Optimality-Preserving Decomposition for Scalable QAOA in Natural-Language-Guided Multi-Drone Assignment

2026-06-12

AI Summary

This work addresses the NP-hard problem of large-scale multi-UAV task allocation, which remains challenging for existing methods to solve efficiently, particularly due to the difficulty of mapping natural language instructions to constrained quantum hardware. The authors propose an end-to-end framework wherein a front-end module leverages supervised fine-tuning and direct preference optimization to translate natural language commands into structured QUBO constraints. The back-end integrates a constraint-preserving graph partitioner with a delimiter-based dynamic programming compression mechanism, combined with W-state initialization and an XY mixer to enable scalable CVaR-QAOA optimization on near-term quantum devices. Under an ideal oracle, the approach recovers the global optimum with 100% success; in realistic QAOA sampling, it achieves a 96.3% success rate, marking the first demonstration of natural-language-guided task allocation at previously intractable scales.

Abstract

As multi-drone fleets scale, zone assignment rapidly evolves into an intractable NP-hard combinatorial problem that overwhelms classical exhaustive search. While quantum optimization promises to shatter these classical bottlenecks, mapping complex spatial tasks from human intent to restricted quantum hardware remains a severe challenge. To bridge this gap, we present an end-to-end framework integrating a fine-tuned Large Language Model (LLM) front-end with a highly scalable, domain-specific quantum-classical backend. The front-end utilizes Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to translate free-form natural language instructions into structurally robust Quadratic Unconstrained Binary Optimization (QUBO) constraints without false negatives. To overcome the strict qubit limits of near-term quantum devices, our framework features a novel constraint-preserving graph partitioner and a compressed separator-based dynamic programming (DP) merge. By structurally encoding constraints via W-state initialization and XY-mixers in Conditional Value-at-Risk Quantum Approximate Optimization (CVaR-QAOA), the pipeline stays highly compact. Empirical results demonstrate that this architecture circumvents classical scaling walls, recovering the global optimum on 100% of idealized oracle cases and 96.3% under real QAOA sampling, enabling natural-language-guided task allocation at previously intractable scales.

Problem

• multi-drone assignment
• NP-hard combinatorial optimization
• natural-language guidance
• quantum hardware constraints
• scalable task allocation

Innovation

• QAOA
• Natural Language to QUBO
• Constraint-Preserving Graph Partitioning
• CVaR-QAOA
• Scalable Quantum Optimization