HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation

arXiv:2510.07794v2 Announce Type: replace-cross Abstract: Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behaviors exist widely, such as over-search (retrieving information already known) and under-search (failing to search when necessary), which leads to unnecessary overhead and unreliable outputs. Current training methods, which typically rely on outcome-based rewards