LLM for Large-Scale Optimization Model Auto-Formulation: A Lightweight Agentic Workflow Construction Approach
Large-scale optimization is a key backbone of modern business decision-making. However, building these models is often labor-intensive and time-consuming. We address this by proposing LEAN-LLM-OPT, a LightwEight AgeNtic workflow construction framework for LLM-assisted large-scale OPTimization auto-formulation. LEAN-LLM-OPT takes as input a problem description together with associated datasets and orchestrates a team of LLM agents to produce an optimization formulation. Specifically, upon receiving a query, two upstream LLM agents dynamically construct a workflow that specifies, step-by-step, how optimization models for similar problems can be formulated. A downstream LLM agent then follows this workflow to generate the final output. Leveraging LLMs’ text-processing capabilities and common modeling practices, the workflow decomposes the modeling task into a sequence of structured sub-tasks and offloads mechanical data-handling operations to auxiliary tools. This design alleviates the downstream agent’s burden related to planning and data handling, allowing it to focus on the most challenging components that cannot be readily standardized. Extensive simulations show that LEAN-LLM-OPT, instantiated with GPT-4.1 and the open source gpt-oss-20B, achieves strong performance on large-scale optimization modeling tasks and is competitive with state-of-the-art approaches. In addition, in a Singapore Airlines choice-based revenue management use case, LEAN-LLM-OPT demonstrates practical value by achieving leading performance across a range of scenarios. Along the way, we introduce Large-Scale-OR and Air-NRM, the first comprehensive benchmarks for large-scale optimization auto-formulation. The code and data of this work is available here.
Bio: Ruihao Zhu is an assistant professor of operations, technology, and information management at the Cornell SC Johnson College of Business. His research develops novel reinforcement learning algorithms to inform decision-making in digital economy, pricing, and supply chain & logistics. He also enjoys tackling practically relevant problems and has been working closely with different companies to test and implement his methods.
Ruihao’s work has received multiple recognitions, including second place in the POMS Chelliah Sriskandarajah Early Career Research Accomplishments Award and an honorable mention in the INFORMS George B. Dantzig Dissertation Award. He currently serves as an associate editor for the INFORMS Journal on Data Science and as an area chair for the Annual Conference on Neural Information Processing Systems (NeurIPS) and the International Conference on Machine Learning (ICML).
Ruihao received his Ph.D. degree from MIT (2021) and his bachelor degrees from the Shanghai Jiao Tong University (2015) and the University of Michigan (2015).