# An Exploratory Study on Architectural Smell Refactoring Using Large Languages Models

- **År:** 2025
- **Type:** Vitenskapelig (NVA: AcademicChapter)
- **Publiseringssted:** 2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C)
- **Forfattere:** Gabriele Pandini, Antonio Martini, Adela Nedisan Videsjorden, Francesca Arcelli Fontana
- **Open access:** https://hdl.handle.net/11250/3243462
- **Cristin:** https://app.cristin.no/results/show.jsf?id=10249971

## Forskere med profil på nettstedet
- [Antonio Martini](https://research.lab.knowit.no/people/#antonio-martini) ([markdown](https://research.lab.knowit.no/people/antonio-martini.md))

## Abstract

Architectural smells are abundant in codebases and regularly hinder the development of stable and maintainable code. Understanding and removing these elements can consume a huge amount of developers' time, who often need to prioritize implementing new features. This causes a substantial increase in Technical Debt, compromising the scalability and maintainability of the codebases, at time bringing the development to a standstill. Meanwhile, the use of Large Language Models for small error correction is constantly growing, bringing the attention of an ever-wider audience to these technologies. This study explores a first approach to use Large Language Models to suggest refactoring for architectural smells, with a focus on Cyclic Dependencies smells. We study the use of detailed prompt and Retrieval-Augmented Generation (RAG) to enhance LLMs, and we study local vs cloud LLMs. The results are promising, also validated with a series of interviews with students and developers, and highlight how additional and precise context is key to enhance the use of LLMs to propose refactoring suggestions. A multi-agent approach seems to be more suited when increasing the complexity of the smells.

---
Kanonisk HTML: https://research.lab.knowit.no/publications/2025-an-exploratory-study-on-architectural-smell-refact/
Oversikt: https://research.lab.knowit.no/publications.md · Alle ruter: https://research.lab.knowit.no/llms.txt