Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]
| Date | Stars |
|---|---|
| 2026-07-24 | 1240 |
| 2026-07-25 | 1240 |
| 2026-07-28 | 1240 |
| 2026-07-30 | 1240 |
| 2026-07-31 | 1240 |
| 2026-08-06 | 1240 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h1 align="center"> 🔍 Search-o1: Agentic Search-Enhanced</br> Large Reasoning Models</a></h1>
<div align="center">
[](https://search-o1.github.io/)
[](https://arxiv.org/abs/2501.05366)
[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/release/python-390/)
[](https://x.com/_akhaliq/status/1877584951840764166?t=fnbTblnqhiPtAyYr1PHbbw&s=19)
</div>
<!-- <div align="center">
<span style="display:inline-block; margin-right: 10px;">
<a href="https://paperswithcode.com/sota/mathematical-reasoning-on-aime24?p=search-o1-agentic-search-enhanced-large">
<img src="https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/search-o1-agentic-search-enhanced-large/mathematical-reasoning-on-aime24" alt="AIME24 Badge">
</a>
</span>
<span style="display:inline-block; margin-right: 10px;">
<a href="https://paperswithcode.com/sota/mathematical-reasoning-on-amc23?p=search-o1-agentic-search-enhanced-large">
<img src="https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/search-o1-agentic-search-enhanced-large/mathematical-reasoning-on-amc23" alt="AMC23 Badge">
</a>
</span>
<span style="display:inline-block; margin-right: 10px;">
<a href="https://paperswithcode.com/sota/on-gpqa?p=search-o1-agentic-search-enhanced-large">
<img src="https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/search-o1-agentic-search-enhanced-large/on-gpqa" alt="GPQA Badge">
</a>
</span>
</div> -->
<h5 align="center"> If you like our project, please give us a star ⭐ on GitHub for the latest update.</h5>
## 📣 Latest News
- **08/21/2025**: 🎉 Search-o1 is accepted by EMNLP 2025 main conference!
- **05/01/2025**: 🎉 **Our new framework WebThinker is available**, which empowers reasoning models with **deep research** capability. You can access the [Github Repo](https://github.com/RUC-NLPIR/WebThinker) and the [Paper](https://arxiv.org/abs/2504.21776).
- **01/10/2025**: The brief introduction of our Search-o1 can be found on platforms like [X](https://x.com/_akhaliq/status/1877584951840764166?t=fnbTblnqhiPtAyYr1PHbbw&s=19), [Zhihu](https://zhuanlan.zhihu.com/p/17527068532), and [WeChat](https://mp.weixin.qq.com/s/J_n5cn_Zp4lRs8ESqFEFmg).
- **01/10/2025**: The paper for Search-o1 is available. You can access it on [arXiv](https://arxiv.org/abs/2501.05366), [alphaXiv](https://www.alphaxiv.org/abs/2501.05366) and [HF-paper](https://huggingface.co/papers/2501.05366).
- **01/06/2025**: The homepage for Search-o1 is available. You can access it [here](https://search-o1.github.io/).
- **01/05/2025**: The code for Search-o1 has been released. You can now apply Search-o1 to enhance your large reasoning models.
## ✏️ To Do List
- [ ] Add results of Search-o1 with different backbone reasoning models like [Sky-T1](https://novasky-ai.github.io/posts/sky-t1) and [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1).
- [ ] Train the reasoning models to better utilize search tool.
- [ ] Add more tools (e.g., calculators, code interpreters, ...) to further improve the capabilities of reasoning models.
## 💡 Overview
Large Reasoning Models (LRMs) like OpenAI's o1 have showcased remarkable long stepwise reasoning capabilities through large-scale reinforcement learning. Despite their strengths, these models often encounter knowledge insufficiencies during prolonged reasoning processes, resulting in frequent uncertainties and potential errors, as shown in the following figure.
<p align="center">
<img src="Excerpt of 11,091 characters
Read on GitHub
Xiaoxi Li · Renmin University of China · China
38
KABI · Renmin University of China (RUC) · China
25
21
Haidong Xin · ModelBest Inc. · China
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ce54430f3599c576, topic:rag