Bachelor and Master Theses

To apply for conducting this thesis, please contact the thesis supervisor(s).

Title:	Using LLMs for architectural restoration
Subject:	Software engineering, Computer science
Level:	Basic, Advanced
Description:	Technical debt is a common problem in software development. It happens when there's a mismatch between the actual code and how it was supposed to be designed. Generally, this issue comes down to keeping things consistent. When building software, developers use different tools and methods, like patterns, architectures, and code, which all need to work well together. Keeping everything aligned involves finding where things don't match up and fixing those issues. In this thesis, you will work on using LLMs to suggest ways to fix these mismatches. The LLMs will look at the problems and recommend strategies to correct them.
Start date:
End date:
Prerequisites:	Software architecture, software engineering Machine learning Good proficiency in English
IDT supervisors:	Alessio Bucaioni
Examiner:
Comments:
Company contact: