README.md

metadata

title: DebugArena
emoji: 🐛
colorFrom: blue
colorTo: green
sdk: docker
pinned: false
license: apache-2.0
tags:
  - reinforcement-learning
  - openenv
  - code-debugging
  - grpo

DebugArena 🐛

Meta PyTorch OpenEnv Hackathon × Scaler School of Technology 2026 | Theme 4: Self-Improving Agents

DebugArena is an RL environment where an agent learns to fix buggy Python code through trial and error. Fine-tuned on Qwen2.5-Coder-0.5B using GRPO, the model improved its solve rate from 35% to 45% entirely through test-failure reward signals.

📖 Read the Full Story

The organizers requested that the main project write-up be kept separate from the README.

➡️ Click here to read the full project breakdown in Blog.MD (The blog covers the problem statement, the GRPO training pipeline, the custom reward functions, and how we overcame 'Reward Hacking' during training).

🛠️ Quick Links

• Training Notebook: View the code on Kaggle
• Environment Code: Check the server/environment.py file in this repository.