Agentic-R：面向智能搜索的检索学习系统

Agentic-R: Learning to Retrieve for Agentic Search

January 17, 2026

作者: Wenhan Liu, Xinyu Ma, Yutao Zhu, Yuchen Li, Daiting Shi, Dawei Yin, Zhicheng Dou

cs.AI

摘要

近期，智能体搜索（Agentic Search）作为一种新兴的强大范式崭露头角，其通过智能体将多步推理与按需检索相结合来解决复杂问题。尽管该范式已取得显著成效，但如何为其设计专用检索器仍缺乏深入探索。现有搜索智能体通常依赖基于相似度的检索器，然而相似文本片段对最终答案生成并非总是有效。本文提出了一种专为智能体搜索设计的新型检索器训练框架。与单轮检索增强生成（RAG）中仅依赖局部段落效用的检索器不同，我们提出通过局部查询-段落相关性和全局答案正确性来共同衡量多轮智能体搜索中的段落效用。此外，我们引入了一种迭代训练策略，使搜索智能体与检索器能够进行双向迭代优化。相较于仅使用固定问题单次训练的RAG检索器，我们的方法能利用智能体动态生成的高质量查询持续优化检索器。在七个单跳与多跳问答基准数据集上的大量实验表明，我们提出的检索器（命名为）在不同搜索智能体中均能稳定超越现有强基线模型。代码已开源：https://github.com/8421BCD/Agentic-R。

English

Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains largely underexplored. Existing search agents typically rely on similarity-based retrievers, while similar passages are not always useful for final answer generation. In this paper, we propose a novel retriever training framework tailored for agentic search. Unlike retrievers designed for single-turn retrieval-augmented generation (RAG) that only rely on local passage utility, we propose to use both local query-passage relevance and global answer correctness to measure passage utility in a multi-turn agentic search. We further introduce an iterative training strategy, where the search agent and the retriever are optimized bidirectionally and iteratively. Different from RAG retrievers that are only trained once with fixed questions, our retriever is continuously improved using evolving and higher-quality queries from the agent. Extensive experiments on seven single-hop and multi-hop QA benchmarks demonstrate that our retriever, termed , consistently outperforms strong baselines across different search agents. Our codes are available at: https://github.com/8421BCD/Agentic-R.