Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lima, Vinicius, Phan, Dzung T., Kalagnanam, Jayant, Patel, Dhaval, Zhou, Nianjun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918115276750848
author Lima, Vinicius
Phan, Dzung T.
Kalagnanam, Jayant
Patel, Dhaval
Zhou, Nianjun
author_facet Lima, Vinicius
Phan, Dzung T.
Kalagnanam, Jayant
Patel, Dhaval
Zhou, Nianjun
contents We present a framework for training trustworthy large language model (LLM) agents for optimization modeling via a verifiable synthetic data generation pipeline. Focusing on linear and mixed-integer linear programming, our approach begins with structured symbolic representations and systematically produces natural language descriptions, mathematical formulations, and solver-executable code. By programmatically constructing each instance with known optimal solutions, the pipeline ensures full verifiability and enables automatic filtering of low-quality demonstrations generated by teacher models. Each dataset instance includes a structured representation of the optimization problem, a corresponding natural language description, the verified optimal solution, and step-by-step demonstrations - generated by a teacher model - that show how to model and solve the problem across multiple optimization modeling languages. This enables supervised fine-tuning of open-source LLMs specifically tailored to optimization tasks. To operationalize this pipeline, we introduce OptiTrust, a modular LLM agent that performs multi-stage translation from natural language to solver-ready code, leveraging stepwise demonstrations, multi-language inference, and majority-vote cross-validation. Our agent achieves state-of-the-art performance on standard benchmarks. Out of 7 datasets, it achieves the highest accuracy on six and outperforms the next-best algorithm by at least 8 percentage on three of them. Our approach provides a scalable, verifiable, and principled path toward building reliable LLM agents for real-world optimization applications.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03117
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation
Lima, Vinicius
Phan, Dzung T.
Kalagnanam, Jayant
Patel, Dhaval
Zhou, Nianjun
Artificial Intelligence
We present a framework for training trustworthy large language model (LLM) agents for optimization modeling via a verifiable synthetic data generation pipeline. Focusing on linear and mixed-integer linear programming, our approach begins with structured symbolic representations and systematically produces natural language descriptions, mathematical formulations, and solver-executable code. By programmatically constructing each instance with known optimal solutions, the pipeline ensures full verifiability and enables automatic filtering of low-quality demonstrations generated by teacher models. Each dataset instance includes a structured representation of the optimization problem, a corresponding natural language description, the verified optimal solution, and step-by-step demonstrations - generated by a teacher model - that show how to model and solve the problem across multiple optimization modeling languages. This enables supervised fine-tuning of open-source LLMs specifically tailored to optimization tasks. To operationalize this pipeline, we introduce OptiTrust, a modular LLM agent that performs multi-stage translation from natural language to solver-ready code, leveraging stepwise demonstrations, multi-language inference, and majority-vote cross-validation. Our agent achieves state-of-the-art performance on standard benchmarks. Out of 7 datasets, it achieves the highest accuracy on six and outperforms the next-best algorithm by at least 8 percentage on three of them. Our approach provides a scalable, verifiable, and principled path toward building reliable LLM agents for real-world optimization applications.
title Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2508.03117