一作SIGIR 2026Oral· Information Retrieval (Full)
Beyond the Single Path: Divergent Reasoning for LLM-based Recommendation
Guojia An · Jie Zou · Yuhan Yang · Shuai Qin · Weikang Guo · Jinyu Guo · Yang Yang
摘要
Large Language Models (LLMs) have demonstrated strong potential in recommendations due to their powerful reasoning capabilities. However, existing methods typically rely on a single reasoning path to drive the entire Top-K recommendations. This paradigm is prone to reasoning path collapse, where...