🛰️ Daily AI Frontier
‹ back to 2026-09-03

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

Research LLM Agents

Ranking

Overall 88
Content 95
Popularity 71

Observed public metrics from 1 member.

Representative image for Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Merged summary

TL;DR - Repo-To-Skill introduces DisCo, an autonomous ML research agent that distills operational knowledge from repositories into compact, verified skills. Adding these skills substantially improves research-agent performance without changing the model backbone, harness, or execution budget.

  • DisCo supports task-agnostic distillation of widely used repositories and task-oriented skill creation for specific research problems.
  • The resulting AREX-Skill Library contains over 5,000 verified skills from 1,000 ML repositories, spanning 20 areas and 178 capability families.
  • With GPT-5.5 and other experimental conditions fixed, skills improved scores by 134.3% on MLE-bench and 34.4% on PaperBench.
  • The same setup also produced gains of 9.2% on FrontierCS and 14.0% on PassNet, indicating that reusable operating context can reduce repeated implementation work.

Sources (1)

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

arXiv cs.AI Jianlyu Chen, Yuyang Hu, Hongjin Qian, Jiawei Liu, Wenqing Wei, Xiaolong Chen, Defu Lian, Zhicheng Dou, Chaozhuo Li, Qiwei Ye, Zheng Liu 2026-09-02 arXiv:2609.02749
Public signals Hugging Face upvotes 401
Providers: Hugging Face · Upvotes 401 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-25 14:24:37.740013 UTC

TL;DR - Repo-To-Skill introduces DisCo, an autonomous ML research agent that distills operational knowledge from repositories into compact, verified skills. Adding these skills substantially improves research-agent performance without changing the model backbone, harness, or execution budget.

  • DisCo supports task-agnostic distillation of widely used repositories and task-oriented skill creation for specific research problems.
  • The resulting AREX-Skill Library contains over 5,000 verified skills from 1,000 ML repositories, spanning 20 areas and 178 capability families.
  • With GPT-5.5 and other experimental conditions fixed, skills improved scores by 134.3% on MLE-bench and 34.4% on PaperBench.
  • The same setup also produced gains of 9.2% on FrontierCS and 14.0% on PassNet, indicating that reusable operating context can reduce repeated implementation work.
item →