Not All Information Brings Benefits: Personalization-Driven Agent Debate for Conversational Recommendation
P P Zhang, Guojia An, Jin Huang, Yuhan Yang, Yang Yang, Jie Zou · 2026
Conversational recommender systems (CRSs) aim to provide real-time recommendations through dynamic interactions between users and the system. Recent studies have revealed the value of personalized information derived from users' historical dialogue records in refining user preferences. However, existing methods often utilize the entire historical dialogue of a user indiscriminately, leading to the issue of cognitive negative transfer, wherein historical dialogue sessions impede rather than facilitate current decision-making. This ultimately degrades the performance of conversational recommendations.