Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language

2026-09-09

AI Summary

本文提出一种多代理框架，自动从自然语言问题描述生成QUBO公式，以解决手动转换耗时且需专业知识的问题。

Abstract

Quadratic Unconstrained Binary Optimization (QUBO) is a central formulation for combinatorial optimization and has gained increasing attention due to its compatibility with quantum, hybrid quantum-classical, and quantum-inspired solvers. However, translating natural-language problem descriptions into correct QUBO formulations remains difficult, requiring the identification of binary variables, constraints, objective functions, penalty terms, and suitable penalty weights. This process is time-consuming and often demands substantial domain expertise. To address this challenge, we propose an end-to-end multi-agent framework that automatically generates QUBO formulations from natural-language problem descriptions, supported by structured or unstructured test cases. To evaluate its performance, We also introduce QUBOBench, a benchmark containing 100 combinatorial optimization problems across 12 application domains, curated from peer-reviewed literature, competitions, and canonical NP-hard problems. Experimental results show that our framework achieves 68% accuracy on QUBOBench, outperforming a direct single-call baseline by 22%. Further analysis identifies iterative self-repair as the most important component contributing to improved performance. The data and code are open-sourced at https://quitttcat.github.io/QuantumQUBOAgent.

Problem

• QUBO
• natural language
• combinatorial optimization
• binary variables
• penalty terms

Innovation

• end-to-end multi-agent framework
• natural-language problem descriptions
• QUBO formulation generation
• iterative self-repair