| --- |
| library_name: transformers |
| license: apache-2.0 |
| language: |
| - en |
| base_model: Qwen/Qwen3-1.7B |
| pipeline_tag: text-generation |
| tags: |
| - code-search |
| - code-localization |
| - reinforcement-learning |
| - agent |
| - software-engineering |
| - GSPO |
| - OpenHands |
| - SWE-Bench |
| datasets: |
| - OpenHands/SWE-smith-py-code-search |
| - OpenHands/SWE-Gym-code-search |
| - OpenHands/CodeScout_Training_Rollouts |
| --- |
| |
| # CodeScout-1.7B-RFT |
|
|
| [📄 Paper](https://arxiv.org/abs/2507.02875) • [💻 Code](https://github.com/OpenHands/codescout) • [🤗 Collection](https://huggingface.co/collections/OpenHands/codescout-69b9a6adcf21f348f4db937f) |
|
|
| **Pre-RL checkpoint — rejection fine-tuned on expert trajectories from CodeScout-14B.** |
|
|
| CodeScout-1.7B-RFT is part of the **CodeScout** family of open-source RL-trained code search agents. |
| CodeScout models achieve state-of-the-art repository-level code localization using *nothing more than a standard Unix terminal* — no static analysis, no repository graphs, no language-specific tooling. |
|
|
| ## Key Highlights |
|
|
| - Warm-start checkpoint for [CodeScout-1.7B](https://huggingface.co/OpenHands/CodeScout-1.7B) RL training |
| - Distilled from CodeScout-14B expert trajectories with rejection sampling |
| - Useful for researchers studying the effect of RFT vs. RL in agent training pipelines |
| - Can be used as a base for custom RL experiments on code search |
|
|
| ## Results |
|
|
| Performance on SWE-Bench code localization (instance-averaged F1 scores): |
|
|
|
|
| | Benchmark | CodeScout-1.7B | CodeScout-4B | CodeScout-14B | |
| |---|---|---|---| |
| | **SWE-Bench Verified** — File F1 | 55.46 | 68.52 | **68.57** | |
| | **SWE-Bench Verified** — Func F1 | 28.22 | 36.78 | **40.32** | |
| | **SWE-Bench Pro** — File F1 | 40.96 | 51.77 | **53.63** | |
| | **SWE-Bench Pro** — Func F1 | 18.24 | **29.03** | 28.74 | |
| | **SWE-Bench Lite** — File F1 | 56.57 | 67.03 | **71.84** | |
| | **SWE-Bench Lite** — Func F1 | 27.07 | 39.87 | **44.43** | |
|
|
|
|
| ## Training |
|
|
| CodeScout-1.7B-RFT is the intermediate checkpoint produced by rejection fine-tuning (RFT) `Qwen3-1.7B` on expert trajectories from CodeScout-14B, before the final RL stage. |
|
|
| - **Teacher model:** [CodeScout-14B](https://huggingface.co/OpenHands/CodeScout-14B) |
| - **Source trajectories:** Rollouts from CodeScout-14B on 7,700 training instances |
| - **Filtered data:** 4K trajectories with perfect scores (F1 = 1.0 at file, module, and function level) |
| - **SFT epochs:** 1 |
| - **Learning rate:** 5e-5 with cosine scheduler (warmup ratio 0.1) |
| - **Batch size:** 8 |
| - **Optimizer:** AdamW |
| - **Framework:** [veRL](https://github.com/volcengine/verl) |
|
|
| This checkpoint serves as the starting point for RL training of [CodeScout-1.7B](https://huggingface.co/OpenHands/CodeScout-1.7B). |
|
|
| ## How It Works |
|
|
| CodeScout uses the **OpenHands-Bash** scaffold — an agent equipped with only a `Terminal` tool (supporting standard Unix commands like `rg`, `find`, `grep`, `ls`) and a `LocalizationFinish` tool for structured output submission. The agent iteratively navigates the repository to identify relevant files, classes, and functions related to a given issue. |
|
|
| The model is trained with **GSPO** (Group Sequence Policy Optimization) using multi-level F1 rewards at the file, module, and function level. |
|
|
| ## Intended Use |
|
|
| CodeScout-1.7B-RFT is designed for **repository-level code localization**: given a GitHub issue description and a code repository, it identifies the relevant files, classes, and functions that need to be modified. It is intended to be used as a localization subagent within larger coding agent pipelines. |
|
|
| ## Limitations |
|
|
| - Trained and evaluated exclusively on **Python** repositories |
| - Designed for code *localization*, not code *editing* or issue resolution |
| - Performance may vary on repositories significantly different from the training distribution |
| - Requires the OpenHands-Bash scaffold for optimal performance |
|
|
| ## Citation |
|
|
|
|
| ```bibtex |
| @article{sutawika2025codescout, |
| title={CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents}, |
| author={Sutawika, Lintang and Soni, Aditya Bharat and R R, Bharath Sriraam and Gandhi, Apurva and Yassine, Taha and Vijayvargiya, Sanidhya and Li, Yuchen and Zhou, Xuhui and Zhang, Yilin and Maben, Leander Melroy and Neubig, Graham}, |
| journal={arXiv preprint arXiv:2507.02875}, |
| year={2025} |
| } |
| ``` |
|
|
|
|
