How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912912913727488 |
|---|---|
| author | Watanabe, Kan Tsuchida, Rikuto Monno, Takahiro Huang, Bin Yamasaki, Kazuma Fan, Youmei Shimari, Kazumasa Matsumoto, Kenichi |
| author_facet | Watanabe, Kan Tsuchida, Rikuto Monno, Takahiro Huang, Bin Yamasaki, Kazuma Fan, Youmei Shimari, Kazumasa Matsumoto, Kenichi |
| contents | The rapid adoption of large language models has led to the emergence of AI coding agents that autonomously create pull requests on GitHub. However, how these agents differ in their pull request description characteristics, and how human reviewers respond to them, remains underexplored. In this study, we conduct an empirical analysis of pull requests created by five AI coding agents using the AIDev dataset. We analyze agent differences in pull request description characteristics, including structural features, and examine human reviewer response in terms of review activity, response timing, sentiment, and merge outcomes. We find that AI coding agents exhibit distinct PR description styles, which are associated with differences in reviewer engagement, response time, and merge outcomes. We observe notable variation across agents in both reviewer interaction metrics and merge rates. These findings highlight the role of pull request presentation and reviewer interaction dynamics in human-AI collaborative software development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17084 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses Watanabe, Kan Tsuchida, Rikuto Monno, Takahiro Huang, Bin Yamasaki, Kazuma Fan, Youmei Shimari, Kazumasa Matsumoto, Kenichi Artificial Intelligence Software Engineering The rapid adoption of large language models has led to the emergence of AI coding agents that autonomously create pull requests on GitHub. However, how these agents differ in their pull request description characteristics, and how human reviewers respond to them, remains underexplored. In this study, we conduct an empirical analysis of pull requests created by five AI coding agents using the AIDev dataset. We analyze agent differences in pull request description characteristics, including structural features, and examine human reviewer response in terms of review activity, response timing, sentiment, and merge outcomes. We find that AI coding agents exhibit distinct PR description styles, which are associated with differences in reviewer engagement, response time, and merge outcomes. We observe notable variation across agents in both reviewer interaction metrics and merge rates. These findings highlight the role of pull request presentation and reviewer interaction dynamics in human-AI collaborative software development. |
| title | How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses |
| topic | Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2602.17084 |