ACQUIRE introduces a QA-driven knowledge acquisition paradigm that explicitly identifies and resolves an agent’s repository understanding gaps before patch generation, replacing unguided pre-repair exploration with structured, evidence-grounded knowledge acquisition for more accurate software issue resolution.</p>\n","updatedAt":"2026-07-15T01:54:32.983Z","author":{"_id":"65684c80a9a1a6a50d779f58","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65684c80a9a1a6a50d779f58/it534ZdH5LxRub1M_o3uM.jpeg","fullname":"Silin Chen","name":"Silin-Chen","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9079490303993225},"editors":["Silin-Chen"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/65684c80a9a1a6a50d779f58/it534ZdH5LxRub1M_o3uM.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.11111","authors":[{"_id":"6a56e80fe548eb96f98cca17","name":"Haotian Lin","hidden":false},{"_id":"6a56e80fe548eb96f98cca18","name":"Silin Chen","hidden":false},{"_id":"6a56e80fe548eb96f98cca19","name":"Xiaodong Gu","hidden":false},{"_id":"6a56e80fe548eb96f98cca1a","name":"Yuling Shi","hidden":false},{"_id":"6a56e80fe548eb96f98cca1b","name":"Chengxi Pan","hidden":false},{"_id":"6a56e80fe548eb96f98cca1c","name":"Jiaqi Ge","hidden":false},{"_id":"6a56e80fe548eb96f98cca1d","name":"Mengfan Li","hidden":false},{"_id":"6a56e80fe548eb96f98cca1e","name":"Jianghong Huang","hidden":false},{"_id":"6a56e80fe548eb96f98cca1f","name":"Mengchieh Chuang","hidden":false},{"_id":"6a56e80fe548eb96f98cca20","name":"Beijun Shen","hidden":false},{"_id":"6a56e80fe548eb96f98cca21","name":"Haibing Guan","hidden":false}],"publishedAt":"2026-07-13T00:00:00.000Z","submittedOnDailyAt":"2026-07-15T00:00:00.000Z","title":"Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution","submittedOnDailyBy":{"_id":"65684c80a9a1a6a50d779f58","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65684c80a9a1a6a50d779f58/it534ZdH5LxRub1M_o3uM.jpeg","isPro":false,"fullname":"Silin Chen","user":"Silin-Chen","type":"user","name":"Silin-Chen"},"summary":"LLM-based coding agents have significantly advanced automated software issue resolution, yet they remain highly prone to factual errors caused by insufficient repository understanding. Recent methods attempt to mitigate this limitation through pre-repair repository exploration; however, their fix-driven strategies explore repositories without identifying the agent's knowledge gaps, often yielding imprecise context that fails to bridge the underlying understanding deficit. In this paper, we propose ACQUIRE, a QA-driven framework for software issue resolution. Mirroring how experienced developers first comprehend unfamiliar code before attempting a fix, ACQUIRE explicitly acquires repository knowledge prior to repair. The framework decouples knowledge acquisition from patch generation through two stages: in the first stage, a Questioner and an Answerer collaborate to acquire structured repository knowledge, where the Questioner poses targeted questions and the Answerer produces evidence-grounded answers through autonomous exploration; in the second stage, the Resolver leverages the resulting QA knowledge to generate informed patches. By transforming implicit knowledge gaps into explicit, factually reliable understanding, ACQUIRE accelerates knowledge-intensive repair stages and enables more accurate resolution. Experiments on SWE-bench Verified demonstrate that ACQUIRE consistently outperforms representative pre-repair methods, raising Pass@1 by up to 4.4 percentage points with modest additional cost and time.","upvotes":4,"discussionId":"6a56e80fe548eb96f98cca22","organization":{"_id":"63e5ef7bf2e9a8f22c515654","name":"SJTU","fullname":"Shanghai Jiao Tong University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1676013394657-63e5ee22b6a40bf941da0928.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6a2da6c8ca070ee12c6e396c","avatarUrl":"/avatars/0355287dcabaa67dbc7f0b10b87451f9.svg","isPro":false,"fullname":"Joe Mama","user":"JoeMama123123123","type":"user"},{"_id":"65684c80a9a1a6a50d779f58","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65684c80a9a1a6a50d779f58/it534ZdH5LxRub1M_o3uM.jpeg","isPro":false,"fullname":"Silin Chen","user":"Silin-Chen","type":"user"},{"_id":"68e3580e71512dfe661ff949","avatarUrl":"/avatars/5355152675c51dca4988ac0c878d47d9.svg","isPro":false,"fullname":"schwa","user":"schwa2003","type":"user"},{"_id":"6368f15350a665fa20d34f6f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/-kyLDb4mYhBwEQrYLIOQZ.png","isPro":false,"fullname":"Kurt H.W. Stolle","user":"khwstolle","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"63e5ef7bf2e9a8f22c515654","name":"SJTU","fullname":"Shanghai Jiao Tong University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1676013394657-63e5ee22b6a40bf941da0928.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.11111.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2607.11111 in a model README.md to link it from this page.

Cite arxiv.org/abs/2607.11111 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2607.11111 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.