GHA-SmellFix：用智能体 LLM 检测并修复 GitHub Actions 工作流坏味道
GHA-SmellFix: Taking Action with Agentic LLMs for Detecting and Refactoring GitHub Actions Workflow Smells
四个轻量模型实测了检测和重构拆开还是合并更有效，结论挺反直觉：拆分主要靠门控省开销，真正的瓶颈是漏检。写 GitHub Actions 的 CI 工程师和做 CI 自动化智能体的人都该看看这套评估设计。
论文提出 GHA-SmellFix，一个用于检测和重构 GitHub Actions 工作流坏味道（smells）的智能体 LLM 流水线。作者从已有目录中选取 19 种坏味道，为每种定义明确的检测标准、重构预期、排除规则和安全检查，并构建了 1,710 个（工作流，坏味道）对的标注数据集。
研究对比了两种设计：Joint 方案由单个智能体同时完成检测和重构，Decomposed 方案由独立的检测智能体和重构智能体分别负责。在 570 个采样样本上，用 GPT-5.4-nano、Gemini 3.5 Flash、Claude Haiku 4.5 和 DeepSeek V4 Flash 四个模型进行评估。
结果显示，任务分解并不普遍提升补丁质量，其主要作用是控制何时尝试生成补丁：对容易漏检的模型有帮助，并通过门控机制减少开销。坏味道一旦被正确检出，干净的重构通常有效，说明端到端的主要瓶颈在检测环节。此外，误报可能触发对执行相关构造的不必要修改，因此实用的 CI/CD 智能体需要可靠的弃权机制和构造感知的验证。
相比现有以规则为主、只报告不给修复的方法，GHA-SmellFix 提供了带安全检查的补丁生成路径。
GHA-SmellFix: Taking Action with Agentic LLMs for Detecting and Refactoring GitHub Actions Workflow Smells
Continuous integration and continuous delivery workflows are key artifacts in software projects. In GitHub Actions, they encode build, test, release, deployment, and security automation in YAML. These workflows contain configuration smells affecting security, reliability, maintainability, or operational stability. Existing approaches are mostly rule-based, with rules hard to create and evolve, and typically report findings without fixes. Agentic LLM pipelines can combine contextual detection, transformation selection, and patch generation. Specialized agents can gate refactoring on positive detection verdicts, potentially avoiding unnecessary changes, but it is unclear whether decomposition improves effectiveness or mainly changes overhead. We present GHA-SmellFix, an agentic LLM pipeline for detecting and refactoring GitHub Actions workflow smells. We compare two designs: Joint, where one agent detects and refactors, and Decomposed, where separate agents detect and then refactor. We operationalize 19 smells from an existing catalog with explicit detection criteria, refactoring expectations, exclusion rules, and safety checks, and curate a ground truth of 1,710 (workflow, smell) pairs. We evaluate the designs with four LLMs (GPT-5.4-nano, Gemini 3.5 Flash, Claude Haiku 4.5, and DeepSeek V4 Flash) on 570 sampled pairs. Results show that decomposition does not universally improve patch quality; its main benefit is controlling when patch generation is attempted. It helps models prone to missing smells and can reduce overhead by gating patches. Once a smell is correctly detected, clean refactoring is generally effective, making detection the main end-to-end bottleneck. However, false positives can trigger unnecessary edits to execution-relevant constructs. Practical CI/CD agents thus need reliable abstention and construct-aware validation alongside patch generation.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include GitHub Actions, CI/CD, 智能体, GHA-SmellFix.
Primary source verification: published directly by arXiv: DeepSeek with first-party authority.
