How Do Agentic AI Systems Deal With Software Energy Concerns? A Pull Request-Based Study

TL;DR

This study investigates how AI coding agents recognize and address software energy concerns through pull requests, revealing that while they show energy awareness, optimization PRs are less accepted due to maintainability issues.

Contribution

It provides the first taxonomy of energy-aware work in AI-generated pull requests and analyzes the alignment of optimization techniques with research recommendations.

Findings

Most energy-explicit PRs align with established research.

Agents exhibit energy awareness in generated artifacts.

Optimization PRs are less accepted due to maintainability concerns.

Abstract

As Software Engineering enters its new era (SE 3.0), AI coding agents increasingly automate software development workflows. However, it remains unclear how exactly these agents recognize and address software energy concerns-an issue growing in importance due to large-scale data centers, energy-hungry language models, and battery-constrained devices. In this paper, we examined the energy awareness of agent-authored pull requests (PRs) using a publicly available dataset. We identified 216 energy-explicit PRs and conducted a thematic analysis, deriving a taxonomy of energy-aware work. Our further analysis of the applied optimization techniques shows that most align with established research recommendations. Although building and running these agents is highly energy intensive, encouragingly, the results indicate that they exhibit energy awareness when generating software artifacts. However, optimization-related PRs are accepted less frequently than others, largely due to their negative impact on maintainability.