Papers › Search-o1: Agentic Search-Enhanced Large Reasoning Models
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, Zhicheng Dou
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 \textbf{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 \url{https://github.com/sunnynexus/Search-o1}.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| GPQA | Search-o1 | Accuracy | 63.6 | #4 of 7 | Archive leaderboard | report | |
| Code Generation | Livecodebench | Search-o1 | Acc | 33 | #3 of 3 | Archive leaderboard | report |
| Mathematical Reasoning | AIME24 | Search-o1 | Acc | 56.7 | #5 of 9 | Archive leaderboard | report |
| Mathematical Reasoning | MATH500 | Search-o1 | Acc | 86.4 | #1 of 1 | Archive leaderboard | report |
| Question Answering | Natural Questions | Search-o1 | EM | 34 | #30 of 47 | Archive leaderboard | report |
| Question Answering | TriviaQA | Search-o1 | F1 | 74.1 | #53 of 56 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections