ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

2026-09-16

AI Summary

为解决科学代码转化为可靠学习经验的难题，ScienceIDE通过专家定义的科学案例和接受标准，将科学代码库转化为可执行环境，支持任务生成、执行和科学验证。

Abstract

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. We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents. Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task generation, execution, and scientific verification. These environments provide a shared foundation for supervised fine-tuning, reinforcement learning, and evaluation. Using verified interaction trajectories, we train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities. ScienceIDE lays the foundation for an integrated workspace for agent learning and scientific practice, making humanity's scientific software a shared substrate for developing scientific intelligence. Code: https://github.com/aitofound/ScienceIDE

Problem

• scientific experience bottleneck
• executable environments
• scientific code

Innovation

• Scientific Code
• Agent Learnable Environments
• Programmable Environments
• Reinforcement Learning
• Supervised Fine-Tuning