一作SIGIR 2026Oral· Information Retrieval (Full)
SmartSearch: Process Reward-Guided Query Refinement for Search Agents
Tongyu Wen · Guanting Dong · Zhicheng Dou
摘要
Large Language Model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of search agents, yet the quality of intermediate search queries...