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

TL;DR

This study empirically evaluates the adoption, configuration, and effectiveness of AI-based code review tools on GitHub, revealing factors that influence whether comments lead to code changes.

Contribution

It introduces a two-stage LLM-assisted framework to assess comment responsiveness and identifies key factors affecting AI review tool effectiveness.

Findings

Adoption of AI review tools is increasing but effectiveness varies.

Concise comments with code snippets are more likely to prompt changes.

Hunk-level review tools have higher impact on code modifications.

Abstract

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.