OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement
2026-07-06 • Artificial Intelligence
Artificial IntelligenceMultiagent Systems
AI summaryⓘ
The authors created OptiAgent, a system that can take a written description of an Operations Research problem and turn it into a ready-to-use mathematical model and code. Their design uses several specialized agents that focus on different parts of the problem, like variables and constraints, and can correct mistakes by checking their work in multiple rounds. They also built in ways to catch errors like misunderstandings or math problems, making the modeling process clearer and easier to follow. Their framework performed very well on standard tests involving different types of optimization problems.
Operations ResearchMathematical ModelingLinear Programming (LP)Mixed-Integer Linear Programming (MILP)Nonlinear ProgrammingMulti-agent SystemIterative ValidationOptimization SolverConstraint Extraction
Authors
Adriana Laurindo Monteiro, Nayse Fagundes, Gabriel Mattos Langeloh, Gustavo de Oliveira Kanno, Priscila Louise Aguirre, Thiago Costa Rizuti da Rocha, Victor Leme Beltran
Abstract
We propose OptiAgent, a multi-agent framework that, given a natural language description of an Operations Research problem, is able to output a solver-ready mathematical formulation as well as executable code. Our architecture prioritizes the mathematical modeling step, where dedicated agents extract structures, such as decision variables and constraints, enabling iterative self-correction. We introduce a novel multi-loop validation architecture with four specialized feedback mechanisms, each targeting a distinct failure mode such as misinterpretation, structural defects, mathematical inconsistencies, validation failures, and code errors. Alongside accuracy, our modular design improves the process of solving optimization problems by improving transparency, as each agent exposes its reasoning and feedback, making the full modeling process auditable. Our framework achieves state-of-the-art performance on 3 out of 4 benchmarks across LP, MILP, and Nonlinear Programming tasks, while remaining highly competitive on the remaining dataset.