📄 Daily Papers：<a href=\"https://huggingface.co/papers/2609.02749\">https://huggingface.co/papers/2609.02749</a><br>📄 Paper：<a href=\"https://arxiv.org/abs/2609.02749\" rel=\"nofollow\">https://arxiv.org/abs/2609.02749</a><br>💻 GitHub：<a href=\"https://github.com/VectorSpaceLab/AREX-Skill\" rel=\"nofollow\">https://github.com/VectorSpaceLab/AREX-Skill</a><br>🚀 DisCo CLI：<a href=\"https://www.npmjs.com/package/@arex-skill/disco\" rel=\"nofollow\">https://www.npmjs.com/package/@arex-skill/disco</a></p>\n","updatedAt":"2026-09-03T03:29:25.343Z","author":{"_id":"6544b9b646dbdeca34ee5f52","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6544b9b646dbdeca34ee5f52/nRx6m1C4wfZ_xSWoBUNJf.png","fullname":"Yuyang Hu","name":"namespace-ERI","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":6,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.29929119348526},"editors":["namespace-ERI"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6544b9b646dbdeca34ee5f52/nRx6m1C4wfZ_xSWoBUNJf.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2609.02749","authors":[{"_id":"6a98e2b9fea818274321fec5","user":{"_id":"64e96e74a98b5aa7dbce1196","avatarUrl":"/avatars/574114921e340dcd340f741d7728e4e8.svg","isPro":false,"fullname":"Jianlyu Chen","user":"hanhainebula","type":"user","name":"hanhainebula"},"name":"Jianlyu Chen","status":"claimed_verified","statusLastChangedAt":"2026-09-03T08:15:42.306Z","hidden":false},{"_id":"6a98e2b9fea818274321fec6","user":{"_id":"6544b9b646dbdeca34ee5f52","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6544b9b646dbdeca34ee5f52/nRx6m1C4wfZ_xSWoBUNJf.png","isPro":false,"fullname":"Yuyang Hu","user":"namespace-ERI","type":"user","name":"namespace-ERI"},"name":"Yuyang Hu","status":"claimed_verified","statusLastChangedAt":"2026-09-03T08:15:40.516Z","hidden":false},{"_id":"6a98e2b9fea818274321fec7","name":"Hongjin Qian","hidden":false},{"_id":"6a98e2b9fea818274321fec8","name":"Jiawei Liu","hidden":false},{"_id":"6a98e2b9fea818274321fec9","name":"Wenqing Wei","hidden":false},{"_id":"6a98e2b9fea818274321feca","name":"Xiaolong Chen","hidden":false},{"_id":"6a98e2b9fea818274321fecb","name":"Defu Lian","hidden":false},{"_id":"6a98e2b9fea818274321fecc","name":"Zhicheng Dou","hidden":false},{"_id":"6a98e2b9fea818274321fecd","name":"Chaozhuo Li","hidden":false},{"_id":"6a98e2b9fea818274321fece","name":"Qiwei Ye","hidden":false},{"_id":"6a98e2b9fea818274321fecf","name":"Zheng Liu","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/6544b9b646dbdeca34ee5f52/AOpvNCjMMlANAB5MjAAMG.mp4"],"publishedAt":"2026-09-02T00:00:00.000Z","submittedOnDailyAt":"2026-09-03T00:00:00.000Z","title":"Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills","submittedOnDailyBy":{"_id":"6544b9b646dbdeca34ee5f52","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6544b9b646dbdeca34ee5f52/nRx6m1C4wfZ_xSWoBUNJf.png","isPro":false,"fullname":"Yuyang Hu","user":"namespace-ERI","type":"user","name":"namespace-ERI"},"summary":"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.\n 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.","upvotes":334,"discussionId":"6a98e2b9fea818274321fed0","githubRepo":"https://github.com/VectorSpaceLab/AREX-Skill","githubRepoAddedBy":"user","ai_summary":"DisCo is a research agent that distills operational knowledge into reusable skills, significantly improving autonomous ML research performance across benchmarks.","ai_keywords":["autonomous agents","machine-learning research","operational knowledge","skill distillation","DisCo","AREX-Skill Library","MLE-bench","PaperBench"],"ai_summary_model":"thinkingmachines/Inkling-Small","organization":{"_id":"61be9739d2f9358e24ca0a4f","name":"BAAI","fullname":"Beijing Academy of Artificial Intelligence","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1664511063789-632c234f42c386ebd2710434.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64e96e74a98b5aa7dbce1196","avatarUrl":"/avatars/574114921e340dcd340f741d7728e4e8.svg","isPro":false,"fullname":"Jianlyu Chen","user":"hanhainebula","type":"user"},{"_id":"6544b9b646dbdeca34ee5f52","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6544b9b646dbdeca34ee5f52/nRx6m1C4wfZ_xSWoBUNJf.png","isPro":false,"fullname":"Yuyang Hu","user":"namespace-ERI","type":"user"},{"_id":"64a627232944e255ef574dda","avatarUrl":"/avatars/4c2fd5bf922013fe691c6a3e3fa138a2.svg","isPro":false,"fullname":"Hongjin Qian","user":"TommyChien","type":"user"},{"_id":"653233da501804124f19297f","avatarUrl":"/avatars/f744086d412b3f524f0e6576e763e2c9.svg","isPro":false,"fullname":"Bingyu Yan","user":"Cooki-e","type":"user"},{"_id":"6875b93bd365b5bf3763556e","avatarUrl":"/avatars/7ce96c0e43288ae1e1c5ead903b03127.svg","isPro":false,"fullname":"wangsen","user":"WangSenQWQ","type":"user"},{"_id":"627933c317c069c72a136b35","avatarUrl":"/avatars/f7aef400e47ac84897e6298c7c881c7a.svg","isPro":false,"fullname":"Kun Luo","user":"Lk123","type":"user"},{"_id":"63e11aea14846428ce230f09","avatarUrl":"/avatars/d56be72b18a0e34fd1cce74e70013d4b.svg","isPro":false,"fullname":"sabulin","user":"sabulin","type":"user"},{"_id":"65367cd78ee17cfd44eae3be","avatarUrl":"/avatars/e6f424e7f96e00d13dcab77f93e55c06.svg","isPro":false,"fullname":"Pengfei Zheng","user":"killerface","type":"user"},{"_id":"65ccbcfde75fc480714d1d04","avatarUrl":"/avatars/2def06230512892928537cf2d8499563.svg","isPro":false,"fullname":"Chaofan Li","user":"cfli","type":"user"},{"_id":"661ac5b53d7248a6f20080c1","avatarUrl":"/avatars/26aef5944759c2e4366a71eb8c7fc50a.svg","isPro":false,"fullname":"Ruiran Yan","user":"Ruiran","type":"user"},{"_id":"63f4723e21eb234ab7397bb9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63f4723e21eb234ab7397bb9/YR8unEn1b0bacK6J6gLGf.png","isPro":false,"fullname":"Lei Xiong","user":"Youxll","type":"user"},{"_id":"6564a2ceedae9c33b7654a1f","avatarUrl":"/avatars/42f09356a1282896573ccb44830cd327.svg","isPro":false,"fullname":"JUNJIE ZHOU","user":"JUNJIE99","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":1,"organization":{"_id":"61be9739d2f9358e24ca0a4f","name":"BAAI","fullname":"Beijing Academy of Artificial Intelligence","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1664511063789-632c234f42c386ebd2710434.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2609/2609.02749.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2609.02749 in a model README.md to link it from this page.

Cite arxiv.org/abs/2609.02749 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2609.02749 in a Space README.md to link it from this page.