Reproduce “Together We Go Further: LLMs and IDE Static Analysis for Extract Method Refactoring” 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
Dorin Pomian, Abhiram Bellur, Malinda Dilhara, Zarina Kurbatova, Egor Bogomolov, Timofey Bryksin, Danny Dig
EM-Assist helps developers choose code to extract into a new method by generating candidate groupings with a language model, screening them with IDE static analysis, refining and ranking them, and leaving the final choice to the programmer. On 1,752 mined refactorings, it achieved mean Recall@5 of 53.4%, versus 39.4% for JExtract at 3% tolerance; this measures line-boundary matches, not acceptance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.