Reproduce “PEA: Enhancing LLM Performance on Computational-Reasoning Tasks” 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
Zi Wang, Shiwei Weng, Mohannad Alhanahnah, Somesh Jha, Tom Reps
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.