# LLM-QUBO: An End-to-End Framework for Automated QUBO Transformation from Natural Language Problem Descriptions

## TL;DR

This paper introduces LLM-QUBO, an automated end-to-end framework that transforms natural language problem descriptions into QUBO formulations using large language models and hybrid quantum-classical methods, enabling scalable quantum optimization.

## Contribution

The paper presents a novel framework combining LLMs and hybrid decomposition techniques to automate and scale the translation of natural language problems into QUBO formats for quantum optimization.

## Key findings

- Successfully automates QUBO generation from natural language.
- Demonstrates scalability with classical solvers.
- Validates correctness and readiness for quantum hardware.

## Abstract

Quantum annealing offers a promising paradigm for solving NP-hard combinatorial optimization problems, but its practical application is severely hindered by two challenges: the complex, manual process of translating problem descriptions into the requisite Quadratic Unconstrained Binary Optimization (QUBO) format and the scalability limitations of current quantum hardware. To address these obstacles, we propose a novel end-to-end framework, LLM-QUBO, that automates this entire formulation-to-solution pipeline. Our system leverages a Large Language Model (LLM) to parse natural language, automatically generating a structured mathematical representation. To overcome hardware limitations, we integrate a hybrid quantum-classical Benders' decomposition method. This approach partitions the problem, compiling the combinatorial complex master problem into a compact QUBO format, while delegating linearly structured sub-problems to classical solvers. The correctness of the generated QUBO and the scalability of the hybrid approach are validated using classical solvers, establishing a robust performance baseline and demonstrating the framework's readiness for quantum hardware. Our primary contribution is a synergistic computing paradigm that bridges classical AI and quantum computing, addressing key challenges in the practical application of optimization problem. This automated workflow significantly reduces the barrier to entry, providing a viable pathway to transform quantum devices into accessible accelerators for large-scale, real-world optimization challenges.