How Do Agentic AI Systems Address Performance Optimizations? A BERTopic-Based Analysis of Pull Requests

TL;DR

This study empirically analyzes how AI agents handle performance optimizations in software development, revealing their focus areas, impact on review outcomes, and phase-specific behaviors using topic modeling and pull request analysis.

Contribution

It introduces a BERTopic-based method to categorize AI-generated performance-related pull requests and provides insights into their application across software development phases.

Findings

AI agents perform diverse performance optimizations.

Optimization type influences review acceptance and duration.

Most optimizations occur during development, less during maintenance.

Abstract

LLM-based software engineering is influencing modern software development. In addition to correctness, prior studies have also examined the performance of software artifacts generated by AI agents. However, it is unclear how exactly the agentic AI systems address performance concerns in practice. In this paper, we present an empirical study of performance-related pull requests generated by AI agents. Using LLM-assisted detection and BERTopic-based topic modeling, we identified 52 performance-related topics grouped into 10 higher-level categories. Our results show that AI agents apply performance optimizations across diverse layers of the software stack and that the type of optimization significantly affects pull request acceptance rates and review times. We also found that performance optimization by AI agents primarily occurs during the development phase, with less focus on the maintenance phase. Our findings provide empirical evidence that can support the evaluation and improvement of agentic AI systems with respect to their performance optimization behaviors and review outcomes.