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.

翻译：智能体搜索系统通过迭代式与检索模型交互来解答复杂查询。尽管取得显著进展，但为智能体搜索优化检索器仍具挑战性，通常需要大量共训练或人工标注数据，限制了实际应用场景。我们提出Critic-R框架，该框架在推理和训练阶段明确建立了推理智能体与检索模型之间的反馈闭环。Critic-R引入了一个评论模型，该模型在消费检索到的证据后评估智能体的内省推理轨迹，以判断检索上下文是否充分支持下一步推理。Critic-R包含两种互补机制：Critic-R-Zero是一种推理时的查询优化循环，可迭代重写查询和检索指令；Critic-Embed是一种检索模型优化方法，利用成功和失败的优化轨迹作为自动监督信号，无需人工相关性标注。我们在HotpotQA、2WikiMultihopQA、MuSiQue和Bamboogle数据集上评估了Critic-R。实验结果表明，Critic-R显著提升了检索质量和下游答案准确率。