Hugging Face Daily Papers · June 5, 2026 · 4 min read

TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Like Read original ↗

Most AI assistants only solve the problems users explicitly ask about, leaving many important issues hidden in the surrounding context. TIDE introduces a template-guided iterative discovery framework that proactively uncovers multiple latent problems, grounds them in evidence, and recommends concrete actions, achieving substantial gains across personal workspace and software repository settings.</p>\n","updatedAt":"2026-06-05T05:42:49.926Z","author":{"_id":"64e5a1cd4c20016ec9020ec8","avatarUrl":"/avatars/d7ffe7fbbe39c0a013375357457c57b3.svg","fullname":"Soyeong","name":"starsuzi","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":19,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8468928933143616},"editors":["starsuzi"],"editorAvatarUrls":["/avatars/d7ffe7fbbe39c0a013375357457c57b3.svg"],"reactions":[{"reaction":"👍","users":["HwanChang0106"],"count":1},{"reaction":"🔥","users":["lordmo2"],"count":1}],"isReport":false}},{"id":"6a228054e2396e33fa2e3906","author":{"_id":"69b944bdea28cd6943b29d84","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/69b944bdea28cd6943b29d84/ykneGmnpdZzdSLAxVNeHP.jpeg","fullname":"DarthVPirateKing-afk","name":"lordmo2","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2026-06-05T07:52:52.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"🤫","html":"<p>🤫</p>\n","updatedAt":"2026-06-05T07:52:52.184Z","author":{"_id":"69b944bdea28cd6943b29d84","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/69b944bdea28cd6943b29d84/ykneGmnpdZzdSLAxVNeHP.jpeg","fullname":"DarthVPirateKing-afk","name":"lordmo2","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.376694917678833},"editors":["lordmo2"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/69b944bdea28cd6943b29d84/ykneGmnpdZzdSLAxVNeHP.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.04743","authors":[{"_id":"6a2260cd3490a593e87b15da","name":"Soyeong Jeong","hidden":false},{"_id":"6a2260cd3490a593e87b15db","name":"Jinheon Baek","hidden":false},{"_id":"6a2260cd3490a593e87b15dc","name":"Minki Kang","hidden":false},{"_id":"6a2260cd3490a593e87b15dd","name":"Sung Ju Hwang","hidden":false}],"publishedAt":"2026-06-03T00:00:00.000Z","submittedOnDailyAt":"2026-06-05T00:00:00.000Z","title":"TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration","submittedOnDailyBy":{"_id":"64e5a1cd4c20016ec9020ec8","avatarUrl":"/avatars/d7ffe7fbbe39c0a013375357457c57b3.svg","isPro":false,"fullname":"Soyeong","user":"starsuzi","type":"user","name":"starsuzi"},"summary":"Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution.","upvotes":30,"discussionId":"6a2260cd3490a593e87b15de","ai_summary":"TIDE is a template-guided iterative framework for discovering hidden problems from context, using iterative discovery and thought templates to improve problem identification and resolution across document and code environments.","ai_keywords":["iterative discovery","thought templates","problem discovery","context-aware agents","template-guided framework","multi-agent systems","task coverage","identification","resolution"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"6475760c33192631bad2bb38","name":"kaist-ai","fullname":"KAIST AI","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6469949654873f0043b09c22/aaZFiyXe1qR-Dmy_xq67m.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64e5a1cd4c20016ec9020ec8","avatarUrl":"/avatars/d7ffe7fbbe39c0a013375357457c57b3.svg","isPro":false,"fullname":"Soyeong","user":"starsuzi","type":"user"},{"_id":"63036b6c5c70c21d0ea79d48","avatarUrl":"/avatars/a7eb03f5cbd4eaa09fe807bbed8bc0f7.svg","isPro":false,"fullname":"Jinheon Baek","user":"jinheon","type":"user"},{"_id":"638716c14e00d7fc0902fef4","avatarUrl":"/avatars/5fa8152f8c0e4e600d1a64802c3e0103.svg","isPro":false,"fullname":"Sangwoo Park","user":"Sangsang","type":"user"},{"_id":"636356b14c9f829ef7014ccd","avatarUrl":"/avatars/6a634fd6431d1e2d8fa000f6afec7f8c.svg","isPro":false,"fullname":"Jae Hyuk Sung","user":"okaybody10","type":"user"},{"_id":"64b5457af249713053c736c5","avatarUrl":"/avatars/84cd17e11f20aee404f7ffadf659cd6f.svg","isPro":false,"fullname":"Yukyeong Lee","user":"leee99","type":"user"},{"_id":"6811d91633558457e1c2c7e0","avatarUrl":"/avatars/9e28daed4fd12bce6ced81d3e1d295f3.svg","isPro":false,"fullname":"Yeonjun Hwang","user":"hbhhyj","type":"user"},{"_id":"676829dd26eb881162d081ea","avatarUrl":"/avatars/b4a402653bf40defc97b35a8d07fb1ea.svg","isPro":true,"fullname":"Junmo Cho","user":"junmokane","type":"user"},{"_id":"66339dbf143f209fe1de6fe7","avatarUrl":"/avatars/25db7821f92fc149e7ac90017acb231b.svg","isPro":false,"fullname":"Silvia Zhang","user":"RealSilvia","type":"user"},{"_id":"666086f24a197fe2f97539be","avatarUrl":"/avatars/f57b9bf277e029bb479d651b9347a8bd.svg","isPro":false,"fullname":"Dohyeon Kim","user":"Dohyeon1","type":"user"},{"_id":"66375f36c3296c5d26e1ccf3","avatarUrl":"/avatars/197d589d508f647e339ba0d9ffe3fe79.svg","isPro":false,"fullname":"Hyomin Lee","user":"pwnhyo","type":"user"},{"_id":"66ed7737f2f27a5dfd81ef09","avatarUrl":"/avatars/f45eea356e92ac7b3db23c2c92dec9fa.svg","isPro":false,"fullname":"Kangsan Kim","user":"KangsanKim71","type":"user"},{"_id":"654738a75cd5692b3ac5d5f0","avatarUrl":"/avatars/77262c6c89193962ae5b21136dad2370.svg","isPro":false,"fullname":"Byeong Hun Bang","user":"bangpro","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":2,"organization":{"_id":"6475760c33192631bad2bb38","name":"kaist-ai","fullname":"KAIST AI","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6469949654873f0043b09c22/aaZFiyXe1qR-Dmy_xq67m.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.04743.md"}">

Papers

arxiv:2606.04743

TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Published on Jun 3

· Submitted by

Soyeong on Jun 5

#2 Paper of the day

KAIST AI

Upvote

Authors:

Abstract

TIDE is a template-guided iterative framework for discovering hidden problems from context, using iterative discovery and thought templates to improve problem identification and resolution across document and code environments.

Generated by Qwen/Qwen2.5-Coder-32B-Instruct

Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution.

View arXiv page View PDF Add to collection