把代码库变成训练场：AI 学写代码的新原料
训练 AI 写代码，最缺的不是模型，而是「练习题」。过去得靠人工标注 bug 和修复记录，又贵又少。这篇的思路是：直接把 GitHub 上现成的开源代码当教材——让 AI 自己读代码、自己出题、自己验证答案，从 3,185 个开源项目里榨出 5,545 道训练题，覆盖 23 种编程语言。用这批题练出来的模型，在修 bug、写整段程序、操作终端等五个测试里全面变强，最高提升 17%。它不是你明天能直接用的工具，但它指了个方向：AI 学写代码，可能不再需要人类出题了。
📄 原文摘要(英文)
Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich source of such tasks, while existing methods typically rely on development artifacts such as issues and commits, limiting the range of tasks that can be extracted. To better scale RL environments, we present CodeMidas, an agentic pipeline that turns implemented functionality in existing codebases into executable RL environments using source code as its only task-specific input. CodeMidas allocates agentic compute to every stage of environment construction: agents explore implemented functionality to formulate behavioral specifications, construct tests grounded in execution of the original code, and validate and filter candidate tasks through execution checks and repeated solution rollouts. The resulting dataset has 5,545 training tasks from 3,185 open-source codebases spanning 23 programming languages and 15 technical domains. Training MiMo-V2.5 on these tasks with GRPO improves performance on all five diverse benchmarks, covering issue repair (DeepSWE + 11.7%), whole-program construction (ProgramBench +17%), and terminal work (Terminal-Bench v2.1 +8.5%). Ablations show that increasing the number of high-quality training tasks improves performance. Trajectory analysis shows the RL-trained agent demonstrates better behaviors like increasing codebase exploration and more diverse self-verification. These results establish source code as a scalable foundation for constructing RL environments that improve coding agents across diverse software tasks.