[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-327714-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-327714-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","is-agentic-code-review-helpful-paper-study-of-coderabbit-reviews","Is Agentic Code Review Helpful? - Paper Study of CodeRabbit Reviews","","Agentic code review introduces autonomous agents that provide inline comments on pull requests, but empirical evidence on developers’ real responses remains limited. This paper presents an empirical study of 31,073 pairs of agentic code review comments and developer feedback from 10,191 pull requests across 239 GitHub repositories using CodeRabbit. Results show mixed reception: 36.4% accepted, 7.3% triggered discussion, and 56.3% rejected. Rejections are mainly linked to invalid suggestions, redundancy, out-of-scope issues, and mismatches with developer intent and coding practices.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/is-agentic-code-review-helpful-paper-study-of-coderabbit-reviews/327714/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/is-agentic-code-review-helpful-paper-study-of-coderabbit-reviews/327714.png","ImageObject",300,407,{"name":42,"@type":43},"Liam","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",14,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What does the study investigate about agentic code review?","Question",{"text":63,"@type":64},"It examines how developers respond in practice to autonomous agent review comments on pull requests, using CodeRabbit as a case study.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What are the main outcomes of the empirical evaluation?",{"text":68,"@type":64},"Across 239 repositories, only 36.4% of agentic review items were accepted, 7.3% triggered discussion, and 56.3% were rejected.",{"name":70,"@type":61,"acceptedAnswer":71},"Why are agentic code review suggestions often rejected?",{"text":72,"@type":64},"Rejections mainly come from invalid suggestions (false positives, redundancy, or out of scope) and misalignment with developer intent and coding practices.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},327714,1791128492,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146,"preview_page_count":4},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","arXiv :2607 .033 16v 1 [ cs . SE] 3 Jul 2026  \nIs Agentic Code Review Helpful? Mining Developers’ Feedback to CodeRabbit Reviews in the Wild  \nHONG YI LIN, The University of Melbourne, Australia MINGZHAO LIANG, The University of Melbourne, Australia KLA TANTITHAMTHAVORN, Monash University, Australia  \nPATANAMON THONGTANUNAM, The University of Melbourne, Australia  \nAgentic code review, where autonomous agents provide code review comments on pull requests, is increasingly integrated into development workflows, yet there is limited empirical evidence on how developers respond to such comments in practice. In this paper, we present an empirical study of agentic code reviews using CodeRabbit as a case study. Through an empirical study of 31,073 pairs of code reviews and developer feedback from 10,191 pull requests across 239 GitHub repositories, our results show that agentic reviews receive mixed reception: 36.4% were accepted and 7.3% triggered discussion, while 56.3% were rejected. Rejections were primarily associated with invalid suggestions that were false positives, redundant, or out of scope, as well as misalignment with developer intent and coding practices. We further found that agentic reviews tend to focus more on functional concerns than evolvability-related comments, yet they were more likely to be invalid. To improve effectiveness in review practices, we explored various LLM-based approaches for predicting review rejection. We found that lightweight learning-based methods achieve up to 76% F1 score, suggesting learnable patterns exist between code reviews and their corresponding feedback. Our results highlight the current state of CodeRabbit’s agentic code reviews, showing opportunity gaps for improvement, as well as shortcomings hindering its effectiveness.  \nCCS Concepts: • Software and its engineering → Software creation and management; Software maintenance tools; • Computing methodologies → Natural language generation.  \nAdditional Key Words and Phrases: Agentic Code Review, CodeRabbit, Developers’ Feedback.  \nACM Reference Format:  \nHong Yi Lin, Mingzhao Liang, Kla Tantithamthavorn, and Patanamon Thongtanunam. 2026. Is Agentic Code Review Helpful? Mining Developers’ Feedback to CodeRabbit Reviews in the Wild. 1, 1 (July 2026), 23 pages. [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \n1 Introduction  \nThe modern code review is an essential software quality assurance practice that helps ensure the maintainability and overall quality of a software system. Recently, the field has witnessed a transformative shift from human review workflows to hybrid human–AI collaborations in the code review practices [9, 41] . In this new paradigm, Large Language Models (LLMs) are no longer just passive completion engines, they function as autonomous reviewer agents capable of providing real-time, inline feedback on pull requests (PRs) . CodeRabbit [9, 10] is one of the most popular agentic code  \nAuthors’ Contact Information: Hong Yi Lin, [holin2@unimelb.edu.au](holin2@unimelb.edu.au), The University of Melbourne, Melbourne, Victoria, Australia; Mingzhao Liang, [mingchiu.leung@gmail.com](mingchiu.leung@gmail.com), The University of Melbourne, Melbourne, Victoria, Australia; Kla Tantithamthavorn, [chakkrit@monash.edu](chakkrit@monash.edu), Monash University, Melbourne, Victoria, Australia; Patanamon Thongtanunam, [patanamon.t@unimelb.edu.au](patanamon.t@unimelb.edu.au), The University of Melbourne, Melbourne, Victoria, Australia.  \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 than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redis","cbCaivyKOhPASgO0","https://ap.wps.com/l/cbCaivyKOhPASgO0","pdf",6531706,23,"English","# Introduction\n## Agentic code review and developer feedback gap\n## Study design and evaluation results\n## Improving effectiveness via rejection prediction","[{\"question\":\"What does the study investigate about agentic code review?\",\"answer\":\"It examines how developers respond in practice to autonomous agent review comments on pull requests, using CodeRabbit as a case study.\"},{\"question\":\"What are the main outcomes of the empirical evaluation?\",\"answer\":\"Across 239 repositories, only 36.4% of agentic review items were accepted, 7.3% triggered discussion, and 56.3% were rejected.\"},{\"question\":\"Why are agentic code review suggestions often rejected?\",\"answer\":\"Rejections mainly come from invalid suggestions (false positives, redundancy, or out of scope) and misalignment with developer intent and coding practices.\"}]","Is Agentic Code Review Helpful? - Paper Study of CodeRabbit Reviews | PDF",1789977894,58]