FrontierOR Challenge benchmarks LLM agents at operations-research algorithm design
The FrontierOR Challenge is a new benchmark and competition for agentic workflows that design, test, and improve optimization algorithms across many operations-research problems. Stage 1 releases 60 of 180 audited problems across six application categories and five formulation types in weekly rounds of 15, while Stage 2 adds new problems and unseen instances. Two tracks are ranked separately: a network-isolated sandbox using open-source dependencies and a self-hosted track allowing any software within a timed window. Organizers report that in one-shot evaluation the strongest model matched Gurobi within 1% objective and no slower on only 39% of large instances.
It provides a concrete, audited benchmark and competition format for measuring whether LLM agents can produce scalable operations-research algorithms.
Comments & Questions (0)
No comments yet
Be the first to comment!