Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updating model parameters. However, discovering effective skills for data analysis remains challenging, as reliable supervision is expensive and success criteria vary across analytical formats. This raises the key question of how to discover reusable data-analysis skills from unlabeled exploration alone. We propose DataCOPE, an unsupervised verifier-guided skill discovery framework for data-analytic agents. DataCOPE derives verifier signals from the exploration trajectories and uses them to characterize relative quality or aggreement among trajectories. It iteratively coordinates a Data-Analytic Agent for trajectory generation, an Unsupervised Verifier for signal extraction, and a Skill Manager for contrastive skill distillation. For report-style analysis, we instantiate the verifier as an Adaptive Checklist Verifier that derives task-specific criteria, scores reports by verifiable coverage, and iteratively refines the checklist. For reasoning-style analysis, we instantiate it as an Answer Agreement Verifier that groups trajectories by answer agreement and uses self-consistency as an auxiliary signal. We evaluate DataCOPE on report-style analysis from Deep Data Research and reasoning-style analysis from DABStep. Across both settings, DataCOPE consistently improves held-out performance over baselines. Averaged across four model settings, DataCOPE improves the mean score by 9.71% and 32.30% on report-style and reasoning-style tasks respectively.</p>\n","updatedAt":"2026-06-05T01:57:09.268Z","author":{"_id":"6441f1d2603214724ec0c1c2","avatarUrl":"/avatars/d3c4b759e6a5635e37ff715fae52e5ba.svg","fullname":"Shumin Deng","name":"231sm","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8786914944648743},"editors":["231sm"],"editorAvatarUrls":["/avatars/d3c4b759e6a5635e37ff715fae52e5ba.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.06416","authors":[{"_id":"6a222cc53490a593e87b13d6","name":"Zhisong Qiu","hidden":false},{"_id":"6a222cc53490a593e87b13d7","name":"Kangqi Song","hidden":false},{"_id":"6a222cc53490a593e87b13d8","name":"Shengwei Tang","hidden":false},{"_id":"6a222cc53490a593e87b13d9","name":"Shuofei Qiao","hidden":false},{"_id":"6a222cc53490a593e87b13da","name":"Lei Liang","hidden":false},{"_id":"6a222cc53490a593e87b13db","name":"Huajun Chen","hidden":false},{"_id":"6a222cc53490a593e87b13dc","name":"Shumin Deng","hidden":false}],"publishedAt":"2026-06-04T00:00:00.000Z","submittedOnDailyAt":"2026-06-05T00:00:00.000Z","title":"Unsupervised Skill Discovery for Agentic Data Analysis","submittedOnDailyBy":{"_id":"6441f1d2603214724ec0c1c2","avatarUrl":"/avatars/d3c4b759e6a5635e37ff715fae52e5ba.svg","isPro":false,"fullname":"Shumin Deng","user":"231sm","type":"user","name":"231sm"},"summary":"Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updating model parameters. However, discovering effective skills for data analysis remains challenging, as reliable supervision is expensive and success criteria vary across analytical formats. This raises the key question of how to discover reusable data-analysis skills from unlabeled exploration alone. We propose DataCOPE, an unsupervised verifier-guided skill discovery framework for data-analytic agents. DataCOPE derives verifier signals from the exploration trajectories and uses them to characterize relative quality or aggreement among trajectories. It iteratively coordinates a Data-Analytic Agent for trajectory generation, an Unsupervised Verifier for signal extraction, and a Skill Manager for contrastive skill distillation. For report-style analysis, we instantiate the verifier as an Adaptive Checklist Verifier that derives task-specific criteria, scores reports by verifiable coverage, and iteratively refines the checklist. For reasoning-style analysis, we instantiate it as an Answer Agreement Verifier that groups trajectories by answer agreement and uses self-consistency as an auxiliary signal. We evaluate DataCOPE on report-style analysis from Deep Data Research and reasoning-style analysis from DABStep. Across both settings, DataCOPE consistently improves held-out performance over baselines. Averaged across four model settings, DataCOPE improves the mean score by 9.71% and 32.30% on report-style and reasoning-style tasks respectively.","upvotes":9,"discussionId":"6a222cc53490a593e87b13dd","ai_summary":"DataCOPE is an unsupervised framework that discovers reusable data-analysis skills through verifier-guided exploration, improving analytical performance in both report-style and reasoning-style tasks.","ai_keywords":["skill discovery","verifier-guided learning","unsupervised learning","contrastive skill distillation","adaptive checklist verifier","answer agreement verifier","self-consistency","data-analytic agent","exploration trajectories"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"620a6fcd8d5e5dfed284bc91","name":"zjunlp","fullname":"ZJUNLP","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1644851027419-620a61cba53066560e226d30.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6441f1d2603214724ec0c1c2","avatarUrl":"/avatars/d3c4b759e6a5635e37ff715fae52e5ba.svg","isPro":false,"fullname":"Shumin Deng","user":"231sm","type":"user"},{"_id":"679e1f7c31bab0a2a309d61f","avatarUrl":"/avatars/116912ef6a154edec9d589e0e0597fc9.svg","isPro":false,"fullname":"Zhenqian","user":"ZhenqianXu","type":"user"},{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","isPro":false,"fullname":"Ningyu Zhang","user":"Ningyu","type":"user"},{"_id":"684bc1be17ae31ba66171292","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/684bc1be17ae31ba66171292/LFlkU4kArMjSzIbwjXd44.jpeg","isPro":false,"fullname":"Jingsheng Zheng","user":"JohnsonZheng03","type":"user"},{"_id":"6a1443f02a9759cfbdf80a48","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6a1443f02a9759cfbdf80a48/dIoHGMzJ3U6k7VTOaBd4Y.jpeg","isPro":false,"fullname":"Haoxiong Wang","user":"WangHX2026","type":"user"},{"_id":"65535b54140fc44a74d43635","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/MIrD8OzDKF2aI38i7ZPjR.jpeg","isPro":false,"fullname":"Zhisong Qiu","user":"consultantQ","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"66abc6da92b9eb71fe476118","avatarUrl":"/avatars/6d1618f45cc76da80335ad926ad24552.svg","isPro":false,"fullname":"xy.r","user":"ShawnRu","type":"user"},{"_id":"6447800f30fa4ecb85ddad80","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6447800f30fa4ecb85ddad80/NsmXIaMsWctmTNA7tFVkX.jpeg","isPro":false,"fullname":"Shuofei Qiao","user":"GoooDte","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"620a6fcd8d5e5dfed284bc91","name":"zjunlp","fullname":"ZJUNLP","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1644851027419-620a61cba53066560e226d30.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.06416.md"}">
Unsupervised Skill Discovery for Agentic Data Analysis
Abstract
DataCOPE is an unsupervised framework that discovers reusable data-analysis skills through verifier-guided exploration, improving analytical performance in both report-style and reasoning-style tasks.
Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updating model parameters. However, discovering effective skills for data analysis remains challenging, as reliable supervision is expensive and success criteria vary across analytical formats. This raises the key question of how to discover reusable data-analysis skills from unlabeled exploration alone. We propose DataCOPE, an unsupervised verifier-guided skill discovery framework for data-analytic agents. DataCOPE derives verifier signals from the exploration trajectories and uses them to characterize relative quality or aggreement among trajectories. It iteratively coordinates a Data-Analytic Agent for trajectory generation, an Unsupervised Verifier for signal extraction, and a Skill Manager for contrastive skill distillation. For report-style analysis, we instantiate the verifier as an Adaptive Checklist Verifier that derives task-specific criteria, scores reports by verifiable coverage, and iteratively refines the checklist. For reasoning-style analysis, we instantiate it as an Answer Agreement Verifier that groups trajectories by answer agreement and uses self-consistency as an auxiliary signal. We evaluate DataCOPE on report-style analysis from Deep Data Research and reasoning-style analysis from DABStep. Across both settings, DataCOPE consistently improves held-out performance over baselines. Averaged across four model settings, DataCOPE improves the mean score by 9.71% and 32.30% on report-style and reasoning-style tasks respectively.
Community
Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updating model parameters. However, discovering effective skills for data analysis remains challenging, as reliable supervision is expensive and success criteria vary across analytical formats. This raises the key question of how to discover reusable data-analysis skills from unlabeled exploration alone. We propose DataCOPE, an unsupervised verifier-guided skill discovery framework for data-analytic agents. DataCOPE derives verifier signals from the exploration trajectories and uses them to characterize relative quality or aggreement among trajectories. It iteratively coordinates a Data-Analytic Agent for trajectory generation, an Unsupervised Verifier for signal extraction, and a Skill Manager for contrastive skill distillation. For report-style analysis, we instantiate the verifier as an Adaptive Checklist Verifier that derives task-specific criteria, scores reports by verifiable coverage, and iteratively refines the checklist. For reasoning-style analysis, we instantiate it as an Answer Agreement Verifier that groups trajectories by answer agreement and uses self-consistency as an auxiliary signal. We evaluate DataCOPE on report-style analysis from Deep Data Research and reasoning-style analysis from DABStep. Across both settings, DataCOPE consistently improves held-out performance over baselines. Averaged across four model settings, DataCOPE improves the mean score by 9.71% and 32.30% on report-style and reasoning-style tasks respectively.
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/2606.06416 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.06416 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.06416 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.