More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests

TL;DR

This study examines how AI-generated pull requests impact code quality, reuse, and reviewer sentiment, revealing that AI often produces redundant code but reviewers remain generally positive, highlighting challenges in human-AI collaboration.

Contribution

The paper introduces a comprehensive evaluation of AI-generated pull requests, focusing on code redundancy, maintainability, and human reviewer reactions, beyond traditional pass rate metrics.

Findings

AI PRs show higher redundancy than human PRs.

Reviewers tend to respond neutrally or positively to AI PRs.

AI-generated code may silently increase technical debt.

Abstract

Large Language Model (LLM) Agents are advancing quickly, with the increasing leveraging of LLM Agents to assist in development tasks such as code generation. While LLM Agents accelerate code generation, studies indicate they may introduce adverse effects on development. However, existing metrics solely measure pass rates, failing to reflect impacts on long-term maintainability and readability, and failing to capture human intuitive evaluations of PR. To increase the comprehensiveness of this problem, we investigate and evaluate the characteristics of LLM to know the pull requests' characteristics beyond the pass rate. We observe the code quality and maintainability within PRs based on code metrics to evaluate objective characteristics and developers' reactions to the pull requests from both humans and LLM's generation. Evaluation results indicate that LLM Agents frequently disregard code reuse opportunities, resulting in higher levels of redundancy compared to human developers. In contrast to the quality issues, our emotions analysis reveals that reviewers tend to express more neutral or positive emotions towards AI-generated contributions than human ones. This disconnect suggests that the surface-level plausibility of AI code masks redundancy, leading to the silent accumulation of technical debt in real-world development environments. Our research provides insights for improving human-AI collaboration.