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.
Figures & tables
Category
Metrics
Description
Work Style
files_changed
Number of changed files
additions
Lines added
deletions
Lines deleted
commits
Commit count
Description Style
char
Total characters
header
Markdown headers count
Table 1. features extracted for PR Description Characteristics
Agent
for Engagement Metrics
for Sentiment Analysis
Claude Code
902
790
Github Copilot
16,581
14,515
Cursor
1,254
1,083
Devin
6,603
5,536
OpenAI Codex
3,621
2,889
Total
28,961
24,813
Table 2. Comment distribution across AI coding agents