{"ID":2922009,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T07:21:46.982601397Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00590","arxiv_id":"2606.00590","title":"Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback","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. Critic-R has two complementary mechanisms: Critic-R-Zero, an inference-time query refinement loop that iteratively rewrites queries and retrieval instructions, and Critic-Embed, an optimization approach for retrieval models that leverages successful and failed refinement trajectories as automatic supervision without requiring manual relevance annotation. We evaluate Critic-R on HotpotQA, 2WikiMultihopQA, MuSiQue, and Bamboogle. Results show that Critic-R significantly improves both retrieval quality and downstream answer accuracy.","short_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 th...","url_abs":"https://arxiv.org/abs/2606.00590","url_pdf":"https://arxiv.org/pdf/2606.00590v1","authors":"[\"Md Zarif Ul Alam\",\"Alireza Salemi\",\"Hamed Zamani\"]","published":"2026-05-30T07:42:22Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[]","has_code":false}