Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills· GitHub 仓库到 AI 技能
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 i
将 GitHub 仓库知识提炼为 AI 研究技能。
- 核心方法
- 提出 DisCo，一种能够从 GitHub 仓库中提取知识并将其转化为紧凑、可验证技能的研究代理。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 自主代理在进行端到端的机器学习研究时缺乏领域特定的操作知识。
- 关键实验
- 未提供
- 主要贡献
- 实现了从 GitHub 仓库自动提炼技能的过程，并展示了如何在 ML 研究中重用这些技能。
- 意义与局限
- 拓展了自主代理的能力，使其能够利用人类编码的知识，提高了研究效率。但该方法可能受限于 GitHub 仓库的质量和范围。