---
license: apache-2.0
base_model: Qwen/Qwen3.5-4B
tags: [debugging, code, reinforcement-learning, grpo, precisecoder]
---
# PreciseCoder-4B

📄 [Paper (arXiv:2610.18755)](https://arxiv.org/abs/2610.18755) · 🌐 [Project page](https://precise-coder-rl.github.io/) · 💻 [Code](https://github.com/precise-coder-rl/PreciseCoder)

Qwen3.5-4B post-trained with reinforcement learning for **precise debugging**: given buggy Python
code, produce a minimal, correct fix (PreciseCoder project).

**Recipe.** GDPO with two rewards, unit-test pass and unit-gated F1 (edit-block F1 against the ground-truth diff), weighted 2:1.

**Eval:**

| eval | result |
|---|---|
| PDB test (1205 BigCodeBench + LiveCodeBench debugging tasks) | unit 0.554 · precision 0.638 · recall 0.728 · F1 0.650 · edit lines 3.0 |
| PDB-Wild (474 tasks: BCB 37 + LCB 209 + SWE-smith 228) | unit 0.276 · precision 0.382 · recall 0.410 · F1 0.377 · edit lines 10.8 |
| GT Debug (1512 clean inputs) | no-op 54.7% · damage 12.1% · unit pass 87.9% |

`no-op` = share of clean (bug-free) inputs returned unchanged; `damage` = share broken by an edit.

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}
}
```