Research paper

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

Published by Association for Computational LinguisticsJul 2026PDF

Compare simulated customer interactions with real online behaviour across several turns.

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

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Yuxuan Lu, Jing Huang, Yan Han, Bingsheng Yao, Sisong Bei, Yaochen Xie, Yisi Sang, Qi He, Dakuo Wang. Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). © 2026 Association for Computational Linguistics. CC BY 4.0. 10.18653/v1/2026.acl-long.2034. Original PDF, unmodified.

CC BY 4.0

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

Related research.

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?

Retrieval Enhancements for RAG: Insights from a Deployed Customer Support Chatbot