S earch- P 1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
Tianle Xia · Ming Xu · Lingxiang Hu · Yiding Sun · Wenwei Li · Linfang Shang · Liqun Liu · Peng Shu · Huan Yu · Jie Jiang
摘要
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, yet traditional single-round retrieval struggles with complex multi-step reasoning.Agentic RAG addresses this by enabling LLMs to dynamically decide when and what to retrieve, but curre...