Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests
This addresses the problem of trustworthiness in AI coding agents for software developers, by revealing how inconsistent pull request descriptions impact collaboration, though it is incremental as it builds on existing concerns about AI reliability.
The study analyzed 23,247 AI-generated pull requests and found that 1.7% exhibited high message-code inconsistency, with the most common issue being descriptions claiming unimplemented changes (45.4%), leading to 51.7% lower acceptance rates and 3.5 times longer merge times.
Pull request (PR) descriptions generated by AI coding agents are the primary channel for communicating code changes to human reviewers. However, the alignment between these messages and the actual changes remains unexplored, raising concerns about the trustworthiness of AI agents. To fill this gap, we analyzed 23,247 agentic PRs across five agents using PR message-code inconsistency (PR-MCI). We contributed 974 manually annotated PRs, found 406 PRs (1.7%) exhibited high PR-MCI, and identified eight PR-MCI types, revealing that "descriptions claim unimplemented changes" was the most common issue (45.4%). Statistical tests confirmed that high-MCI PRs had 51.7% lower acceptance rates (28.3% vs. 80.0%) and took 3.5 times longer to merge (55.8 vs. 16.0 hours). Our findings suggest that unreliable PR descriptions undermine trust in AI agents, highlighting the need for PR-MCI verification mechanisms and improved PR generation to enable trustworthy human-AI collaboration.