把 GitHub 仓库蒸馏成技能，AI 研究员成绩翻倍
AI 做科研，一直有个尴尬：它知道方法，但不会用。论文和代码仓库里全是「怎么让方法跑起来」的实操经验，可这些是写给人类看的，又长又散，AI 在干活时根本来不及读。这篇把 1000 个最常用的机器学习仓库，蒸馏成 5000 多条「技能」——每条都是经过验证的、能直接调用的操作知识，按 20 个领域、178 个能力族整理好。装上这套技能库的 AI 研究员，在 MLE-bench 上分数提高了 134%，其他三个科研基准也涨了 9% 到 34%。这不是换了个更强的模型，而是同一套系统、同样的算力，只加了这些蒸馏出来的「操作上下文」。它不是你明天能用上的东西，但它指向一个趋势：AI 的能力竞争，正在从「模型多大」转向「经验怎么沉淀和复用」。
📄 原文摘要(英文)
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and verification, but this architecture still leaves domain-specific know-how outside the agent. We call this missing layer operational knowledge, the know-how that separates knowing a method from making it work. That knowledge is not absent from the field. It appears in repositories and papers, but in forms written for human readers and too large to load during a task. Once distilled into compact, verified skills, this knowledge can be reused across tasks rather than rediscovered during each run. We present DisCo, a skill-powered research agent that creates skills and uses them during research. Its distillation runs in two complementary forms: task-agnostic, condensing the field's widely used repositories into reusable skills, and task-oriented, producing the skills a concrete task calls for. The former, applied across the open ecosystem, yields the AREX-Skill Library, with 5,000+ verified skills distilled from 1,000 widely used ML repositories and organized into 20 areas and 178 capability families. With the GPT-5.5 backbone, research harness, and downstream execution budget held fixed, the skill-equipped research agent scores 134.3% higher on MLE-bench, 34.4% higher on PaperBench, 9.2% higher on FrontierCS, and 14.0% higher on PassNet than the same agent without skills. These gains come from adding distilled operating context under that fixed setup.