用自我反思反馈优化搜索，让检索模型更懂下一步要什么。
Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback
- 引入评论模型评估推理过程，自动判断检索内容是否足够支持下一步。
- 在多个数据集上提升检索质量和答案准确率，无需人工标注。
- 适合需要高效迭代搜索的智能系统开发者或研究者。
智能搜索系统通过与检索模型多次交互来回答复杂问题。尽管已有显著进展，但为智能搜索优化检索模型仍具挑战性，常需大量联合训练或黄金标准标注，限制了实际应用。本文提出Critic-R框架，显式构建推理代理与检索模型之间的反馈闭环，贯穿推理与训练阶段。Critic-R引入评论模型，在代理消耗检索证据后，评估其自我反思的推理轨迹，判断当前检索内容是否足以支撑下一步推理。该框架包含两种互补机制：Critic-R-Zero在推理时通过迭代重写查询与检索指令实现查询优化；Critic-Embed则利用成功与失败的优化轨迹作为自动监督信号，训练检索模型，无需人工相关性标注。我们在HotpotQA、2WikiMultihopQA、MuSiQue和Bamboogle数据集上进行了评估，结果表明Critic-R显著提升了检索质量与下游答案准确率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。