ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research

TL;DR

ORMind is a novel cognitive-inspired framework that improves operations research problem-solving by transforming requirements into models and code, outperforming existing methods in key datasets.

Contribution

It introduces a new end-to-end reasoning framework inspired by human cognition, addressing deployment challenges of LLMs in operations research.

Findings

9.5% improvement on NL4Opt dataset

14.6% improvement on ComplexOR dataset

Enhanced optimization performance demonstrated

Abstract

Operations research (OR) is widely deployed to solve critical decision-making problems with complex objectives and constraints, impacting manufacturing, logistics, finance, and healthcare outcomes. While Large Language Models (LLMs) have shown promising results in various domains, their practical application in industry-relevant operations research (OR) problems presents significant challenges and opportunities. Preliminary industrial applications of LLMs for operations research face two critical deployment challenges: 1) Self-correction focuses on code syntax rather than mathematical accuracy, causing costly errors; 2) Complex expert selection creates unpredictable workflows that reduce transparency and increase maintenance costs, making them impractical for time-sensitive business applications. To address these business limitations, we introduce ORMind, a cognitive-inspired framework that enhances optimization through counterfactual reasoning. Our approach emulates human cognition, implementing an end-to-end workflow that systematically transforms requirements into mathematical models and executable solver code. It is currently being tested internally in Lenovo's AI Assistant, with plans to enhance optimization capabilities for both business and consumer customers. Experiments demonstrate that ORMind outperforms existing methods, achieving a 9.5\% improvement on the NL4Opt dataset and a 14.6\% improvement on the ComplexOR dataset.