| --- |
| license: apache-2.0 |
| base_model: Qwen/Qwen3.5-9B |
| tags: [debugging, code, reinforcement-learning, gdpo, agent, precisecoder] |
| --- |
| # PreciseCoder-9B-Agent |
|
|
| 馃搫 [Paper (arXiv:2610.18755)](https://arxiv.org/abs/2610.18755) 路 馃寪 [Project page](https://precise-coder-rl.github.io/) 路 馃捇 [Code](https://github.com/precise-coder-rl/PreciseCoder) |
|
|
| Qwen3.5-9B post-trained with multi-turn agentic reinforcement learning for **precise debugging**: the model |
| inspects buggy Python code with tools and repairs it with minimal edits (PreciseCoder project). |
|
|
| **Recipe.** Agentic GDPO from the base model, with two rewards weighted 2:1: unit-test pass and unit-gated F1 |
| (edit-block F1 against the ground-truth diff). The agent loop has up to 5 turns with `view`, `str_replace_editor` |
| and `submit` tools. 328 steps, final checkpoint. |
|
|
| **Eval:** |
|
|
| | eval | result | |
| |---|---| |
| | PDB test, agentic (1205 BigCodeBench + LiveCodeBench debugging tasks, 5 turns) | unit 0.685 路 precision 0.721 路 recall 0.796 路 F1 0.731 路 edit lines 2.9 | |
|
|
| Load with `transformers` / vLLM (>=0.17) as a standard Qwen3.5 model (thinking enabled by default). |
|
|
| ## Citation |
|
|
| ```bibtex |
| @article{precisecoder, |
| title = {{PreciseCoder}: Faithful and Generalizable Debugging Beyond Unit-Test Rewards}, |
| author = {Zhan, Yunkai and Chai, Miaosen and Wang, Shangshang and Zhong, Jike and Yang, Yuqing and Fu, Deqing and Chang, Serina and Zhu, Wang Bill}, |
| journal = {arXiv preprint arXiv:2610.18755}, |
| year = {2026} |
| } |
| ``` |
|
|
