AI agents are increasingly used in software development, yet their interaction with CI/CD configurations is not well studied. We analyze 8,031 agentic pull requests (PRs) from 1,605 GitHub repositories where AI agents touch YAML configurations. CI/CD configuration files account for 3.25% of agent changes, varying by agent (Devin: 4.83%, Codex: 2.01%, p < 0.001). When agents modify CI/CD, 96.77% target GitHub Actions. Agentic PRs with CI/CD changes merge slightly less often than others (67.77% vs. 71.80%), except for Copilot, whose CI/CD changes merge 15.63 percentage points more often. Across 99,930 workflow runs, build success rates are comparable for CI/CD and non-CI/CD changes (75.59% vs. 74.87%), though three agents show significantly higher success when modifying CI/CD. These results show that AI agents rarely modify CI/CD and focus mostly on GitHub Actions, yet their configuration changes are as reliable as regular code. Copilot's strong CI/CD performance despite lower acceptance suggests emerging configuration specialization, with implications for agent training and DevOps automation.

翻译：AI智能体在软件开发中的应用日益广泛，但其与CI/CD配置的交互尚未得到充分研究。本研究分析了来自1,605个GitHub仓库的8,031个涉及AI智能体修改YAML配置的智能体式拉取请求（PR）。CI/CD配置文件占智能体修改总量的3.25%，不同智能体间存在显著差异（Devin：4.83%，Codex：2.01%，p < 0.001）。当智能体修改CI/CD配置时，96.77%的改动针对GitHub Actions。包含CI/CD修改的智能体式PR合并率略低于其他PR（67.77% vs. 71.80%），但Copilot的CI/CD修改合并率反而高出15.63个百分点。通过对99,930次工作流运行的分析发现，CI/CD修改与非CI/CD修改的构建成功率基本相当（75.59% vs. 74.87%），但有三款智能体在修改CI/CD时展现出显著更高的成功率。这些结果表明：AI智能体较少修改CI/CD配置且主要聚焦GitHub Actions，但其配置修改的可靠性与常规代码相当。Copilot在CI/CD方面表现突出但接受度较低的现象，揭示了智能体在配置专业化方面的发展趋势，这对智能体训练与DevOps自动化具有重要启示。