[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82206-en":3,"doc-seo-82206-105":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},82206,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","ReProAgent Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports","ReProAgent is a tool-augmented, multi-stage agent framework for generating executable bug reproduction tests directly from open-source issue reports. It addresses limitations of prompt-based pipelines by decomposing the workflow into four stages: bug localization, root cause analysis, test planning, and test generation. ReProAgent combines task-specific decomposition and reflection tools, retrieval from both textual sources and repository graphs, and runtime interaction with the execution environment. Experiments on SWT-bench-lite and SWT-bench-verified reach 58.43% and 70.30% reproduction success rates, outperforming baselines.","arXiv :2607 .09 123v 1 [ cs . SE] 10 Jul 2026  \nReProAgent: Tool-Augmented Multi-Stage Agentic  \nGeneration of Bug Reproduction Tests from Issue Reports  \nQUANJUN ZHANG, School of Computer Science and Engineering, Nanjing University of Science and Technology, China  \nYI ZHENG and YE SHANG, State Key Laboratory for Novel Software Technology, Nanjing University Nanjing University, China  \nWEIFENG SUN, Singapore Management University, Singapore  \nHAICHUAN HU, School of Computer Science and Engineering, Nanjing University of Science and Technology, China  \nCHUNRONG FANG and ZHENYU CHEN, State Key Laboratory for Novel Software Technology, Nanjing University, China  \nLIANG XIAO, School of Computer Science and Engineering, Nanjing University of Science and Technology, China  \nReproduction tests help developers confirm reported issues and provide executable feedback for issue resolution, yet issue reports in open-source projects rarely include such tests. Recent studies have explored generating issue reproduction tests from issue reports with large language models, but existing approaches largely rely on prompt-based pipelines that retrieve textual context and generate tests. This limits their ability to understand how reported issues behave in repository-scale codebases and to flexibly organize the construction of reproduction tests. In this paper, we propose ReProAgent, a multi-stage agent framework for reproduction test generation from issue reports. Inspired by how developers manually reproduce reported issues, ReProAgent decomposes the task into four agen stages: bug localization, root cause analysis, test planning, and test generation. To support these stages, ReProAgent integrates task-specific tools for task decomposition and reflection, context retrieval from both textual sources and repository graphs, and runtime interaction with the execution environment. Experiments on SWT-bench-lite and SWT-bench-verified show that ReProAgent successfully reproduces 58.43% and 70.30% of issues, outperforming all baselines, with an average cost of $0.14 per instance. For example, when equipped with GPT-5-mini, ReProAgent exceeds OpenHands with the same backbone by 20.43 and 7.90 percentage points, respectively. ReProAgent also generalizes across multiple backbone LLMs and improves downstream issue resolution performance when integrated with existing repair approaches.  \nCCS Concepts: • Software and its engineering → Software testing and debugging.  \nAdditional Key Words and Phrases: LLMs, Reproduction Test Generation, Agents, Knowledge Graph  \nAuthors’ Contact Information: Quanjun Zhang, [quanjunzhang@njust.edu.cn](quanjunzhang@njust.edu.cn), School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China; Yi Zheng, [201250182@smail.nju.edu.cn](201250182@smail.nju.edu.cn); Ye Shang, yeshang@ [smail.nju.edu.cn](smail.nju.edu.cn), State Key Laboratory for Novel Software Technology, Nanjing University and Nanjing University, Nanjing, China; Weifeng Sun, [wfsun@smu.edu.sg](wfsun@smu.edu.sg), Singapore Management University, Singapore; Haichuan Hu, huhaichuan2024@ [gmail.com](gmail.com), School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China; Chunrong Fang, [fangchunrong@nju.edu.cn](fangchunrong@nju.edu.cn); Zhenyu Chen, [zychen@nju.edu.cn](zychen@nju.edu.cn), State Key Laboratory for Novel Software  \nTechnology, Nanjing University, Nanjing, China; Liang Xiao, [xiaoliang@mail.njust.edu.cn](xiaoliang@mail.njust.edu.cn), School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others ","cbCaicnsgGnsTJHf","https://ap.wps.com/l/cbCaicnsgGnsTJHf","pdf",1390566,1,23,"English","en",105,"# Introduction\n## Problem and Motivation\n## Proposed Approach\n## Experimental Evaluation","[{\"question\":\"What problem does ReProAgent address in open-source issue fixing?\",\"answer\":\"Issue reports commonly lack executable reproduction tests, making it harder for developers to confirm bugs before fixing and validate patches afterward. ReProAgent generates faithful reproduction tests from the issue text to reduce debugging and maintenance cost.\"},{\"question\":\"How does ReProAgent structure its test generation workflow?\",\"answer\":\"ReProAgent decomposes the task into four agent stages: bug localization, root cause analysis, test planning, and test generation, mirroring how developers manually reproduce reported issues.\"},{\"question\":\"Which capabilities help ReProAgent generate better reproduction tests?\",\"answer\":\"It integrates task-specific tools for decomposition and reflection, retrieves context from both textual sources and repository graphs, and interacts with the execution environment at runtime.\"}]",1784178804,58,{"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},"reproagent-tool-augmented-multi-stage-agentic-generation-of-bug-reproduction-tests-from-issue-reports","",{"@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/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/reproagent-tool-augmented-multi-stage-agentic-generation-of-bug-reproduction-tests-from-issue-reports/82206/",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},"What problem does ReProAgent address in open-source issue fixing?","Question",{"text":75,"@type":76},"Issue reports commonly lack executable reproduction tests, making it harder for developers to confirm bugs before fixing and validate patches afterward. ReProAgent generates faithful reproduction tests from the issue text to reduce debugging and maintenance cost.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does ReProAgent structure its test generation workflow?",{"text":80,"@type":76},"ReProAgent decomposes the task into four agent stages: bug localization, root cause analysis, test planning, and test generation, mirroring how developers manually reproduce reported issues.",{"name":82,"@type":73,"acceptedAnswer":83},"Which capabilities help ReProAgent generate better reproduction tests?",{"text":84,"@type":76},"It integrates task-specific tools for decomposition and reflection, retrieves context from both textual sources and repository graphs, and interacts with the execution environment at runtime.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},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"]