Project and code: <a href=\"https://github.com/DANG-ai/SKILLER\" rel=\"nofollow\">https://github.com/DANG-ai/SKILLER</a></p>\n","updatedAt":"2026-08-14T06:03:25.312Z","author":{"_id":"66189942f795e6fb97a38f43","avatarUrl":"/avatars/0e44490b15563c3320dcd382ec87b262.svg","fullname":"Chenhao Dang","name":"DDAI-D","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.49218297004699707},"editors":["DDAI-D"],"editorAvatarUrls":["/avatars/0e44490b15563c3320dcd382ec87b262.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.10538","authors":[{"_id":"6a7eaf3e42823931a1f17775","user":{"_id":"66189942f795e6fb97a38f43","avatarUrl":"/avatars/0e44490b15563c3320dcd382ec87b262.svg","isPro":false,"fullname":"Chenhao Dang","user":"DDAI-D","type":"user","name":"DDAI-D"},"name":"Chenhao Dang","status":"claimed_verified","statusLastChangedAt":"2026-08-14T08:45:04.786Z","hidden":false},{"_id":"6a7eaf3e42823931a1f17776","name":"Siyuan Xiong","hidden":false},{"_id":"6a7eaf3e42823931a1f17777","name":"Conghui He","hidden":false},{"_id":"6a7eaf3e42823931a1f17778","name":"Weijia Li","hidden":false}],"publishedAt":"2026-08-11T00:00:00.000Z","submittedOnDailyAt":"2026-08-14T00:00:00.000Z","title":"SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models","submittedOnDailyBy":{"_id":"66189942f795e6fb97a38f43","avatarUrl":"/avatars/0e44490b15563c3320dcd382ec87b262.svg","isPro":false,"fullname":"Chenhao Dang","user":"DDAI-D","type":"user","name":"DDAI-D"},"summary":"Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essential mechanism to continually constrain a language model's behavior space for repeatable, high-quality task execution. However, because strong closed-source models entail high inference costs, current popular agent harnesses, such as Codex and OpenClaw, remain prohibitively expensive when deploying these skills to accomplish real-world tasks. The rapid capability enhancement of open-source models deployable on consumer-grade GPUs presents a compelling opportunity to drastically reduce these costs by leveraging skill-based behavioral constraints. Nevertheless, automatically generating effective skills tailored specifically for such compact models remains a significant practical challenge. To address this, we propose SKILLER, a natural-language-driven reinforcement learning framework designed to automatically generate executor-specific skills for small models, which employs a strong model as the actor and critic, treats the small-model agent system as the environment, and propagates all reinforcement learning signals entirely via natural language. Extensive experimental evaluations across five relevant benchmarks using Qwen3.5-9B and Qwen3.5-4B demonstrate that SKILLER outperforms three open-source and one closed-source skill generation or evolution methods, achieving absolute gains ranging from 4.3 to 20.4 percentage points for the 9B model and 1.8 to 13.3 points for the 4B model, while remarkably matching the performance of strong closed-source models on single-skill tasks in SkillsBench. The project is available at https://github.com/DANG-ai/SKILLER.","upvotes":1,"discussionId":"6a7eaf3e42823931a1f17779","projectPage":"https://github.com/DANG-ai/SKILLER","githubRepo":"https://github.com/DANG-ai/SKILLER","githubRepoAddedBy":"user","ai_summary":"SKILLER is a reinforcement learning framework that automatically generates tailored skills for small open-source models to reduce inference costs while maintaining high task performance.","ai_keywords":["agent skills","reinforcement learning","natural-language-driven RL","actor-critic","small-model agent system","SKILLER","open-source models","skill generation"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":1,"organization":{"_id":"66ce9d1f5e180b9b9c8e6f31","name":"opendatalab","fullname":"OpenDataLab","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/639c3afa7432f2f5d16b7296/yqxxBknyeqkGnYsjoaR4M.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63c1699e40a26dd2db32400d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63c1699e40a26dd2db32400d/3N0-Zp8igv8-52mXAdiiq.jpeg","isPro":false,"fullname":"Chroma","user":"Chroma111","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"66ce9d1f5e180b9b9c8e6f31","name":"opendatalab","fullname":"OpenDataLab","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/639c3afa7432f2f5d16b7296/yqxxBknyeqkGnYsjoaR4M.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.10538.md","query":{}}">
SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models
Abstract
SKILLER is a reinforcement learning framework that automatically generates tailored skills for small open-source models to reduce inference costs while maintaining high task performance.
Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essential mechanism to continually constrain a language model's behavior space for repeatable, high-quality task execution. However, because strong closed-source models entail high inference costs, current popular agent harnesses, such as Codex and OpenClaw, remain prohibitively expensive when deploying these skills to accomplish real-world tasks. The rapid capability enhancement of open-source models deployable on consumer-grade GPUs presents a compelling opportunity to drastically reduce these costs by leveraging skill-based behavioral constraints. Nevertheless, automatically generating effective skills tailored specifically for such compact models remains a significant practical challenge. To address this, we propose SKILLER, a natural-language-driven reinforcement learning framework designed to automatically generate executor-specific skills for small models, which employs a strong model as the actor and critic, treats the small-model agent system as the environment, and propagates all reinforcement learning signals entirely via natural language. Extensive experimental evaluations across five relevant benchmarks using Qwen3.5-9B and Qwen3.5-4B demonstrate that SKILLER outperforms three open-source and one closed-source skill generation or evolution methods, achieving absolute gains ranging from 4.3 to 20.4 percentage points for the 9B model and 1.8 to 13.3 points for the 4B model, while remarkably matching the performance of strong closed-source models on single-skill tasks in SkillsBench. The project is available at https://github.com/DANG-ai/SKILLER.
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2608.10538 in a model README.md to link it from this page.
Cite arxiv.org/abs/2608.10538 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.10538 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.