Beyond the Single Path: Divergent Reasoning for LLM-based Recommendation

作者：Guojia An, Jie Zou, Yi Yang, Shuai Qin, Weikang Guo, Jinyu Guo, Yang Yang · 年份：2026 · DOI：10.1145/3805712.3809732 · 被引用次数：1 · 研究领域：Topic Modeling、Artificial Intelligence in Healthcare and Education、Explainable Artificial Intelligence (XAI)

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 limiting exploration of potentially superior and diverse reasoning paths within the LLMs space. As a result, both the accuracy and diversity of the recommendation outcomes are constrained.