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.
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
| Date | Stars |
|---|---|
| 2026-07-24 | 1412 |
| 2026-07-25 | 1421 |
| 2026-07-28 | 1421 |
| 2026-07-30 | 1421 |
| 2026-07-31 | 1426 |
| 2026-08-06 | 1426 |
Today
— stars today
This week
+5 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.35%/day
<div align="center"> # ***ReCall***: Learning to ***Re***ason with Tool ***Call*** for LLMs via Reinforcement Learning [](https://attractive-almandine-935.notion.site/ReCall-Learning-to-Reason-with-Tool-Call-for-LLMs-via-Reinforcement-Learning-1d7aec91e9bb8006ad40f9edbfe2191a) [](https://arxiv.org/abs/2503.19470) [](https://huggingface.co/collections/agentrl/research-67e506a0311bea06dc54878b) </div> We introduce ***ReCall***, a novel framework that trains LLMs to ***Re***ason with Tool ***Call*** via reinforcement learning—without requiring any supervised data on tool use trajectories or reasoning steps. *ReCall* empowers LLMs to agentically use and combine arbitrary tools like [OpenAI o3](https://openai.com/index/introducing-o3-and-o4-mini/), offering an accessible approach toward general-purpose agents. Additionally, we provide a novel perspective to generate synthetic data with diverse environments and complex multi-step tasks, enabling LLMs to develop sophisticated tool-based reasoning capabilities. This is a work in progress and we are actively working on it. > [!IMPORTANT] > *ReCall* is the successor to [*ReSearch*](https://arxiv.org/abs/2503.19470) and represents a more comprehensive framework that extends beyond the search tool to support reasoning with any user-defined tools. It can be a drop-in replacement of *ReSearch*. We've archived the original implementation of *ReSearch* in the branch `re-search`. <p align="center"> <img src="./assets/overview.png" width="90%" alt="Overview" /> <img src="./assets/eval_bar.png" width="90%" alt="Eval" /> </p> ## 📰 News - **[2025-04-24]** 🎉 We release the first version of *ReCall*, and archive the original implementation of *ReSearch*. - ➡️ The name of the repository is changed from *ReSearch* to *ReCall*. - 📝 We release a [blog](https://attractive-almandine-935.notion.site/ReCall-Learning-to-Reason-with-Tool-Call-for-LLMs-via-Reinforcement-Learning-1d7aec91e9bb8006ad40f9edbfe2191a) to introduce the idea of *ReCall*. - 📦 Current implementation of *ReCall* is based on verl 0.3.0 + vllm 0.8.4. - **[2025-03-27]** 🤗 We release our trained *ReSearch* models on [Hugging Face](https://huggingface.co/collections/agentrl/research-67e506a0311bea06dc54878b), please check it out! - **[2025-03-26]** 🎉 We release the paper and update the code of *ReSearch*. - 📝 The **paper is released** on arXiv, more details and evaluation results can be found in our [paper](https://arxiv.org/abs/2503.19470). - 🛠️ The **repository is updated** with the new implementation, especially the rollout with search during RL training. This version of implementation is based on the latest release of verl. - **[2025-03-03]** ✅ We have released the preview version of *ReSearch* implementation. ## 📦 Installation We recommend using conda to manage the environment. First create a conda environment and activate it. ```bash conda create -n re-call python==3.10 conda activate re-call ``` Then install dependencies, and the packages under ```src/``` will be installed in the editable mode. Check out ```setup.py``` for details. ```bash git clone https://github.com/Agent-RL/ReCall.git cd ReCall pip3 install -e . pip3 install flash-attn --no-build-isolation ``` If you want to host a Wikipedia RAG system based on FlashRAG, you need to install faiss-gpu as follow. As described in the [FlashRAG](https://github.com/RUC-NLPIR/FlashRAG?tab=readme-ov-file#wrench-installation), due to the incompatibility when installing faiss using pip, we need to use the following conda command to install faiss-gpu. ```bash conda install -c pytorch -c nvidia faiss-gpu=1.8.0 ``` ## 🚀 Quick Start > If you want to learn the details of current version of *ReCall*, please refer to the [blog]
Excerpt of 10,948 characters
Read on GitHub
8
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d9ccfd6bb665b001, topic:reinforcement-learning, desc:reinforcement learning, readme:reinforcement learning
matched fp:d9ccfd6bb665b001, topic:llm
matched fp:d9ccfd6bb665b001, topic:function-calling