More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests
Haoming Huang, Pongchai Jaisri, Shota Shimizu, Lingfeng Chen, Sota Nakashima, Gema Rodríguez-Pérez
TL;DR
The paper addresses the problem that improvement in PR generation speed from AI agents may mask long-term maintainability issues. It couples traditional code-quality metrics with a novel Max Redundancy Score derived from semantic embeddings to detect Type-4 semantic clones, and it analyzes reviewer sentiment to understand human perception of AI-contributed PRs. Findings show AI-generated PRs exhibit significantly higher redundancy than human PRs, yet reviewers tend to respond with neutral or positive sentiment toward AI code, revealing a disconnect that can lead to silent technical debt. This work highlights the need for including reuse-focused metrics in evaluation and informs better human-AI collaboration practices in software development.
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.