ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling

TL;DR

ORPilot is an open-source AI system designed for production-level optimization modeling, capable of handling ambiguous data and multiple solvers, outperforming academic benchmarks in real-world business problems.

Contribution

It introduces a novel, production-oriented approach with four key components, enabling robust, portable, and accurate optimization modeling from raw business data.

Findings

Outperforms state-of-the-art tools on IndustryOR benchmark.

Achieves comparable results on NL4OPT and NLP4LP benchmarks.

Demonstrates effectiveness on real-world business problems.

Abstract

This paper presents ORPilot, an open-source agentic AI system that translates real-world business problems into solver-ready optimization models. Unlike academic LLM-for-OR tools that assume clean problem specifications with preformatted inline data, ORPilot is designed for production conditions: ambiguous descriptions, large-scale raw operational data, and the need for portability across solver backends. The system introduces four novel components: (1) a conversational interview agent to elicit complete problem specifications, (2) a data collection agent that retrieves data independently of prompts, (3) a parameter computation agent to bridge raw tabular data and model-ready parameters, and (4) a solver-agnostic Intermediate Representation (IR) for deterministic, zero-LLM-call recompilation to Gurobi, CPLEX, PuLP, Pyomo, or OR-Tools solvers. Additionally, self-correcting retry loops utilize solver tracebacks for targeted repairs. ORPilot represents the first attempt to target production-level business problems rather than textbook operations research (OR) cases. Evaluation on real-world problems demonstrates promising results. When tested against traditional academic benchmarks: IndustryOR, NL4OPT and NLP4LP, ORPilot outperformed state-of-the-art tools in accuracy on the IndustryOR benchmark and delivered comparable performance on NL4OPT and NLP4LP.