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.
The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.
| Date | Stars |
|---|---|
| 2026-07-31 | 446 |
| 2026-08-02 | 446 |
| 2026-08-03 | 446 |
| 2026-08-05 | 447 |
| 2026-08-06 | 447 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
# The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning
[](https://arxiv.org/pdf/2505.22617) [](https://github.com/PRIME-RL/Entropy-Mechanism-of-RL) [](https://www.alphaxiv.org/abs/2505.22617) [](https://x.com/stingning/status/1928088554166505667) [](https://x.com/charlesfornlp/status/1928089451080585283) [](https://x.com/_akhaliq/status/1928077929105268861)
<div align="center" style="font-family: Arial, sans-serif;">
<p>
<a href="#🎉news" style="text-decoration: none; font-weight: bold;">🎉 News</a> •
<a href="#✨getting-started" style="text-decoration: none; font-weight: bold;">✨ Getting Started</a> •
<a href="#📖introduction" style="text-decoration: none; font-weight: bold;">📖 Introduction</a>
</p>
<p>
<a href="#🎈citation" style="text-decoration: none; font-weight: bold;">🎈 Citation</a> •
<a href="#🌻acknowledgement" style="text-decoration: none; font-weight: bold;">🌻 Acknowledgement</a> •
<a href="#📬Contact" style="text-decoration: none; font-weight: bold;">📬 Contact</a> •
<a href="#📈star-history" style="text-decoration: none; font-weight: bold;">📈 Star History</a>
</p>
</div>
</div>
# 🎉News
- **[2025/06/20]** 🎉 **Our KL_Cov and Clip_Cov are merged into [verl](https://github.com/volcengine/verl/pull/1830)!** One can use our method easily in verl main with setting loss_mode as "clip_cov" or "kl_cov", an example script in verl can be found [here](https://github.com/volcengine/verl/blob/main/recipe/entropy/32b_kl_cov.sh).
- **[2025/06/04]** Sent a PR to verl, one can use our approaches in verl with PR [#1830](https://github.com/volcengine/verl/pull/1830).
- **[2025/06/03]** 🎉 Ranked **#3** of the week on [Huggingface Weekly Papers](https://huggingface.co/papers/week/2025-W22).
- **[2025/05/29]** 🎉 Ranked **#1** of the day on [Huggingface Daily Papers](https://huggingface.co/papers?date=2025-05-29).
- **[2025/05/29]** Released our Paper on arXiv. See [here](https://arxiv.org/pdf/2505.22617). We provide insights into the entropy mechanism of RL for LLMs and propose two simple yet effective strategies to alleviate the entropy collapse.
# ✨Getting started
This repo is forked from [verl](https://github.com/volcengine/verl). We build our code on the [dapo recipe](https://github.com/PRIME-RL/Entropy-Mechanism-of-RL/tree/main/recipe/dapo).
**Note:** For any training and test set, please modify the system prompt and specify the answer in the format of `\boxed{}`, as we need to extract the answer based on `\boxed{}` for verification.
Our training and evaluation data can be found [here](https://drive.google.com/drive/folders/1AhZ3yyfesVlz9dvIV0eR2LbiWz_XFHMX?usp=sharing).
## Installation
You can install dependencies by running the following commands:
```
conda env create -n entropy -f environment.yaml
```
## Training
Before training, you need to ensure that the AIME, AIME25 and AMC datasets are with "data_source" of "aime", "aime25" and "amc" respectively. As we hardcode it to make sure they are rollouted with temperature of 0.6.
For training Qwen2.5-7B on a single node, taking the KL-Cov approach as an example, you can simply run:
```
cd Entropy-Mechanism-of-RL
conda activate entropy
bash recipe/dapo/7b_kl_cov.sh
```
While for training Qwen2.5-32B on multi nodes, you Excerpt of 8,101 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a1747add59e219b1, llm:Repository title and description: 'The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.' topics: llm, reasoning, rl
matched fp:a1747add59e219b1, llm:Repository title and description: 'The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.' topics: llm, reasoning, rl
matched fp:a1747add59e219b1, llm:Repository title and description: 'The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.' topics: llm, reasoning, rl