AI RESEARCH
SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair
arXiv CS.CL
•
ArXi:2605.07001v1 Announce Type: cross Architectural code smells erode software maintainability and are costly to repair manually, yet unlike localized bugs, they require cross-module reasoning about design intent that challenges both developers and automated tools. While large language model agents excel at bug fixing and code-level refactoring, their ability to repair architectural code smells remains unexplored. We present the first empirical evaluation of LLM agents on architectural code smell repair.