Paper Detail

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Jianlyu Chen, Yuyang Hu, Hongjin Qian, Jiawei Liu, Wenqing Wei, Xiaolong Chen, Defu Lian, Zhicheng Dou, Chaozhuo Li, Qiwei Ye, Zheng Liu

huggingface Score 11.5

Published 2026-09-02 · First seen 2026-09-03

General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{chen2026repo,
  title = {Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills},
  author = {Jianlyu Chen and Yuyang Hu and Hongjin Qian and Jiawei Liu and Wenqing Wei and Xiaolong Chen and Defu Lian and Zhicheng Dou and Chaozhuo Li and Qiwei Ye and Zheng Liu},
  year = {2026},
  abstract = {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 huma},
  url = {https://huggingface.co/papers/2609.02749},
  keywords = {autonomous agents, machine-learning research, operational knowledge, skill distillation, DisCo, AREX-Skill Library, MLE-bench, PaperBench, code available, huggingface daily},
  eprint = {2609.02749},
  archiveprefix = {arXiv},
}

Metadata

{}