Let's Make Every Pull Request Meaningful: An Empirical Analysis of Developer and Agentic Pull Requests
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915756428492800 |
|---|---|
| author | Yoshioka, Haruhiko Monno, Takahiro Tokumasu, Haruka Wakamatsu, Taiki Ota, Yuki Weeraddana, Nimmi Matsumoto, Kenichi |
| author_facet | Yoshioka, Haruhiko Monno, Takahiro Tokumasu, Haruka Wakamatsu, Taiki Ota, Yuki Weeraddana, Nimmi Matsumoto, Kenichi |
| contents | The automatic generation of pull requests (PRs) using AI agents has become increasingly common. Although AI-generated PRs are fast and easy to create, their merge rates have been reported to be lower than those created by humans. In this study, we conduct a large-scale empirical analysis of 40,214 PRs collected from the AIDev dataset. We extract 64 features across six families and fit statistical regression models to compare PR merge outcomes for human and agentic PRs, as well as across three AI agents. Our results show that submitter attributes dominate merge outcomes for both groups, while review-related features exhibit contrasting effects between human and agentic PRs. The findings of this study provide insights into improving PR quality through human-AI collaboration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18749 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Let's Make Every Pull Request Meaningful: An Empirical Analysis of Developer and Agentic Pull Requests Yoshioka, Haruhiko Monno, Takahiro Tokumasu, Haruka Wakamatsu, Taiki Ota, Yuki Weeraddana, Nimmi Matsumoto, Kenichi Software Engineering The automatic generation of pull requests (PRs) using AI agents has become increasingly common. Although AI-generated PRs are fast and easy to create, their merge rates have been reported to be lower than those created by humans. In this study, we conduct a large-scale empirical analysis of 40,214 PRs collected from the AIDev dataset. We extract 64 features across six families and fit statistical regression models to compare PR merge outcomes for human and agentic PRs, as well as across three AI agents. Our results show that submitter attributes dominate merge outcomes for both groups, while review-related features exhibit contrasting effects between human and agentic PRs. The findings of this study provide insights into improving PR quality through human-AI collaboration. |
| title | Let's Make Every Pull Request Meaningful: An Empirical Analysis of Developer and Agentic Pull Requests |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2601.18749 |