用大模型分析海量开源项目的流水线，发现其可靠性与维护问题。
LLM-Driven CI-CD Workflow Intelligence for Cyber Systems Engineering
- 通过大模型从配置文件中挖掘流水线阶段并识别异常模式
- 在超7.5万条流水线中发现43万次可靠性与可维护性问题
- 为不同语言和领域项目提供定制化优化建议，适合系统工程师参考
CI/CD 流水线已成为可执行的运营策略：决定哪些代码被构建、测试、发布和部署，并影响维护者与交付基础设施的交互方式。这使其成为网络系统工程的重要度量点。尽管近期大语言模型（LLM）研究显示可直接从配置文件中识别流水线阶段，但仅靠阶段标签无法判断流程是否脆弱、是否偏离生态常态或是否值得优先优化。本文提出一个基于 LLM 的 CI/CD 分析流水线，涵盖仓库增强、反模式检测、阶段挖掘与推荐生成，覆盖 59,550 个至少拥有 1,000 颗星的 GitHub 仓库，共识别出 34,225 个含 CI/CD 的项目，收集 127,559 份配置文件。在分析的 75,201 条流水线中，反模式检测报告 434,769 项发现，主要集中在可靠性和可维护性问题。在 59,906 份配置中，不同语言的阶段使用存在显著差异（χ² = 4168.88，p < 0.001，Cramer's V = 0.063），领域分析揭示不同项目类型的运行特征，如移动项目中发布与缓存使用更高。针对仓库级推荐生成，少样本提示效果最佳，平均每仓库生成 8.25 条建议，其中 96.1% 的 YAML 片段语法正确。结果表明，应将流水线可观测性视为诊断、上下文与人工评审相结合的综合过程，而非仅限于阶段分类任务。
原文摘要 · Abstract (English)
CI/CD workflows have become executable operational policy: they decide what gets built, tested, released, and deployed, and they mediate how maintainers interact with delivery infrastructure. That makes them an important measurement point for cyber-systems engineering. Recent large language model (LLM) work shows that workflow stages can be recognized directly from configuration files, but stage labels alone do not tell us whether a workflow is brittle, unusual for its ecosystem, or worth revising first. We present an LLM-based CI/CD analysis pipeline that combines repository enrichment, anti-pattern detection, stage mining, and recommendation generation over a large GitHub corpus. Starting from 59,550 repositories with at least 1,000 stars, we identify 34,225 projects with CI/CD and collect 127,559 configuration files. Across 75,201 analyzed workflows, the anti-pattern detector reports 434,769 findings, dominated by reliability and maintainability issues. Across 59,906 configurations, stage usage differs significantly by language ($χ^2 = 4168.88$, $p < 0.001$, Cramer's $V = 0.063$), and domain analysis shows distinct operational profiles, including higher release and cache usage in mobile projects. For repository-level recommendation generation, few-shot prompting performs best overall, averaging 8.25 recommendations per repository with 96.1% YAML-valid snippets. Taken together, the results argue for CI/CD observability that combines diagnosis, context, and human review rather than treating workflow mining as a stage-classification problem alone.
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。