作者位次 #5/9ACL 2026Poster· Natural Language Processing
Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data
Yuxuan Lu · Jing Huang · Yan Han · Bingsheng Yao · Sisong Bei · Yaochen Xie · Yisi Sang · Qi He · Dakuo Wang
摘要
Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, and such agents have been increasingly adopted in downstream applications. However, existing evaluation of these agents only focuses on qualitative believability (whether human raters think th...