Open access
Nov 2026
Refactoring architectural smells with large language models: an exploratory study on cyclic dependencies
Findings show that detailed contextualization significantly improves the quality of LLM-generated suggestions and that more complex smells may benefit from an agentic approach.
Gabriele Pandini, Arda Goknil, Karthik Shivashankar et al.
· Empirical Software Engineeri... · 0 citations