Meta用AI自动化低风险代码审查，显著提升效率且保障安全。
Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency
- 分层自动化流程：基于作者、来源等多维度筛选，结合模型评分与LLM审查
- 审批率升至60.31%，回滚率降低至非自动化水平的1/3，事故率降为1/50
- 适合大规模研发团队应对AI生成代码激增带来的审查瓶颈
AI辅助编程工具改变了软件开发方式。在Meta，人均提交代码量年增长105.9%，开发者提交频次上升51%，其中超80%由智能体生成。然而，及时评审的代码比例下降，代码产出与评审能力间出现巨大缺口。我们提出三个问题：（1）风险分级自动化能否在多样化组织中规模化运行？（2）调整风险阈值如何影响自动化覆盖率与安全性之间的权衡？（3）自动化审查能多大程度减少AI生成代码的端到端延迟？部署了RADAR（Risk Aware Diff Auto Review）系统，采用多阶段流水线：按作者和源类型分类，通过准入条件、静态规则、机器学习的代码风险评分、LLM自动审查及确定性验证后才落地符合条件的变更。评估基于覆盖53.5万+次审查的遥测数据、政策变更的前后对比及效率结果的双重差分分析。RADAR已审查53.5万+次提交，成功落地33.1万+次。将风险评分阈值从第25百分位放宽至第50百分位，审批率提升至60.31%。经雷达审查的提交回滚率仅为非雷达提交的1/3，生产事故率仅为1/50。雷达系统使平均关闭时间缩短超330%，平均评审耗时减少35%。风险感知的分层自动化可有效缓解由AI驱动的代码增长带来的审查瓶颈，且不牺牲生产安全。
原文摘要 · Abstract (English)
AI-assisted coding tools have altered software production. At Meta, significant lines of code per human-landed diff grew by 105.9% year over year and per-developer diff volume rose 51%, with agentic AI responsible for over 80% of that growth. Meanwhile, the share of diffs receiving timely review has declined, exposing a widening gap between code supply and reviewer bandwidth. We ask three questions that progress from feasibility through calibration to impact: (1) can risk-stratified automation operate at scale across diverse organizations, (2) how does tuning the risk threshold affect the trade-off between automation yield and safety, and (3) to what extent does automated review reduce end-to-end latency for AI-generated changes? We deployed RADAR (Risk Aware Diff Auto Review), a multi-stage funnel that classifies each diff by authorship and source type, applies eligibility gates, static heuristics, a machine-learned Diff Risk Score, LLM-based Automated Code Review, and deterministic validation before landing qualifying changes. We evaluate RADAR through telemetry covering 535K+ RADAR-reviewed diffs, observational before-after comparisons for policy changes, and difference-in-differences analysis of efficiency outcomes. RADAR has reviewed 535K+ diffs and landed 331K+. Relaxing the Diff Risk Score threshold from the 25th to the 50th percentile increased the approve rate to 60.31%. The revert rate for RADAR-reviewed diffs is 1/3 that of non-RADAR diffs, and the Production Incident rate is 1/50 that of non-RADAR diffs. RADAR reduces median time to close by over 330% and median diff review wall time by 35%. Risk-aware layered automation can materially reduce review bottlenecks created by AI-driven code growth without compromising production safety.
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。