Reproduce “EffiPair: Improving the Efficiency of LLM-generated Code with Differential Execution Feedback” 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

Samira Hajizadeh, Suman Jana

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.