Generative AI-Assisted Migration of Large Software Projects to Modern Cross-Platform Technologies
Received: 08 Oct 2026 Revised: 23 Oct 2026 Accepted: 25 Oct 2026
Published: 2026, vol. 30, issue 4, pp. 332–335
Abstract
Two LLM-assisted C# migrations are studied: EnergyCalc from Xamarin.Forms to Uno Platform and HouseBuilder from Xamarin.Forms and WPF/OpenTK to Godot. The assessment separates core reuse, host creation, LLM participation, and scenario parity. EnergyCalc retained 40–55% of code and passed 260 of 300 scenarios in 200 person-hours. HouseBuilder reused 70–80% of product code and passed 450 of 600 scenarios in 330 person-hours.
Keywords: large language models, AI agents, software migration, C\#, Uno Platform, Godot.
BibTeX
@article{IS-Beliaev2026,
author = {Beliaev, Artem},
title = {{Generative AI-Assisted Migration of Large Software Projects to Modern Cross-Platform Technologies}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {332--335},
}
AMSBIB
\Bibitem{IS-Beliaev2026}
\by A.~Beliaev
\paper Generative AI-Assisted Migration of Large Software Projects to Modern Cross-Platform Technologies
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 332--335
\lang In Russian
RU