Hybrid Quantum-AI Architectures for Intelligent Decision Systems

Abstract

Intelligent decision systems -- AI architectures that synthesise multi-source information to produce actionable decisions in complex environments -- increasingly encounter problem structures where quantum computational resources could provide meaningful advantage: high-dimensional state spaces, combinatorial action selection, uncertainty quantification under exponential hypothesis spaces, and real-time optimisation under resource constraints. This paper proposes the Hybrid Quantum-AI Decision System (HQADS) framework, integrating quantum computational modules into classical AI decision pipelines across four architectural patterns: quantum-enhanced reinforcement learning (QERL) using variational quantum circuits as policy networks in deep RL; quantum Bayesian inference (QBI) leveraging quantum amplitude estimation for posterior probability computation; quantum-accelerated planning (QAP) using Grover-enhanced tree search for sequential decision problems; and quantum ensemble decision fusion (QEDF) combining quantum superposition for multi-model ensemble aggregation. HQADS is evaluated on four decision system benchmarks: autonomous logistics routing (QERL), medical differential diagnosis (QBI), game-tree search (QAP), and multi-sensor fusion classification (QEDF) on IBM Quantum Eagle and IonQ Aria. QERL achieves 18.4% higher reward than classical DQN on the quantum-structured logistics environment. QBI reduces posterior computation time by 6.4x vs. classical MCMC at equal accuracy. QAP achieves 4.8x speedup for depth-12 game-tree search. QEDF improves multi-sensor classification AUC by 3.8pp vs. classical ensemble. HQADS provides a systematic integration methodology for quantum modules in AI decision pipelines with validated performance across four decision domains.