aiqbench analysis
This research introduces a multi-agent framework capable of automatically translating natural language descriptions into QUBO formulations, addressing a significant bottleneck in preparing problems for quantum and hybrid solvers. By leveraging iterative self-repair mechanisms, the system achieves 68% accuracy on a new benchmark covering 12 domains, marking a substantial improvement over single-call baselines. The open-sourced code and dataset provide a critical resource for advancing automated workflows in combinatorial optimization and quantum computing applications.
Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language
arXiv:2609.10629v1 Announce Type: new 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.
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 this https URL.
Artificial Intelligence (cs.AI)
arXiv:2609.10629 [cs.AI]
(or arXiv:2609.10629v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.10629 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 254 words
Related coverage
Korea University Team Presents LLM-Qubo Framework for Multi-Drone Assignment Optimisation
Quantum Zeitgeist · Jun 17, 2026
JIJ and ORCA Computing Demonstrate Hybrid Quantum-Classical Energy Optimization
Quantum Computing Report · Jun 12, 2026
Mixed-Binary Quadratic Programming via QUBO Sampling without Continuous-Variable Binarization
arXiv · Jul 24, 2026
Superpixels Cut Quantum Image Segmentation Problems 33× Faster
Quantum Zeitgeist · Jul 31, 2026