversarial User Model for Reinforcement Learning Based Recommendation Systemcited by 64
- 2021Counterfactual Explainable Recommendationcited by 60
- 2021Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systemscited by 47
- 2020Evaluating Conversational Recommender Systems via User Simulationcited by 46
- 2019Human-Centered Artificial Intelligence and Machine Learningcited by 37
- 2021Temporal Meta-path Guided Explainable Recommendationcited by 26
- 2023Exploiting Simulated User Feedback for Conversational Search: Ranking, Rewriting, and Beyondcited by 23
- 2021RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystemscited by 21
- 2021Measuring Recommender System Effects with Simulated Userscited by 20
- 2023An In-depth Investigation of User Response Simulation for Conversational Searchcited by 20
- 2021Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulationcited by 16
- 2018LensKit for Python: Next-Generation Software for Recommender System Experimentscited by 13
- 2021Simulations in Recommender Systems: An industry perspectivecited by 6
- 2022Synthetic Data-Based Simulators for Recommender Systems: A Surveycited by 5
Built on by
Citing papers per year: 2023: 4; 2024: 16; 2025: 65; 2026: 51.
136 papers.
Sort:
By area:
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
- 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
- 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
- 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
- 2024The Emerged Security and Privacy of LLM Agent: A Survey with Case Studiescited by 127
- 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 127
- 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
- 2025MLGym: A New Framework and Benchmark for Advancing AI Research Agentscited by 111
- 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
- 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
- 2023Large Language Models for Generative Recommendation: A Survey and Visionary Discussionscited by 72
- 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
38 more
- 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 56
- 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Applicationcited by 54
- 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Userscited by 50
- 2025A Survey on LLM-powered Agents for Recommender Systemscited by 49
- 2024GenSim: A General Social Simulation Platform with Large Language Model based Agentscited by 48
- 2026Mind the Sim2Real Gap in User Simulation for Agentic Taskscited by 44
- 2025PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequencecited by 33
- 2025Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systemscited by 32
- 2025Generative to Agentic AI: Survey, Conceptualization, and Challengescited by 32
- 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32
- 2024Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networkscited by 31
- 2025Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulationscited by 28
- 2025A Survey of Personalization: From RAG to Agentcited by 26
- 2025OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulationcited by 26
- 2025RecoWorld: Building Simulated Environments for Agentic Recommender Systemscited by 18
- 2025Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialoguecited by 17
- 2024Agentic Feedback Loop Modeling Improves Recommendation and User Simulationcited by 16
- 2025PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Processcited by 16
- 2025Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shoppingcited by 16
- 2024LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultationcited by 14
- 2026A Survey on LLM-based Conversational User Simulationcited by 14
- 2024Human-inspired Perspectives: A Survey on AI Long-term Memorycited by 12
- 2025DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agentscited by 12
- 2024Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspectivecited by 11
- 2024Knowledge Graph Enhanced Language Agents for Recommendationcited by 11
- 2025LLM-Based Social Simulations Require a Boundarycited by 11
- 2025Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosiscited by 10
- 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applicationscited by 10
- 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 10
- 2025SPeCtrum: A Grounded Framework for Multidimensional Identity Representation in LLM-Based Agentcited by 8
- 2025Agent Guide: A Simple Agent Behavioral Watermarking Frameworkcited by 8
- 2025Modeling Earth-Scale Human-Like Societies with One Billion Agentscited by 8
- 2025RedDebate: Safer Responses Through Multi-Agent Red Teaming Debatescited by 7
- 2025Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RLcited by 7
- 2025Investigating and Extending Homans' Social Exchange Theory with Large Language Model based Agentscited by 6
- 2025textttBluePrint: A Social Media User Dataset for LLM Persona Evaluation and Trainingcited by 6
- 2026Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Auditscited by 6
- 2024Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systemscited by 5
50 most cited of 136 All 136 (JSON)
- 2026SCBO: Semantically Coherent Batching and Ordering for LLM-Based Social Surveys28 Sep 2026
- 2026AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side25 Sep 2026
- 2026A Behavioral Trait Leaks into Preferences: Diagnosing Trait Interference in LLM User Simulators22 Sep 2026
- 2026Tipping Points in LLM-Based Multi-Agent Systems: Stance on Climate Change Action21 Sep 2026
- 2026AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale15 Sep 2026
- 2026Are LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA)14 Sep 2026
- 2026CORAL: An LLM-Native Harness for Production Recommender Systems2 Sep 2026
- 2026Data-Driven Persona-Conditioned Agents for A/B Test Simulation1 Sep 2026
- 2026LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems27 Aug 2026
- 2026The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search24 Aug 2026
- 2026Learning from Online User Feedback for Shopping Agents12 Aug 2026
- 2026Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity4 Aug 2026
38 more
- 2026LLMs struggle to simulate human belief updates in controlled environments30 Jul 2026
- 2026Eco3S: Complex Socio-Economic System Simulation via Agent-Based Models29 Jul 2026
- 2026Personalized Recommendation Tool Learning via Autonomous Language Agents22 Jul 2026
- 2026From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations7 Jul 2026
- 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems5 Jul 2026
- 2026PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction3 Jul 2026
- 2026Will Scaling Improve Social Simulation with LLMs?2 Jul 2026
- 2026Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale29 Jun 2026
- 2026AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphs16 Jun 2026
- 2026Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call13 Jun 2026
- 2026BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces1 Jun 2026
- 2026Can LLM Agents Sustain Long-Horizon Organizational Dynamics?31 May 2026
- 2026Simulating Human Memory with Language Models25 May 2026
- 2026Reinforcing Human Behavior Simulation via Verbal Feedback19 May 2026
- 2026Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits17 May 2026
- 2026Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling15 May 2026
- 2026Agentic Recommender System with Hierarchical Belief-State Memory14 May 2026
- 2026Mechanism Plausibility in Generative Agent-Based Modeling12 May 2026
- 2026TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents11 May 2026
- 2026Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework8 May 2026
- 2026A Survey on LLM-based Conversational User Simulation27 Apr 2026
- 2026SAGER: Self-Evolving User Policy Skills for Recommendation Agent16 Apr 2026
- 2026Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender Systems11 Apr 2026
- 2026LLM Agents as Social Scientists: A Human-AI Collaborative Platform for Social Science Automation2 Apr 2026
- 2026Entropy Guided Diversification and Preference Elicitation in Agentic Recommendation Systems12 Mar 2026
- 2026Mind the Sim2Real Gap in User Simulation for Agentic Tasks11 Mar 2026
- 2026Your Reviews Replicate You: LLM-Based Agents as Customer Digital Twins for Conjoint Analysis6 Mar 2026
- 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions26 Feb 2026
- 2026InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation23 Feb 2026
- 2026AI Agents Alone Are Not (Yet) Sufficient for Social Simulation19 Feb 2026
- 2026Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation16 Feb 2026
- 2026Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs8 Feb 2026
- 2026AgenticTagger: Structured Item Representation for Recommendation with LLM Agents5 Feb 2026
- 2026PersonaAct: Simulating Short-Video Users with Personalized Agents for Counterfactual Filter Bubble Auditing30 Jan 2026
- 2026From Who They Are to How They Act: Behavioral Traits in Generative Agent-Based Models of Social Media21 Jan 2026
- 2026Exploring Recommender System Evaluation: A Multi-Modal User Agent Framework for A/B Testing8 Jan 2026
- 2026PersonaLedger: Generating Realistic Financial Transactions with Persona Conditioned LLMs and Rule Grounded Feedback6 Jan 2026
- 2026Ahead of the Spread: Agent-Driven Virtual Propagation for Early Fake News Detection6 Jan 2026
50 newest of 136 All 136 (JSON)
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
- 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
- 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
- 2024The Emerged Security and Privacy of LLM Agent: A Survey with Case Studiescited by 127
- 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
- 2025MLGym: A New Framework and Benchmark for Advancing AI Research Agentscited by 111
- 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
- 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
- 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 56
- 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Applicationcited by 54
- 2025A Survey on LLM-powered Agents for Recommender Systemscited by 49
- 2026Mind the Sim2Real Gap in User Simulation for Agentic Taskscited by 44
12 most cited of 74 All 74 (JSON)
- 2026AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side25 Sep 2026
- 2026Tipping Points in LLM-Based Multi-Agent Systems: Stance on Climate Change Action21 Sep 2026
- 2026AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale15 Sep 2026
- 2026Data-Driven Persona-Conditioned Agents for A/B Test Simulation1 Sep 2026
- 2026LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems27 Aug 2026
- 2026Learning from Online User Feedback for Shopping Agents12 Aug 2026
- 2026Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity4 Aug 2026
- 2026Eco3S: Complex Socio-Economic System Simulation via Agent-Based Models29 Jul 2026
- 2026From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations7 Jul 2026
- 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems5 Jul 2026
- 2026Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call13 Jun 2026
- 2026Can LLM Agents Sustain Long-Horizon Organizational Dynamics?31 May 2026
12 newest of 74 All 74 (JSON)
- 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
- 2025PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Processcited by 16
- 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
- 2024Large Language Models Need Consultants for Reasoning: Becoming an Expert in a Complex Human System Through Behavior Simulationcited by 1
- 2026Personalized Recommendation Tool Learning via Autonomous Language Agentscited by 1
- 2025Selection and Exploitation of High-Quality Knowledge from Large Language Models for Recommendationcited by 0
- 2026Personalized Recommendation Tool Learning via Autonomous Language Agents22 Jul 2026
- 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents20 Oct 2025
- 2025Selection and Exploitation of High-Quality Knowledge from Large Language Models for Recommendation10 Aug 2025
- 2025PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process7 Jul 2025
- 2024Large Language Models Need Consultants for Reasoning: Becoming an Expert in a Complex Human System Through Behavior Simulation27 Mar 2024
- 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents20 Nov 2023
- 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
- 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Userscited by 50
- 2024GenSim: A General Social Simulation Platform with Large Language Model based Agentscited by 48
- 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users14 Apr 2025
- 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society12 Feb 2025
- 2024GenSim: A General Social Simulation Platform with Large Language Model based Agents6 Oct 2024
- 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 127
- 2023Large Language Models for Generative Recommendation: A Survey and Visionary Discussionscited by 72
- 2024Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networkscited by 31
- 2025OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulationcited by 26
- 2025Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialoguecited by 17
- 2026A Survey on LLM-based Conversational User Simulationcited by 14
- 2024Human-inspired Perspectives: A Survey on AI Long-term Memorycited by 12
- 2024Knowledge Graph Enhanced Language Agents for Recommendationcited by 11
- 2025LLM-Based Social Simulations Require a Boundarycited by 11
- 2025Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosiscited by 10
- 2025Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RLcited by 7
- 2025textttBluePrint: A Social Media User Dataset for LLM Persona Evaluation and Trainingcited by 6
12 most cited of 49 All 49 (JSON)
- 2026SCBO: Semantically Coherent Batching and Ordering for LLM-Based Social Surveys28 Sep 2026
- 2026A Behavioral Trait Leaks into Preferences: Diagnosing Trait Interference in LLM User Simulators22 Sep 2026
- 2026Are LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA)14 Sep 2026
- 2026CORAL: An LLM-Native Harness for Production Recommender Systems2 Sep 2026
- 2026LLMs struggle to simulate human belief updates in controlled environments30 Jul 2026
- 2026PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction3 Jul 2026
- 2026Will Scaling Improve Social Simulation with LLMs?2 Jul 2026
- 2026Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale29 Jun 2026
- 2026AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphs16 Jun 2026
- 2026BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces1 Jun 2026
- 2026Simulating Human Memory with Language Models25 May 2026
- 2026Reinforcing Human Behavior Simulation via Verbal Feedback19 May 2026
12 newest of 49 All 49 (JSON)
Similar, not cited
Close in wording, no citation either way
- 2023Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering
- 2025Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data
- 2024LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities
- 2024Can Large Language Model Agents Simulate Human Trust Behavior?
- 2024BASES: Large-scale Web Search User Simulation with Large Language Model based Agents
- 2024Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models
- 2025Don't Trust Generative Agents to Mimic Communication on Social Networks Unless You Benchmarked their Empirical Realism
- 2026RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation