These Aren't the Reviews You're Looking For How Humans Review AI-Generated Pull Requests
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909011712933888 |
|---|---|
| author | Duma, Kacper Wróblewski, Patryk Bobińska, Jagoda Winiarska, Julia Przymus, Piotr |
| author_facet | Duma, Kacper Wróblewski, Patryk Bobińska, Jagoda Winiarska, Julia Przymus, Piotr |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02273 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | These Aren't the Reviews You're Looking For How Humans Review AI-Generated Pull Requests Duma, Kacper Wróblewski, Patryk Bobińska, Jagoda Winiarska, Julia Przymus, Piotr Software Engineering 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. |
| title | These Aren't the Reviews You're Looking For How Humans Review AI-Generated Pull Requests |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2605.02273 |