ENGLISH
La vitrine de diffusion des publications et contributions des chercheurs(-euses) de l'ÉTS
RECHERCHER

On the reliability of agentic AI in continuous integration pipelines

Chouchen, Moataz, Khelifi, Jasem, Begoug, Mahi, Ouni, Ali, Sayagh, Mohammed et Saied, Mohamed Aymen. 2026. « On the reliability of agentic AI in continuous integration pipelines ». In MSR '26: Proceedings of the 23rd International Conference on Mining Software Repositories (Rio de Janeiro, Brazil, Apr. 13-14, 2026) 837–841. Association for Computing Machinery, Inc.

[thumbnail of Ouni-A-2026-34488.pdf]
Prévisualisation
PDF
Ouni-A-2026-34488.pdf - Version publiée
Licence d'utilisation : Creative Commons CC BY.

Télécharger (656kB) | Prévisualisation

Résumé

Agentic AI systems powered by Large Language Models (LLMs) are increasingly used to autonomously contribute code in modern software development. While prior work has shown that such systems can accelerate development tasks, their reliability and maintenance behavior in real-world Continuous Integration (CI) workflows remain poorly understood. In this study, we analyze 11,771 pull requests (PRs) from GitHub, including 7,619 agentic and 4,152 human-authored PRs, to investigate how agentic code behaves during CI workflows. We examine (1) CI failure rates at the pull-request level, (2) responsibility for introducing and fixing CI failures, and (3) time-to-fix at the commit level using fail–fix mappings. Our results show that human-authored CI fixes exhibit a median time to fix of 71.70 minutes, whereas AI agentic-authored CI fixes resolve failures nearly four times faster, with a median of 17.23 minutes. Our results show that agent-authored fixes resolve CI failures nearly four times faster than human fixes (median 17.23 vs. 71.70 minutes). However, agents introduce most CI failures (79.15%) while performing a smaller share of fixes (60.63%), indicating that human developers remain heavily involved in failure resolution despite faster agent responses.

Type de document: Compte rendu de conférence
Chercheur(-euse):
Chercheur(-euse)
Ouni, Ali
Sayagh, Mohammed
Affiliation: Génie logiciel et des technologies de l'information, Génie logiciel et des technologies de l'information
Date de dépôt: 02 oct. 2026 18:40
Dernière modification: 02 oct. 2026 22:34
URI: https://espace2.etsmtl.ca/id/eprint/34488

Actions (Authentification requise)

Dernière vérification avant le dépôt Dernière vérification avant le dépôt