OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners

A new benchmark, OR-License, evaluates whether large language model agents can produce expert-level operations research solutions directly from original client materials without prior expert reformulation. The work targets a gap in existing OR benchmarks, which typically start from self-contained descriptions or predefined optimization tasks rather than raw client inputs. The source provides no results, figures, or named authors for the benchmark.

Can large language model LLM agents deliver expert-level operations research OR solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks typically begin with self-contained descriptions or predefined optimization tasks, underrepresenting the t