ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling
Top Cited Papers
- 1 November 2025
- journal article
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Operations Research
- Vol. 73 (6) , 2986-3009
Abstract
ORLM: Pioneering Open-Source Framework for Automated Optimization Modeling A study titled "ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling" has been published, introducing the first open-source framework designed to automate optimization modeling using large language models (LLMs). This innovative approach addresses critical challenges in the field of operations research (OR), particularly the overreliance on closed-source LLMs like GPT-4, which raises privacy concerns and limits customization in industrial applications. The research team proposed OR-Instruct, a semiautomated data synthesis framework that generates high-quality training data tailored to specific optimization modeling requirements. They also introduced IndustryOR, the first benchmark for evaluating LLMs’ performance on real-world OR problems. By training several 7B-scale open-source LLMs with the synthesized data, the team achieved state-of-the-art results across multiple benchmarks, including NL4Opt, MAMO, and IndustryOR. This advancement not only enhances the accessibility and applicability of optimization modeling, but also paves the way for more efficient and privacy-conscious solutions in various industrial sectors. The ORLM framework exemplifies the potential of open-source initiatives in driving innovation and democratizing advanced analytical tools for operations research.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Solving olympiad geometry without human demonstrationsNature, 2024
- Deep Spatial Q-Learning for Infectious Disease ControlJournal of Agricultural, Biological and Environmental Statistics, 2023
- TGVx: Dynamic Personalized POI Deep Recommendation ModelINFORMS Journal on Computing, 2023
- A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applicationsJournal of Big Data, 2023
- A Practical End-to-End Inventory Management Model with Deep LearningManagement Science, 2023
- Advanced Analytics Drives Reengineering of Field Operations for the 2020 U.S. CensusINFORMS Journal on Applied Analytics, 2023
- JD.com: Operations Research Algorithms Drive Intelligent Warehouse Robots to WorkINFORMS Journal on Applied Analytics, 2022
- Grammatical evolution for constraint synthesis for mixed-integer linear programmingSwarm and Evolutionary Computation, 2021
- Probabilistic forecasting with temporal convolutional neural networkNeurocomputing, 2020
- Automatic synthesis of constraints from examples using mixed integer linear programmingEuropean Journal of Operational Research, 2017