Does AI Code Review Lead to Code Changes? A Case Study of GitHub Actions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Kexin, Kuang, Hongyu, Baltes, Sebastian, Zhou, Xin, Zhang, He, Ma, Xiaoxing, Rong, Guoping, Shao, Dong, Treude, Christoph
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908992295403520
author Sun, Kexin
Kuang, Hongyu
Baltes, Sebastian
Zhou, Xin
Zhang, He
Ma, Xiaoxing
Rong, Guoping
Shao, Dong
Treude, Christoph
author_facet Sun, Kexin
Kuang, Hongyu
Baltes, Sebastian
Zhou, Xin
Zhang, He
Ma, Xiaoxing
Rong, Guoping
Shao, Dong
Treude, Christoph
contents AI-based code review tools automatically review and comment on pull requests to improve code quality. Despite their growing presence, little is known about their actual impact. We present a large-scale empirical study of 16 popular AI-based code review actions for GitHub workflows, analyzing more than 22,000 review comments in 178 repositories. We investigate (1) how these tools are adopted and configured, (2) whether their comments lead to code changes, and (3) which factors influence their effectiveness. We develop a two-stage LLM-assisted framework to determine whether review comments are addressed, and use interpretable machine learning to identify influencing factors. Our findings show that, while adoption is growing, effectiveness varies widely. Comments that are concise, contain code snippets, and are manually triggered, particularly those from hunk-level review tools, are more likely to result in code changes. These results highlight the importance of careful tool design and suggest directions for improving AI-based code review systems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18771
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Does AI Code Review Lead to Code Changes? A Case Study of GitHub Actions
Sun, Kexin
Kuang, Hongyu
Baltes, Sebastian
Zhou, Xin
Zhang, He
Ma, Xiaoxing
Rong, Guoping
Shao, Dong
Treude, Christoph
Software Engineering
AI-based code review tools automatically review and comment on pull requests to improve code quality. Despite their growing presence, little is known about their actual impact. We present a large-scale empirical study of 16 popular AI-based code review actions for GitHub workflows, analyzing more than 22,000 review comments in 178 repositories. We investigate (1) how these tools are adopted and configured, (2) whether their comments lead to code changes, and (3) which factors influence their effectiveness. We develop a two-stage LLM-assisted framework to determine whether review comments are addressed, and use interpretable machine learning to identify influencing factors. Our findings show that, while adoption is growing, effectiveness varies widely. Comments that are concise, contain code snippets, and are manually triggered, particularly those from hunk-level review tools, are more likely to result in code changes. These results highlight the importance of careful tool design and suggest directions for improving AI-based code review systems.
title Does AI Code Review Lead to Code Changes? A Case Study of GitHub Actions
topic Software Engineering
url https://arxiv.org/abs/2508.18771