ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
ScienceIDE turns scientific code repositories into agent-trainable environments and trains PhAI-IDE models at 72B, 9B, and 4B scales.
ScienceIDE is infrastructure that transforms scientific repositories into executable environments supporting task generation, execution, and scientific verification, guided by expert-defined cases and acceptance criteria. Using verified interaction trajectories, the authors train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family improves held-out scientific-code repair and selected general benchmarks in code, reasoning, and knowledge, indicating positive transfer. Code is released on GitHub.
- Addresses the 'scientific experience bottleneck' from fragmented toolchains and implicit conventions
- Environments support supervised fine-tuning, reinforcement learning, and evaluation
- Training uses verified agent interaction trajectories from transformed repositories
- Gains shown in scientific-code repair plus general code, reasoning, and knowledge benchmarks
- AI models
- PhAI-IDE-72BPhAI-IDE-9BPhAI-IDE-4B
From the original article
1 min read at arxiv.orgScientific 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 · arxiv.org
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.