Pith. sign in

REVIEW 3 cited by

BitsAI-CR: Automated Code Review via LLM in Practice

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.15134 v1 pith:QNXIXUW7 submitted 2025-01-25 cs.SE

Tao Sun , Jian Xu , Yuanpeng Li , Zhao Yan , Ge Zhang , Lintao Xie , Lu Geng , Zheng Wang
show 4 more authors
Yueyan Chen Qin Lin Wenbo Duan Kaixin Sui
This is my paper
classification cs.SE
keywords reviewcodeautomatedbitsai-crevaluationprecisionapproachbytedance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 Our approach introduces an Outdated Rate metric that can reflect developers' actual adoption of review comments, enabling automated evaluation and systematic optimization at scale.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 For the Go language which has predominant usage at ByteDance, we maintain an Outdated Rate of 26.7%.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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation

    cs.SE 2025-09 conditional novelty 6.0 of 10

    SWR-Bench is a PR-centric code review benchmark with objective LLM scoring; current ACR tools reach at best 19.4% F1, and multi-review aggregation yields relative F1 gains up to 43.7%.

  2. BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice

    cs.SE 2025-08 conditional novelty 6.0 of 10

    A 32B LLM trained with progressive reinforcement learning on cold-start and user-feedback data fixes Go lint errors at 84.68% accuracy with 1.72% redundancy on a private ByteDance test set.

  3. P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark

    cs.CL 2025-05 conditional novelty 6.0 of 10

    P2P is a multi-agent framework that automatically generates HTML-rendered academic posters from papers, backed by a 30k instruction dataset and a 121-pair evaluation benchmark.

Pith tools