作者位次 #3/7ACL 2026Findings· Findings of ACL
C ritic S earch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic
Yaocheng Zhang · Haohuan Huang · Zijun Song · Zijie Zhao · Qichao Zhang · Yuanheng Zhu · Dongbin Zhao
摘要
Tool-Integrated Reasoning (TIR) with search engines enables large language models to iteratively retrieve up-to-date external knowledge, enhancing adaptability and generalization in complex question-answering tasks. However, existing search agent pipelines typically depend on reinforcement learni...