User Behavior Simulation with Large Language Model based Agents

2023/06/05 by Lei Wang, Wang, Lei, Jingsen Zhang +18 · 40 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2306.02552

openalex publication_date 2023/06/05 · openalex created_date 2023/06/07 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• LLM Agents as VC investors: Predicting Startup Success via RolePlay-Based Collective Simulation
• Agent-based simulation of online social networks and disinformation
• StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios
• Selecting User Histories to Generate LLM Users for Cold-Start Item Recommendation
• CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models
• Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation
• When Top-ranked Recommendations Fail: Modeling Multi-Granular Negative Feedback for Explainable and Robust Video Recommendation
• Humanlike Multi-user Agent (HUMA): Designing a Deceptively Human AI Facilitator for Group Chats
• PersonaDrift: A Benchmark for Temporal Anomaly Detection in Language-Based Dementia Monitoring
• Sim4IA-Bench: A User Simulation Benchmark Suite for Next Query and Utterance Prediction
• Evaluating Online Moderation Via LLM-Powered Counterfactual Simulations
• LLM-as-a-Judge: Toward World Models for Slate Recommendation Systems
• InsurAgent: A Large Language Model-Empowered Agent for Simulating Individual Behavior in Purchasing Flood Insurance
• A Survey on Generative Recommendation: Data, Model, and Tasks
• Eco3S: Complex Socio-Economic System Simulation via Agent-Based Models
• Will Scaling Improve Social Simulation with LLMs?
• Integrating LLM and Diffusion-Based Agents for Social Simulation
• Integrating Machine Learning into Belief-Desire-Intention Agents: Current Advances and Open Challenges
• Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
• Enhance Large Language Models as Recommendation Systems with Collaborative Filtering
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL
• SocioBench: Modeling Human Behavior in Sociological Surveys with Large Language Models
• Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping
• AgentDR Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents
• AgenticRAG: Tool-Augmented Foundation Models for Zero-Shot Explainable Recommender Systems
• CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine
• BluePrint: A Social Media User Dataset for LLM Persona Evaluation and Training
• LLMs struggle to simulate human belief updates in controlled environments
• Temporal-Aware User Behaviour Simulation with Large Language Models for Recommender Systems
• A Dynamic Approach to Collaborative Document Writing (Full Version)
• Chinese Court Simulation with LLM-Based Agent System
• From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
• Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue
• RecoWorld: Building Simulated Environments for Agentic Recommender Systems
• Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models
• Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation
• Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
• Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation
• Chimera: Harnessing Multi-Agent LLMs for Automatic Insider Threat Simulation
• Selection and Exploitation of High-Quality Knowledge from Large Language Models for Recommendation
• G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulation

Related

• Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
• LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation
• GenSim: A General Social Simulation Platform with Large Language Model based Agents
• Don't Trust Generative Agents to Mimic Communication on Social Networks Unless You Benchmarked their Empirical Realism
• How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation