BitsAI-CR: Automated Code Review via LLM in Practice
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909466376536064 |
|---|---|
| author | Sun, Tao Xu, Jian Li, Yuanpeng Yan, Zhao Zhang, Ge Xie, Lintao Geng, Lu Wang, Zheng Chen, Yueyan Lin, Qin Duan, Wenbo Sui, Kaixin |
| author_facet | Sun, Tao Xu, Jian Li, Yuanpeng Yan, Zhao Zhang, Ge Xie, Lintao Geng, Lu Wang, Zheng Chen, Yueyan Lin, Qin Duan, Wenbo Sui, Kaixin |
| contents | Code review remains a critical yet resource-intensive process in software development, particularly challenging in large-scale industrial environments. While Large Language Models (LLMs) show promise for automating code review, existing solutions face significant limitations in precision and practicality. This paper presents BitsAI-CR, an innovative framework that enhances code review through a two-stage approach combining RuleChecker for initial issue detection and ReviewFilter for precision verification. The system is built upon a comprehensive taxonomy of review rules and implements a data flywheel mechanism that enables continuous performance improvement through structured feedback and evaluation metrics. Our approach introduces an Outdated Rate metric that can reflect developers' actual adoption of review comments, enabling automated evaluation and systematic optimization at scale. Empirical evaluation demonstrates BitsAI-CR's effectiveness, achieving 75.0% precision in review comment generation. For the Go language which has predominant usage at ByteDance, we maintain an Outdated Rate of 26.7%. The system has been successfully deployed at ByteDance, serving over 12,000 Weekly Active Users (WAU). Our work provides valuable insights into the practical application of automated code review and offers a blueprint for organizations seeking to implement automated code reviews at scale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_15134 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BitsAI-CR: Automated Code Review via LLM in Practice Sun, Tao Xu, Jian Li, Yuanpeng Yan, Zhao Zhang, Ge Xie, Lintao Geng, Lu Wang, Zheng Chen, Yueyan Lin, Qin Duan, Wenbo Sui, Kaixin Software Engineering Code review remains a critical yet resource-intensive process in software development, particularly challenging in large-scale industrial environments. While Large Language Models (LLMs) show promise for automating code review, existing solutions face significant limitations in precision and practicality. This paper presents BitsAI-CR, an innovative framework that enhances code review through a two-stage approach combining RuleChecker for initial issue detection and ReviewFilter for precision verification. The system is built upon a comprehensive taxonomy of review rules and implements a data flywheel mechanism that enables continuous performance improvement through structured feedback and evaluation metrics. Our approach introduces an Outdated Rate metric that can reflect developers' actual adoption of review comments, enabling automated evaluation and systematic optimization at scale. Empirical evaluation demonstrates BitsAI-CR's effectiveness, achieving 75.0% precision in review comment generation. For the Go language which has predominant usage at ByteDance, we maintain an Outdated Rate of 26.7%. The system has been successfully deployed at ByteDance, serving over 12,000 Weekly Active Users (WAU). Our work provides valuable insights into the practical application of automated code review and offers a blueprint for organizations seeking to implement automated code reviews at scale. |
| title | BitsAI-CR: Automated Code Review via LLM in Practice |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2501.15134 |