← all papers · overview

Codetaste: Can Llms Generate Human-level Code Refactorings?

Abstract

Large language model (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. In this paper, we investigate if LLM agents (i) can execute refactorings reliably and (ii) identify

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).