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

介绍

科学集成开发平台

科学经验基础设施：关注真实科学代码、任务、环境和强化学习训练。

ScienceIDE 是一项面向真实科学代码库、研究任务和可验证科学经验的独立基础设施探索。

它把真实科学代码、研究流程、任务目标和验证标准转化为可运行、可测量、可复现的科学环境，让研究者能够在真实科学场景中开展 Agent 执行、模型训练和强化学习研究。

它的核心价值在于，把真实科学软件、领域判断、任务目标和可验证反馈组织到同一个可执行环境中，为科研 Agent、模型训练、强化学习和科学发现研究提供经验基础。ScienceIDE 不要求接入 ScienceBuddy 才能使用，也不依赖 JEPA-Anything 才能成立。

当前任务形态

加速
发现
修复
复现
集成

项目主页、技术报告和 PhAI-IDE 系列模型权重均已公开，模型用 ScienceIDE 中已验证的交互轨迹训练。ScienceIDE 继续接受任务提案。

摘要

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.

作者

Hejia Geng*, Zesen Huang*, Haoyang Li, Wenbin Li, Koutian Wu, Zihan Zhou, Yuanbo Pang, Weihao Liu, Zigong Xu, Zhiping Li, Zongzheng Zhang, Chuanfei Dong, Jiankai Sun, Tianzhe Zheng, Fengyu Xie, Yue Ma, Yueheng Shi, Junkai Wang, Tong Xie, Zonglin Di, Xianrong Liu, Qucheng Gao, Yimin Liu, Jiaming Pan, Sheng Huang, Xiao-Han Ma, Lanqing Yuan, Zhenlin Zhu, Ziang Liu, Ziyang Xu, Kangkai Liang, Jiayi Xian, Zehong Zhao, Taigao Ma, Fuming Chang, Yuanzhe Hu, Liuwei Xu, Xianzhe Tang, Jingxu Xie, Peijin Zhang, Qiang Gao, Chengyi Xing, Zhe Zhao, Xi Wang, Leo Wang, Fang Wu, Yaopeng Xing, Xing Meng, Zhenfei Yin, Yingcheng Wu, Ling Yang

* 共同一作

引用

BibTeX

@article{geng2026scienceide,
  title={ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments},
  author={Geng, Hejia and Huang, Zesen and Li, Haoyang and Li, Wenbin and Wu, Koutian and Zhou, Zihan and Pang, Yuanbo and Liu, Weihao and Xu, Zigong and Li, Zhiping and Zhang, Zongzheng and Dong, Chuanfei and Sun, Jiankai and Zheng, Tianzhe and Xie, Fengyu and Ma, Yue and Shi, Yueheng and Wang, Junkai and Xie, Tong and Di, Zonglin and Liu, Xianrong and Gao, Qucheng and Liu, Yimin and Pan, Jiaming and Huang, Sheng and Ma, Xiao-Han and Yuan, Lanqing and Zhu, Zhenlin and Liu, Ziang and Xu, Ziyang and Liang, Kangkai and Xian, Jiayi and Zhao, Zehong and Ma, Taigao and Chang, Fuming and Hu, Yuanzhe and Xu, Liuwei and Tang, Xianzhe and Xie, Jingxu and Zhang, Peijin and Gao, Qiang and Xing, Chengyi and Zhao, Zhe and Wang, Xi and Wang, Leo and Wu, Fang and Xing, Yaopeng and Meng, Xing and Yin, Zhenfei and Wu, Yingcheng and Yang, Ling},
  journal={arXiv preprint arXiv:2609.19134},
  year={2026}
}

介绍

摘要

作者

期刊/会议

引用