# When AI Agents Touch CI/CD Configurations: Frequency and Success

arXiv: https://arxiv.org/abs/2601.17413 · HTML: https://mlsanity.com/paper/2601.17413/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2026.

## Built on by (most cited first, 3 of 3)

- [From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines](https://mlsanity.com/paper/2605.07062/) (2026)
- [AgenTag: Attribution of AI Coding Agents from Behavioral Fingerprints](https://mlsanity.com/paper/2608.00966/) (2026)
- [Specifying and Maintaining Agentic Workflows: An Empirical Study of GitHub Agentic Workflows](https://mlsanity.com/paper/2609.27263/) (2026)

## Abstract (arXiv)

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.