论文信息与摘要（原文）

原文标题：Search-o1: Agentic Search-Enhanced Large Reasoning Models arXiv：2501.05366（v1）　方向：第三批 检索与智能体：把知识与行动接入推理

以下为 arXiv 官方 HTML 全文，一字不落保留原文结构、图表与参考文献，仅供学习研究参考，版权归原作者所有。

Xiaoxi Li

Affiliation: Renmin University of China

Guanting Dong

Affiliation: Renmin University of China

Jiajie Jin

Affiliation: Renmin University of China

Yuyao Zhang

Affiliation: Renmin University of China

Yujia Zhou

Affiliation: Tsinghua University

Yutao Zhu

Affiliation: Renmin University of China

Peitian Zhang

Affiliation: Renmin University of China

Zhicheng Dou ††thanks: Correpsonding author. Email: {xiaoxi_li, dou}@ruc.edu.cnProject Page: https://search-o1.github.io/

Affiliation: Renmin University of China

Abstract

Large reasoning models (LRMs) like OpenAI-o1 have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning. However, their extended reasoning processes often suffer from knowledge insufficiency, leading to frequent uncertainties and potential errors. To address this limitation, we introduce Search-o1, a framework that enhances LRMs with an agentic retrieval-augmented generation (RAG) mechanism and a Reason-in-Documents module for refining retrieved documents. Search-o1 integrates an agentic search workflow into the reasoning process, enabling dynamic retrieval of external knowledge when LRMs encounter uncertain knowledge points. Additionally, due to the verbose nature of retrieved documents, we design a separate Reason-in-Documents module to deeply analyze the retrieved information before injecting it into the reasoning chain, minimizing noise and preserving coherent reasoning flow. Extensive experiments on complex reasoning tasks in science, mathematics, and coding, as well as six open-domain QA benchmarks, demonstrate the strong performance of Search-o1. This approach enhances the trustworthiness and applicability of LRMs in complex reasoning tasks, paving the way for more reliable and versatile intelligent systems. The code is available at https://github.com/sunnynexus/Search-o1.