Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback 文章

ArXiv CS.AI2026-06-02NEWSen作者: Md Zarif Ul Alam, Alireza Salemi, Hamed Zamani

摘要

arXiv:2606.00590v1 Announce Type: cross Abstract: Agentic search systems iteratively interact with retrieval models to answer complex queries. Despite substantial progress, optimizing retrievers for agentic search remains challenging, often requiring heavy co-training or gold-standard annotations that limit real-world applicability. We propose Critic-R, a framework that explicitly closes the feedback loop between the reasoning agent and the retrieval model during both inference and training. Critic-R introduces a critic model that evaluates the agent's introspective reasoning trace after consuming retrieved evidence to determine whether the retrieved context sufficiently supports the next reasoning step.

相关公司

暂无数据

相关人物

暂无数据