How Do Agentic AI Systems Deal With Software Energy Concerns? A Pull Request-Based Study
By: Tanjum Motin Mitul , Md. Masud Mazumder , Md Nahidul Islam Opu and more
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.
Similar Papers
On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
Software Engineering
AI helps programmers fix code, saving them time.
How Do Agents Perform Code Optimization? An Empirical Study
Software Engineering
AI helps make computer programs run faster.
A Study of Library Usage in Agent-Authored Pull Requests
Software Engineering
AI coding helpers use many tools wisely.