AI-assisted Distributed Quantum Approximate Optimization Algorithm for Solving Ising Models

Solving Ising models remains computationally difficult due to the exponential growth of the solution space. Quantum algorithms such as the Quantum Approximate Optimization Algorithm (QAOA) offer a promising pathway to address this challenge, though their scalability is still limited by current quantum computing system constraints (e.g., qubit counts, coherence time, and gate fidelity). In this work, we present a Distributed QAOA (DQAOA) framework enhanced with Generative Pre-trained Transformers (GPT), which integrates quantum computing, high-performance computing, and artificial intelligence. The proposed DQAOA-GPT approach efficiently distributed heavy computational workloads across quantum-classical resources while leveraging GPT to generate optimized quantum circuits. We demonstrate that this framework enables efficient solution for Ising models and paves the way for tackling more complex problems.