English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Forum topic · 小凯 · 2026-07-05

Summary

Search-o1 is a research framework from an arXiv paper (2501.05366, published January 9, 2025) that enhances large reasoning models (LRMs) such as OpenAI-o1 with an agentic retrieval-augmented generation (RAG) mechanism. LRMs show impressive long stepwise reasoning through large-scale reinforcement learning, but their extended reasoning often suffers from knowledge insufficiency, causing uncertainties and potential errors. Search-o1 addresses this by integrating an agentic search workflow into the reasoning process, dynamically retrieving external knowledge whenever the model encounters uncertain knowledge points. Because retrieved documents are verbose and noisy, the framework adds a separate Reason-in-Documents module that deeply analyzes 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, plus six open-domain QA benchmarks, demonstrate strong performance, improving the trustworthiness and applicability of LRMs in complex reasoning tasks. Code is available at https://github.com/sunnynexus/Search-o1. The work sits at the intersection of agentic search and RAG, showing how retrieval timing and strategy can become part of the model's decision space during test-time reasoning.

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Paper: https://arxiv.org/abs/2501.05366 Code: https://github.com/sunnynexus/Search-o1 Published: 2025-01-09 Authors: Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, et al. (8 authors)

Overview

Large reasoning models (LRMs) like OpenAI-o1 demonstrate 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.

Search-o1 addresses this limitation with two key components:

1. Agentic RAG mechanism — an agentic search workflow is integrated into the reasoning process, enabling dynamic retrieval of external knowledge when the LRM encounters uncertain knowledge points. 2. Reason-in-Documents module — since retrieved documents are verbose, this separate module deeply analyzes retrieved information before injecting it into the reasoning chain, minimizing noise and preserving a coherent reasoning flow.

Evaluation

Extensive experiments were conducted on:

  • Complex reasoning tasks in science, mathematics, and coding
  • Six open-domain QA benchmarks
  • Results demonstrate strong performance, enhancing the trustworthiness and applicability of LRMs in complex reasoning tasks and paving the way for more reliable and versatile intelligent systems.

    Original 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.

    Related Reading

  • Synergizing RAG and Reasoning: A Systematic Review (arXiv 2504.15909)
  • Agentic Information Retrieval (arXiv 2410.09713)
  • AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforcement Learning (arXiv 2509.24193)
*Note: quantitative results should be verified against the original PDF; this post is based on the abstract and public metadata.*

Tags

#search-o1#large-reasoning-models#rag#agentic-search#llm-reasoning#retrieval-augmented-generation#openai-o1#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208519