# ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization Modeling

arXiv: https://arxiv.org/abs/2602.03070 · HTML: https://mlsanity.com/paper/2602.03070/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2026.

## Built on by (most cited first, 3 of 3)

- [OptArgus: A Multi-Agent System to Detect Hallucinations in LLM-based Optimization Modeling](https://mlsanity.com/paper/2605.11738/) (2026)
- [Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery](https://mlsanity.com/paper/2610.03872/) (2026)
- [ML-OPF-Bench: Benchmarking Machine Learning for Optimal Power Flow](https://mlsanity.com/paper/2610.04307/) (2026)

## Abstract (arXiv)

Growing renewable penetration introduces substantial uncertainty into power system operations, necessitating frequent adaptation of dispatch objectives and constraints and challenging expertise-intensive, near-real-time modeling workflows. Large Language Models (LLMs) provide a promising avenue for automating this process by translating natural-language (NL) operational requirements into executable optimization models via semantic reasoning and code synthesis. Yet existing LLM datasets and benchmarks for optimization modeling primarily target coarse-grained cross-domain generalization, offering limited, rigorous evaluation in power-system settings, particularly for Optimal Power Flow (OPF). We therefore introduce ProOPF-D and ProOPF-B, a dataset and benchmark for professional-grade OPF modeling: ProOPF-D contains 12K instances pairing NL requests with parameter adjustments and structural extensions to a canonical OPF, together with executable implementations; ProOPF-B provides 121 expert-annotated test cases with ground-truth code, enabling end-to-end evaluation under both concrete and abstract OPF modeling regimes.