Imagen de Portada

Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lu, Yuxuan, Huang, Jing, Han, Yan, Yao, Bingsheng, Bei, Sisong, Gesi, Jiri, Xie, Yaochen, Sang, Yisi, Zheshen, Wang, He, Qi, Wang, Dakuo
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?
por: Sun, Lu, et al.
Publicado: (2025)

Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping
por: Wang, Ziyi, et al.
Publicado: (2025)

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation
por: Chen, Jiaju, et al.
Publicado: (2025)

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents
por: Zhang, Yimeng, et al.
Publicado: (2025)

DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans
por: Yao, Bingsheng, et al.
Publicado: (2025)

UXAgent: A System for Simulating Usability Testing of Web Design with LLM Agents
por: Lu, Yuxuan, et al.
Publicado: (2025)

UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design
por: Lu, Yuxuan, et al.
Publicado: (2025)

OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation
por: Wang, Ziyi, et al.
Publicado: (2025)

Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning
por: Zhang, Yimeng, et al.
Publicado: (2025)

Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline
por: Xu, Jiawei, et al.
Publicado: (2026)

Human and LLM-Based Voice Assistant Interaction: An Analytical Framework for User Verbal and Nonverbal Behaviors
por: Chan, Szeyi, et al.
Publicado: (2024)

WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale
por: Lu, Yuxuan, et al.
Publicado: (2025)

More Samples or More Prompts? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering
por: Yao, Bingsheng, et al.
Publicado: (2023)

AgentA/B: Automated and Scalable Web A/BTesting with Interactive LLM Agents
por: Lu, Yuxuan, et al.
Publicado: (2025)

Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs
por: Lu, Yuxuan, et al.
Publicado: (2026)

Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents
por: Wang, Ziyi, et al.
Publicado: (2026)

From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM Agents
por: Yao, Bingsheng, et al.
Publicado: (2026)

Through the Lens of Human-Human Collaboration: A Configurable Research Platform for Exploring Human-Agent Collaboration
por: Yao, Bingsheng, et al.
Publicado: (2025)

Secret Use of Large Language Model (LLM)
por: Zhang, Zhiping, et al.
Publicado: (2024)

User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistants
por: Mahmood, Amama, et al.
Publicado: (2023)

How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
por: Li, Yuxuan, et al.
Publicado: (2026)

Beyond Self-learned Attention: Mitigating Attention Bias in Transformer-based Models Using Attention Guidance
por: Gesi, Jiri, et al.
Publicado: (2024)

From ChatGPT to DeepSeek: Can LLMs Simulate Humanity?
por: Wang, Qian, et al.
Publicado: (2025)

Can Large Language Model Agents Simulate Human Trust Behavior?
por: Xie, Chengxing, et al.
Publicado: (2024)

Human-Centered Privacy Research in the Age of Large Language Models
por: Li, Tianshi, et al.
Publicado: (2024)

Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation?
por: Gu, Yuxuan, et al.
Publicado: (2026)

Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies
por: Varshney, Prasoon, et al.
Publicado: (2025)

Estimated Dynamic Equilibrium Model: Supply and Demand as a Sample Path of a Stochastic Process
por: Arbuzov, Mikhail L., et al.
Publicado: (2026)

Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data
por: Xu, Xuhai, et al.
Publicado: (2023)

"I Like Sunnie More Than I Expected!": Exploring User Expectation and Perception of an Anthropomorphic LLM-based Conversational Agent for Well-Being Support
por: Wu, Siyi, et al.
Publicado: (2024)

"It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents
por: Zhang, Zhiping, et al.
Publicado: (2023)

StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children's Story-Based Learning
por: Chen, Jiaju, et al.
Publicado: (2023)

Eliciting Behaviors in Multi-Turn Conversations
por: Huang, Jing, et al.
Publicado: (2025)

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
por: Tang, Jingyu, et al.
Publicado: (2025)

AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society
por: Piao, Jinghua, et al.
Publicado: (2025)

Towards Trustworthy Multi-Turn LLM Agents via Behavioral Guidance
por: Gürsun, Gonca
Publicado: (2025)

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
por: Zhang, Xiangxu, et al.
Publicado: (2026)

Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors
por: Zhao, Yi, et al.
Publicado: (2025)

"Should I Give Up Now?" Investigating LLM Pitfalls in Software Engineering
por: Tie, Jiessie, et al.
Publicado: (2024)

Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLM
por: Li, Jiachen, et al.
Publicado: (2024)