---
library_name: transformers
tags:
- fuzzing
- code-generation
- grpo
- rl
base_model:
- Qwen/Qwen2.5-Coder-32B-Instruct
pipeline_tag: text-generation
language:
- en
---

# RLDriver

GRPO-fine-tuned Qwen/Qwen2.5-Coder-32B-Instruct for fuzzing harness generation. Trained on 10 C/C++ libraries (cJSON, curl, libjpeg, libtiff, libvpx, zlib, …) with four reward tasks: coverage, alignment, throughput, and stateful API interaction.

See the [code repository](https://anonymous.4open.science/r/RLDriver-5FD9/) for training scripts and the static-analysis backend.