Reproduce “The FrontierOR Challenge: Agentic Algorithm Design for Operations Research” 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
Hai Wang, Bretislav Hajek, Chonghe Jiang, Minwei Kong, Ao Qu, Huatian Gong, Bo Dong, Cynthia Barnhart and 1 more
The paper proposes a competition to test workflows that design, test, and improve algorithms, scoring them on hidden instances. Stage 1 covers 60 benchmark problems, while Stage 2 is intended to test transfer to problems outside the published benchmark. In a prior one-shot benchmark, Claude Fable 5 met its quality-and-runtime criterion on 39% of large instances; this is not a Challenge result.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.