[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86138-en":3,"doc-seo-86138-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},86138,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",6,"Technology","Know Before Fix QA Driven Repository Knowledge Acquisition for Software Issue Resolution","LLM-based coding agents advance automated software issue resolution but often produce factual errors due to insufficient repository understanding. Existing approaches mitigate this via pre-repair exploration, yet their fix-driven strategies do not identify the agent’s specific knowledge gaps, leading to incomplete or imprecise context. ACQUIRE introduces a QA-driven framework that explicitly acquires structured repository knowledge before patch generation. Two stages separate Question/Answer knowledge acquisition from Resolver repair, improving evidence reliability and accelerating knowledge-intensive fixes. Experiments on SWE-bench Verified show up to 4.4-point Pass@1 gains with modest overhead.","Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue  \nResolution  \nHaotian Lin 1 , Silin Chen 1 , Xiaodong Gu 1* , Yuling Shi 1 , Chengxi Pan2 , Jiaqi Ge3 , Mengfan Li 1 ,  \nJianghong Huang 1 , MENGCHIEH CHUANG 1 , Beijun Shen 1 , and Haibing Guan 1  \n1 Shanghai Jiao Tong University, Shanghai, China  \n2University of Pittsburgh, Pittsburgh, PA, USA  \n3 Guangdong Technion–Israel Institute of Technology, Shantou, China  \n{hyperlynnx, [xiaodong.gu](xiaodong.gu), yuling.shi, lmf2951510526, jh.huang, Zhuangmengjie, bjshen, [hbguan](hbguan}@sjtu.edu.cn)[}](hbguan}@sjtu.edu.cn)[@sjtu.edu.cn](hbguan}@sjtu.edu.cn),  \n[csl2457029646@163.com](csl2457029646@163.com), [chp252@pitt.edu](chp252@pitt.edu), [ge24876@gtiit.edu.cn](ge24876@gtiit.edu.cn)  \narXiv :2607 . 1 1 1 1 1v 1 [ cs . SE] 13 Jul 2026  \nAbstract—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.  \nIndex Terms—software issue resolution, repository knowledge acquisition, coding agents, large language models  \nI. INTRODUCTION  \nCoding agents empowered by large language models (LLMs) have driven significant advances in automated software issue resolution [1]–[3] . Powered by techniques such as chain-of-thought reasoning, multi-step planning, and toolaugmented interaction, these agents can navigate complex codebases, identify relevant code locations, and generate candidate patches with remarkable fluency [4]–[6] .  \nDespite these rapid advancements, a critical class of failures remains largely unresolved, even for frontier-scale models:  \n* Xiaodong Gu is the corresponding author.  \nfactual errors stemming from insufficient repository understanding. These failures are not due to limitations in the model’s reasoning capacity; rather, they arise because the issue description alone does not supply the repository-internal knowledge, such as cross-module dependencies, implicit API contracts, and data-flow details, required to formulate a correct fix. Consequently, agents often fall back on shallow, keyword-based localization, fail to trace fault origins across module boundaries, and inadvertently violate implicit API contracts [6]–[9] . Furthermore, these knowledge-deficient attempts are disproportionately costly, consuming over four times the token cost and nearly twice the execution steps compared to successful resolutions [8], [10] .  \nTo bridge this gap, recent methods have attempted to explore the repository prior to issue resolution [1], [3], [11], [12] . For instance, LingmaAgent links issue keyword","cbCaim7h6yoB7pGS","https://ap.wps.com/l/cbCaim7h6yoB7pGS","pdf",1148831,1,21,"English","en",105,"# Introduction\n## Problem Motivation\n## ACQUIRE Framework Overview\n## Knowledge Acquisition and Repair Stages","[{\"question\":\"Why do LLM-based coding agents often generate factual errors in software issue resolution?\",\"answer\":\"They lack repository-internal knowledge required for a correct fix, such as cross-module dependencies, implicit API contracts, and data-flow details. The issue description alone is insufficient, so agents resort to shallow localization and may violate contracts.\"},{\"question\":\"What is ACQUIRE and how does it differ from fix-driven pre-repair exploration?\",\"answer\":\"ACQUIRE decouples repository knowledge acquisition from patch generation. It explicitly identifies knowledge gaps and acquires structured QA evidence before any editing, rather than exploring repositories in a way driven only by the intended fix.\"},{\"question\":\"How does ACQUIRE work across its two stages?\",\"answer\":\"In Stage I, a Questioner and an Answerer collaborate to acquire structured repository knowledge through targeted questions and evidence-grounded answers. In Stage II, a Resolver uses the resulting QA knowledge to generate informed patches.\"}]",1784208853,53,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"know-before-fix-qa-driven-repository-knowledge-acquisition-for-software-issue-resolution","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/know-before-fix-qa-driven-repository-knowledge-acquisition-for-software-issue-resolution/86138/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do LLM-based coding agents often generate factual errors in software issue resolution?","Question",{"text":75,"@type":76},"They lack repository-internal knowledge required for a correct fix, such as cross-module dependencies, implicit API contracts, and data-flow details. The issue description alone is insufficient, so agents resort to shallow localization and may violate contracts.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is ACQUIRE and how does it differ from fix-driven pre-repair exploration?",{"text":80,"@type":76},"ACQUIRE decouples repository knowledge acquisition from patch generation. It explicitly identifies knowledge gaps and acquires structured QA evidence before any editing, rather than exploring repositories in a way driven only by the intended fix.",{"name":82,"@type":73,"acceptedAnswer":83},"How does ACQUIRE work across its two stages?",{"text":84,"@type":76},"In Stage I, a Questioner and an Answerer collaborate to acquire structured repository knowledge through targeted questions and evidence-grounded answers. In Stage II, a Resolver uses the resulting QA knowledge to generate informed patches.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]