无需微调的LLM代码审查工具，显著提升开发效率与质量。
RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassian
- 基于上下文感知的无微调代码评论生成
- 38.7%评论触发后续代码修改，缩短30.8%提交周期
- 适合希望降本增效的大型研发团队
基于大语言模型（LLMs）的代码审查自动化有望重塑开发流程。尽管已有方法在生成评论方面取得进展，但企业级工具仍面临诸多实际挑战。本文旨在回答：如何在不微调模型的前提下，设计出以评审为导向、上下文感知且质量可控的代码评论生成系统？我们提出了RovoDev Code Reviewer，一款在Atlassian内部规模化部署的端到端集成于Bitbucket的企业级代码审查自动化工具。通过为期一年的离线、在线及用户反馈评估，结果表明该工具能有效生成可引发代码修改的评论，成功率达38.7%；同时将拉取请求（PR）周期时间减少30.8%，降低人工评论数量35.6%，并发现具可操作性的错误，整体提升软件质量。
原文摘要 · Abstract (English)
Large Language Models (LLMs)-powered code review automation has the potential to transform code review workflows. Despite the advances of LLM-powered code review comment generation approaches, several practical challenges remain for designing enterprise-grade code review automation tools. In particular, this paper aims at answering the practical question: how can we design a review-guided, context-aware, quality-checked code review comment generation without fine-tuning? In this paper, we present RovoDev Code Reviewer, an enterprise-grade LLM-based code review automation tool designed and deployed at scale within Atlassian's development ecosystem with seamless integration into Atlassian's Bitbucket. Through the offline, online, user feedback evaluations over a one-year period, we conclude that RovoDev Code Reviewer is effective in generating code review comments that could lead to code resolution for 38.70% (i.e., comments that triggered code changes in the subsequent commits); and offers the promise of accelerating feedback cycles (i.e., decreasing the PR cycle time by 30.8%), alleviating reviewer workload (i.e., reducing the number of human-written comments by 35.6%), and improving overall software quality (i.e., finding errors with actionable suggestions).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。