Reproduce “Abstract Operations Research Modeling Using Natural Language Inputs” 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
Junxuan Li, Ryan Wickman, Sahil Bhatnagar, Raj Kumar Maity, Arko Mukherjee
NL2OR turns natural-language requests into reusable optimization model rules, then connects them to data and a solver. It supports edits to those rules before creating a concrete model. On 287 LPWP test problems at temperature 0.1, GPT-4o achieved 94.4% Valid@1, meaning valid model generations. This measures generation validity on that test, not correctness for every real-world use.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.