OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale
read the original abstract
Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare. However, most such problems are still solved heuristically by hand rather than optimally by state-of-the-art solvers because the expertise required to formulate and solve these problems limits the widespread adoption of optimization tools and techniques. We introduce a Large Language Model (LLM)-based system designed to formulate and solve (mixed integer) linear programming problems from their natural language descriptions. Our system can develop mathematical models, write and debug solver code, evaluate the generated solutions, and improve efficiency and correctness of its model and code based on these evaluations. OptiMUS is designed as a productivity tool for optimization practitioners who understand the problem domain and can describe it precisely, but seek to accelerate the modeling and implementation workflow. OptiMUS-0.3 utilizes a modular structure to process problems, allowing it to handle problems with long descriptions and complex data without long prompts. Experiments demonstrate that OptiMUS-0.3 outperforms direct-prompting baselines by over 43% on easy and 18% on hard instances. It remains competitive with fine-tuned specialist models on benchmark problems, and outperforms them on real-world case studies (28.6% vs. 0%) where fine-tuned models fail to generalize. Ablation studies show that modular architecture with error correction is central to these gains. A key finding is that system architecture is a stronger driver of performance than model capability. Structured decomposition with targeted error correction enables weaker models to match stronger models under naive prompting, and remains competitive with fine-tuned specialist models without retraining costs.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Agentic MIP Research: Accelerated Constraint Handler Generation
LLM agents in a solver-aware harness recover global constraints from MIP formulations, generate executable propagation-only handlers for SCIP, and solve five additional MIPLIB 2017 instances.
-
ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling
ORPilot is the first agentic LLM system built specifically for production optimization modeling, using interview, data collection, parameter computation agents and a solver-agnostic intermediate representation to hand...
-
Graph-Grounded Optimization: Rao-Family Metaheuristics, Classical OR, and SLM-Driven Formulation over Knowledge Graphs
Graph-grounded optimization pulls problem elements from knowledge graphs via Cypher and shows that a portfolio of Rao-family metaheuristics outperforms single variants while OR-tools fails on non-linear objectives tha...
-
Graph-Grounded Optimization: Rao-Family Metaheuristics, Classical OR, and SLM-Driven Formulation over Knowledge Graphs
Graph-grounded optimization sources problem elements from knowledge graphs and shows Rao-family metaheuristics plus OR-tools perform differently across seven real-world KG-backed problems while surfacing data issues.
-
From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling
Agora-Opt uses decentralized debate among LLM agent teams plus a read-write memory bank to produce more accurate optimization models from text than prior LLM methods.
-
Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
EvoOR-Agent co-evolves agent architectures as AOE-style networks with graph-mediated recombination and knowledge-base-assisted mutation to outperform fixed LLM pipelines on OR benchmarks.
-
LLM Biases
Transformer attention in generative recommenders can create positional, popularity, latent-driver, and synthetic-data biases that concentrate exposure and reduce diversity.
-
Large Language Models for Operations Research: A Comprehensive Survey
A survey compiling roles, applications, benchmarks, challenges, and future directions for large language models in operations research.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.