These Aren't the Reviews You're Looking For How Humans Review AI-Generated Pull Requests

TL;DR

This study compares human and AI-generated pull request reviews on GitHub, revealing significant differences in review patterns and highlighting challenges in assessing human oversight in automated workflows.

Contribution

It provides the first systematic analysis of review interactions for AI-generated PRs, contrasting them with human-authored PRs within the same repositories.

Findings

Most AI-generated PRs receive no review.

AI-generated PR reviews are dominated by AI agents rather than humans.

Reviews of AI-generated PRs often involve automation-mediated interactions.

Abstract

We analyze code review interactions for AI-generated pull requests (PRs) on GitHub using the AIDev dataset and compare them to human-authored PRs within the same repositories. We find that most AI-generated PRs receive no review and, when reviewed, are largely dominated by AI agents rather than humans. Human-authored PRs are more likely to receive human-only review and to attract direct human feedback. In contrast, reviews of AI-generated PRs more often take the form of automation-mediated interaction, with human involvement frequently expressed through agent steering rather than standalone evaluation. These results indicate systematic differences in how review activity is structured in agentic workflows and raise challenges for interpreting review metrics as indicators of human oversight in large-scale mining studies.