ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
ScienceIDE converts scientific code repositories into verifiable agent training environments, producing the PhAI-IDE 4B-72B model family.
ScienceIDE turns scientific code repositories into executable environments supporting task generation, execution, and scientific verification, guided by expert-defined scientific cases and acceptance criteria. Using verified interaction trajectories, the authors train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family shows gains in held-out scientific-code repair and selected general-purpose code, reasoning, and knowledge benchmarks, evidencing positive transfer from scientific experience.
- Converts scientific repositories into executable environments for task generation and verification
- Trains PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B from verified trajectories
- Gains on held-out scientific-code repair tasks
- Positive transfer to general code, reasoning, and knowledge benchmarks
- Supports supervised fine-tuning, reinforcement learning, and evaluation
- AI models
- ScienceIDE
From the original article
1 min read at huggingface.co
Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the scientific experience bottleneck.
By Hejia Geng, Zesen Huang, Haoyang Li · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.