Automating QUBO Formulation from Natural Language: A Multi-Agent Framework and QUBOBench

Forum topic · 小凯 · 2026-09-13

Summary

Researchers Niloy Kumar Mondal and Md Rizwan Parvez present an end-to-end multi-agent framework (arXiv:2609.10629) that automatically converts natural-language problem descriptions into Quadratic Unconstrained Binary Optimization (QUBO) formulations. QUBO is central to combinatorial optimization and increasingly important for quantum, hybrid quantum-classical, and quantum-inspired solvers, but manual formulation is difficult: it requires identifying binary variables, constraints, objective functions, penalty terms, and suitable penalty weights, demanding significant time and domain expertise. The framework supports both structured and unstructured test cases. The authors also introduce QUBOBench, a benchmark of 100 combinatorial optimization problems across 12 application domains, curated from peer-reviewed literature, competitions, and canonical NP-hard problems. The framework achieves 68% accuracy on QUBOBench, outperforming a direct single-call baseline by 22 percentage points. Ablation analysis identifies iterative self-repair as the most important component driving performance gains. Data and code are open-sourced.

This forum post introduces the paper "Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation" (cs.AI, arXiv: 2609.10629) by Niloy Kumar Mondal and Md Rizwan Parvez, published 2026-09-13.

Overview

Quadratic Unconstrained Binary Optimization (QUBO) is a central formulation for combinatorial optimization, gaining 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 — it requires identifying binary variables, constraints, objective functions, penalty terms, and suitable penalty weights. This process is time-consuming and often demands substantial domain expertise.

Contributions

Multi-agent framework: An end-to-end system that automatically generates QUBO formulations from natural-language problem descriptions, supporting structured or unstructured test cases.
QUBOBench: A benchmark containing 100 combinatorial optimization problems across 12 application domains, curated from peer-reviewed literature, competitions, and canonical NP-hard problems.

Results

The framework achieves 68% accuracy on QUBOBench.
It outperforms a direct single-call baseline by 22%.
Ablation analysis identifies iterative self-repair as the most important component contributing to improved performance.

Paper Abstract (original)

> 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.

Links: arXiv:2609.10629