• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    BAAI Paper Distills Repos Into AI4AI Skills

    Tweet promotes BAAI paper on distilling GitHub repositories into skills for research agents.

    DA
    2 Sources, 27d ago, first seen 27d ago

    TLDR

    DAIR.AI posted about a BAAI paper titled Repo-To-Skill. The work introduces DisCo and the AREX-Skill Library. It distills 1,000 widely used ML repositories into skills. The post states that adding these skills produces higher scores on MLE-bench, PaperBench, FrontierCS and PassNet. The arXiv abstract notes that autonomous agents now combine a model backbone with planning, execution, memory and verification to carry out machine-learning research end to end.

    Combined views

    10K

    2 Sources, first seen 27d ago

    Combined views

    10K

    2 Sources, first seen 27d ago

    104 likes
    104 likes
    6 comments
    139 saves
    27 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    6 comments
    139 saves
    27 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    @dair_aiBanger paper from BAAI. If you are building research agents, this one is worth your time. (bookmark it) They find that adding skills scores 134.3% higher on MLE-bench, 34.4% higher on PaperBench, 9.2% higher on FrontierCS and 14.0% higher on PassNet. More details on the approach: The agent has a strong backbone and a harness for planning, execution, memory and verification, and it still does not know how to make a given method actually work. That know-how lives in repositories and papers, written for human readers and far too large to load during a task. DisCo distills it. Task-agnostic distillation condenses 1,000 widely used ML repositories into the AREX-Skill Library, over 5,000 verified skills organized into 20 areas and 178 capability families. Task-oriented distillation writes the skills a concrete task calls for. Paper: https://arxiv.org/abs/2609.02749 Chat with Paper: https://academy.dair.ai/papers/repo-to-skill-distilling-github-repositories-into-ai4ai-skills-2609.02749

    2 Sources

    @dair_aiBanger paper from BAAI. If you are building research agents, this one is worth your time. (bookmark it) They find that adding skills scores 134.3% higher on MLE-bench, 34.4% higher on PaperBench, 9.2% higher on FrontierCS and 14.0% higher on PassNet. More details on the approach: The agent has a strong backbone and a harness for planning, execution, memory and verification, and it still does not know how to make a given method actually work. That know-how lives in repositories and papers, written for human readers and far too large to load during a task. DisCo distills it. Task-agnostic distillation condenses 1,000 widely used ML repositories into the AREX-Skill Library, over 5,000 verified skills organized into 20 areas and 178 capability families. Task-oriented distillation writes the skills a concrete task calls for. Paper: https://arxiv.org/abs/2609.02749 Chat with Paper: https://academy.dair.ai/papers/repo-to-skill-distilling-github-repositories-into-ai4ai-skills-2609.02749