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.
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
| Date | Stars |
|---|---|
| 2026-07-31 | 721 |
| 2026-08-01 | 721 |
| 2026-08-02 | 722 |
| 2026-08-06 | 722 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h1 align="center"> R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning</a></h1>
<div align="center">
<a href="https://github.com/RUCAIBox/RLRAG/edit/main//LICENSE"><img src="https://img.shields.io/badge/Code_License-MIT-blue" alt="license"></a>
<a href="https://github.com/RUCAIBox/RLRAG/edit/main//LICENSE"><img src="https://img.shields.io/badge/Model_License-MIT-blue" alt="license"></a>
<a href="[https://huggingface.co/collections/yulan-team/yulan-mini-676d214b24376739b00d95f3](https://github.com/RUCAIBox/RLRAG)"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-blue?color=8A2BE2"></a>
<a href="https://arxiv.org/pdf/2503.05592" target="_blank"><img src=https://img.shields.io/badge/arXiv-b5212f.svg?logo=arxiv></a>
</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>
# ✨ News
+ [22 May 2025] ⚡️⚡️ [**R1-Searcher++**](https://github.com/RUCAIBox/R1-Searcher-plus):We propose **R1-Searcher++**, a framework for training LLMs to adaptively use internal and external knowledge. It uses a two-stage strategy: an initial SFT Cold-start phase for basic format learning, and an RL phase for Dynamic
Knowledge Acquisition. In the RL phase, we introduce a reward mechanism for the utilization of internal knowledge and integrate a memorization mechanism to continuously assimilate the retrieved information, thereby enriching the model's internal knowledge.
The paper can be found here: [**arxiv.org/abs/2505.17005**](https://arxiv.org/abs/2505.17005)
+ [22 May 2025] ⚡️⚡️ [**SimpleDeepSearcher-paper**](https://github.com/RUCAIBox/SimpleDeepSearcher):We release the paper of the SimpleDeepSearcher, which also explores the impact of using a distilled model as the backbone for continued reinforcement learning training, as well as the effects of incorporating long cot math reasoning data during the training process. Additionally, the paper includes comprehensive experiments. The paper can be found here: [**arxiv.org/abs/2505.16834**](https://arxiv.org/abs/2505.16834)
+ [16 Apr 2025] ⚡️⚡️ [**SimpleDeepSearcher**](https://github.com/RUCAIBox/SimpleDeepSearcher):We propose **SimpleDeepSearcher**, a framework designed to stimulate autonomous retrieval during complex reasoning via knowledge distillation and self-distillation. The goal is to achieve efficient and effective training using only a small amount of data.
+ [8 Mar 2025] ⚡️⚡️ [**R1-Searcher**](https://arxiv.org/abs/2503.05592)We propose **R1-searcher**, utilizing a *two-stage outcome-supervision reinforcement learning* approach to enable the model to learn to invoke web search during the reasoning process: first allowing the model to learn how to invoke web search, and then teaching it how to effectiExcerpt of 14,105 characters
Read on GitHub
63
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:aa18c5e6377d9d21, desc:reinforcement learning