Reproduce “Software Refactoring Research with Large Language Models: A Systematic Literature Review” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sofia Martinez, Luo Xu, Mariam Elnaggar, Eman Abdullah AlOmar
The authors review 50 primary studies of large language models used for software refactoring, finding that tasks, benchmarks, and success measures vary. Only 22 studies report correctness-focused assessments. In one Java unit-test refactoring study, UTRefactor reduced test smells from 2,375 to 265, compared with 55% elimination for standard LLM-based approaches; this result is specific to that task, not general capability.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.