[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83039-en":3,"doc-seo-83039-105":30,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83039,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","SWE-Review Closing the Loop on Issue Resolution with Agentic Code Review","Coding agents increasingly produce pull requests (PRs) for real-world software issues, yet PR generation often stays open-loop: the agent proposes changes without systematic review, diagnosis, or revision. SWE-Review introduces an agentic code review framework where a reviewer agent explores the repository and outputs an accept/request-changes decision plus structured diagnosis. SWE-Review-Bench and SWE-Review-Traj evaluate review correctness and revision usefulness. Results show continuous generate–review–revise improvements, stronger decision quality than fixed-context review, broader transfer to issue-resolution models, and efficient test-time scaling.","arXiv :2607 .06065v 1 [ cs . SE] 7 Jul 2026  \nSWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review  \nRuoyu Wang 1 ∗ Jierun Chen2 ∗ Shaowei Wang2 Chaofan Tao2 Sidi Yang3 Yuxin Jiang2 Kim-Hui Yap 1 Lifeng Shang2 Xiaohui Li2 Haoli Bai2†  \n1NTU 2Huawei Technologies 3HKU  \n Webpage  Code  Data  Plugin  \nAbstract  \nCoding agents increasingly generate pull requests (PRs) for real-world software issues, yet one-shot PR generation remains open-loop: the PR is proposed without systematic review, diagnosis, or revision. We introduce SWE-Review, a framework for closing this loop with agentic code review. Given an issue and an AIgenerated PR, a reviewer agent explores the repository, decides whether the PR should be accepted, and provides structured feedback for revision. We evaluate this setting with our proposed SWE-Review-Bench to measure both review correctness and downstream revision usefulness. We further curate SWE-ReviewTraj dataset to study broader applications of agentic review and fill the datascarcity gap for open reviewer training. Experiments show that agentic review continuously improves PRs through a generate-review-revise loop, outperforms single-turn fixed-context review in both decision accuracy and resolve rate after revision, transfers beyond review to improve issue-resolution models, and enables effective and efficient test-time scaling. These results position agentic code review as a practical mechanism for moving AI coding agents from one-shot PR generation toward closed-loop issue resolution.  \n1 Introduction  \nAI coding tools have advanced from autocomplete assistants to autonomous agents that can propose pull requests (PRs) for real-world software engineering (SWE) issues. Yet one-shot PR generation remains open-loop: after an agent produces a candidate PR, there is often no reliable mechanism for determining whether the issue has been resolved or for diagnosing how the PR should be revised when it has not.  \nCode review, the practice of inspecting changes before they are merged, is the natural mechanism for closing this loop. A reviewer provides both a binary decision, accept or request changes, anda diagnosis of what is wrong and how to fix it. As AI-assisted PR submissions continue to grow, automated review is becoming increasingly important. However, code review capabilities remain less developed than those of other software engineering tasks such as issue resolution, and we still lack systematic benchmarks, reliable metrics, public training data, and end-to-end evaluations for understanding review’s role in a closed-loop issue-resolution pipeline.  \nTo fill this gap, we present SWE-Review, a framework for closing the issue-resolution loop with agentic code review. Given a repository, an issue, and an AI-generated pull request, the reviewer explores the environment and produces two outputs: a binary accept/request-changes decision anda structured diagnosis that guides revision when the PR should not be merged. To study this setting  \n∗ Equal contribution  \n†Corresponding author: [baihaoli@huawei.com](baihaoli@huawei.com)  \nPreprint.  \nsystematically, we construct SWE-Review-Bench, a benchmark of 1,384 candidate pull requests derived from 500 SWE-bench Verified issues and three PR generators spanning high-, medium- , and low-quality candidate distributions. We also construct SWE-Review-Traj, a dataset consisting of 8,914 agentic review trajectories to support training and evaluation of open reviewers. We evaluate review capacities with three complementary metrics: Completion Rate (CR), which measures whether the reviewer produces a parseable final review; Decision Accuracy (DA), which measures whether the reviewer makes the correct merge decision; and Resolve Rate after Revision (RRR), which measures whether the review improves the final patch outcome after revision. We will release the benchmark, review trajectories, and reviewer models to support reproducible research on open agentic cod","cbCailzOIVbDiyBE","https://ap.wps.com/l/cbCailzOIVbDiyBE","pdf",916651,4,1,34,"English","en",105,"# Abstract\n# Introduction\n# Related Work","[{\"question\":\"What problem does SWE-Review target in AI-generated pull requests?\",\"answer\":\"SWE-Review targets the open-loop nature of one-shot PR generation, where candidate PRs lack reliable systematic review, diagnosis, and revision to confirm whether the issue is resolved.\"},{\"question\":\"How does the SWE-Review reviewer agent respond to an issue and an AI-generated PR?\",\"answer\":\"Given an issue and repository plus an AI-generated PR, the reviewer agent explores the repository and produces a binary accept or request-changes decision along with structured diagnosis that guides revision.\"},{\"question\":\"How do the experiments evaluate whether agentic code review improves outcomes?\",\"answer\":\"The work evaluates review capacities with Completion Rate (CR), Decision Accuracy (DA), and Resolve Rate after Revision (RRR), and demonstrates higher resolve rates through iterative generate–review–revise versus single-turn fixed-context review.\"}]",1784184810,86,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"swe-review-closing-the-loop-on-issue-resolution-with-agentic-code-review","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/swe-review-closing-the-loop-on-issue-resolution-with-agentic-code-review/83039/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","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 SWE-Review target in AI-generated pull requests?","Question",{"text":75,"@type":76},"SWE-Review targets the open-loop nature of one-shot PR generation, where candidate PRs lack reliable systematic review, diagnosis, and revision to confirm whether the issue is resolved.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the SWE-Review reviewer agent respond to an issue and an AI-generated PR?",{"text":80,"@type":76},"Given an issue and repository plus an AI-generated PR, the reviewer agent explores the repository and produces a binary accept or request-changes decision along with structured diagnosis that guides revision.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the experiments evaluate whether agentic code review improves outcomes?",{"text":84,"@type":76},"The work evaluates review capacities with Completion Rate (CR), Decision Accuracy (DA), and Resolve Rate after Revision (RRR), and demonstrates higher resolve rates through iterative generate–review–revise versus single-turn fixed-context review.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]