Let's Make Every Pull Request Meaningful: An Empirical Analysis of Developer and Agentic Pull Requests

In recent years, 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 tend 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 spanning six families, and fit statistical regression models to analyze and compare the features associated with PR merge outcomes for human and agentic PRs, as well as across three prominent AI agents.
The findings of this study provide insights into improving PR quality through human–AI collaboration.