On Autopilot? An Empirical Study of Human-AI Teaming and Review Practices in Open Source
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917211431501824 |
|---|---|
| author | Gao, Haoyu Banyongrakkul, Peerachai Guan, Hao Zahedi, Mansooreh Treude, Christoph |
| author_facet | Gao, Haoyu Banyongrakkul, Peerachai Guan, Hao Zahedi, Mansooreh Treude, Christoph |
| contents | Large Language Models (LLMs) increasingly automate software engineering tasks. While recent studies highlight the accelerated adoption of ``AI as a teammate'' in Open Source Software (OSS), developer interaction patterns remain under-explored. In this work, we investigated project-level guidelines and developers' interactions with AI-assisted pull requests (PRs) by expanding the AIDev dataset to include finer-grained contributor code ownership and a comparative baseline of human-created PRs. We found that over 67.5\% of AI-co-authored PRs originate from contributors without prior code ownership. Despite this, the majority of repositories lack guidelines for AI-coding agent usage. Notably, we observed a distinct interaction pattern: AI-co-authored PRs are merged significantly faster with minimal feedback. In contrast to human-created PRs where non-owner developers receive the most feedback, AI-co-authored PRs from non-owners receive the least, with approximately 80\% merged without any explicit review. Finally, we discuss implications for developers and researchers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13754 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On Autopilot? An Empirical Study of Human-AI Teaming and Review Practices in Open Source Gao, Haoyu Banyongrakkul, Peerachai Guan, Hao Zahedi, Mansooreh Treude, Christoph Software Engineering Large Language Models (LLMs) increasingly automate software engineering tasks. While recent studies highlight the accelerated adoption of ``AI as a teammate'' in Open Source Software (OSS), developer interaction patterns remain under-explored. In this work, we investigated project-level guidelines and developers' interactions with AI-assisted pull requests (PRs) by expanding the AIDev dataset to include finer-grained contributor code ownership and a comparative baseline of human-created PRs. We found that over 67.5\% of AI-co-authored PRs originate from contributors without prior code ownership. Despite this, the majority of repositories lack guidelines for AI-coding agent usage. Notably, we observed a distinct interaction pattern: AI-co-authored PRs are merged significantly faster with minimal feedback. In contrast to human-created PRs where non-owner developers receive the most feedback, AI-co-authored PRs from non-owners receive the least, with approximately 80\% merged without any explicit review. Finally, we discuss implications for developers and researchers. |
| title | On Autopilot? An Empirical Study of Human-AI Teaming and Review Practices in Open Source |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2601.13754 |