38 lines
1.3 KiB
Markdown
38 lines
1.3 KiB
Markdown
|
---
|
||
|
|
license: mit
|
||
|
|
library_name: transformers
|
||
|
|
---
|
||
|
|
|
||
|
|
<p align="center">
|
||
|
|
<img src="https://github.com/yinjjiew/Data/raw/main/cure/overviewplot.png" width="100%"/>
|
||
|
|
</p>
|
||
|
|
|
||
|
|
|
||
|
|
<p align="center">
|
||
|
|
<img src="https://github.com/yinjjiew/Data/raw/main/cure/results.png" width="100%"/>
|
||
|
|
</p>
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# Introduction to our ReasonFlux-Coders
|
||
|
|
|
||
|
|
We introduce **ReasonFlux-Coders**, trained with **CURE**, our algorithm for co-evolving an LLM's coding and unit test generation abilities.
|
||
|
|
|
||
|
|
* **ReasonFlux-Coder-7B** and **ReasonFlux-Coder-14B** outperform similarly sized Qwen Coders, DeepSeek Coders, and Seed-Coders, and naturally integrate into common test-time scaling and agentic coding pipelines.
|
||
|
|
* **ReasonFlux-Coder-4B** is our Long-CoT model, outperforming Qwen3-4B while achieving 64.8% efficiency in unit test generation. We have demonstrated its ability to serve as a reward model for training base models via reinforcement learning (see our [paper](https://arxiv.org/abs/2506.03136)).
|
||
|
|
|
||
|
|
|
||
|
|
[Paper](https://arxiv.org/abs/2506.03136) | [Code](https://github.com/Gen-Verse/CURE)
|
||
|
|
|
||
|
|
# Citation
|
||
|
|
|
||
|
|
```
|
||
|
|
@article{wang2025cure,
|
||
|
|
title={Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning},
|
||
|
|
author={Wang, Yinjie and Yang, Ling and Tian, Ye and Shen, Ke and Wang, Mengdi},
|
||
|
|
journal={arXiv preprint arXiv:2506.03136},
|
||
|
|
year={2025}
|
||
|
|
}
|
||
|
|
```
|