多智能体框架从自然语言自动生成QUBO公式
原标题：Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language
AI 摘要
研究者提出一个端到端多智能体框架，可从自然语言问题描述自动生成 QUBO（二次无约束二值优化）公式，并支持结构化或非结构化测试用例。团队同时发布 QUBOBench 基准，涵盖 12 个应用领域的 100 个组合优化问题。实验显示该框架在 QUBOBench 上达到 68% 准确率，比直接单次调用基线（46%）高出 22 个百分点，其中迭代自修复被识别为提升性能的最关键组件。数据与代码已开源。
正文节选
QuantumQUBO Agent: Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language 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 iden