发表机构
Bangladesh University of Engineering and Technology; Qatar Computing Research Institute, HBKU（孟加拉国工程技术大学; 卡塔尔计算研究所，哈马德·本·哈利法大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出一个端到端多智能体框架，从自然语言自动生成QUBO公式，并引入含100个问题的QUBOBench基准，实验显示准确率达68%，较基线提升22%。
AI 中文摘要
二次无约束二元优化（QUBO）是组合优化的核心公式，因其与量子、混合量子经典及量子启发求解器的兼容性而受到越来越多的关注。然而，将自然语言问题描述转化为正确的QUBO公式仍然困难，需要识别二元变量、约束、目标函数、惩罚项以及合适的惩罚权重。这一过程耗时且通常需要大量的领域专业知识。为应对这一挑战，我们提出了一种端到端的多智能体框架，能够从自然语言问题描述中自动生成QUBO公式，并辅以结构化或非结构化的测试用例。为评估其性能，我们还引入了QUBOBench，一个包含100个组合优化问题的基准，涵盖12个应用领域，这些数据来自同行评审文献、竞赛和经典的NP难问题。实验结果表明，我们的框架在QUBOBench上达到了68%的准确率，比直接单次调用基线高出22%。进一步分析表明，迭代自我修复是提升性能的最重要组成部分。数据和代码已在以下网址开源：此https URL。
英文摘要
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.
CommentsAccepted at the ICML 2026 Workshop on AI as a Tool for Mathematics, Computer Science, and Machine Learning (AI4Research)
