CodeTaste: Can LLMs Generate Human-Level Code Refactorings?

arXiv:2603.04177v2 Announce Type: replace-cross Abstract: LLM coding agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt. Human developers address such issues through refactoring: behavior-preserving program transformations that improve structure and maintainability. We investigate whether agents (i) can execute refactorings reliably and (ii) identify the refactorings that human developers actually chose in real codebases. To thi