Quantum State Preparation via Large-Language-Model-Driven Evolution

2025-05-09

AI Summary

Traditional variational quantum algorithms suffer from expert-dependent circuit design, poor scalability, and hardware incompatibility. This paper introduces the first large language model (LLM)-driven automated ansatz generation framework, integrating symbolic reasoning, evolutionary optimization, and zero-noise extrapolation to enable system-size-agnostic, scalable circuit construction—featuring a constant parameter count (e.g., only four parameters for nine qubits) and cross-scale energy extrapolation. Experimentally validated on the Zuchongzhi superconducting quantum processor, the framework achieves near-exact ground-state energy predictions for nine-qubit Ising and XY spin chains. For a 20-qubit system, it successfully suppresses two-qubit gate noise, markedly enhancing hardware efficiency and generalization capability. The approach bridges high-level algorithmic design with low-level hardware constraints, enabling robust, adaptive, and resource-efficient quantum circuit synthesis across problem scales.

Technology Category

• Machine Learning: Quantum Machine Learning
• Natural Language Processing: (Large) Language Models
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

We propose an automated framework for quantum circuit design by integrating large-language models (LLMs) with evolutionary optimization to overcome the rigidity, scalability limitations, and expert dependence of traditional ones in variational quantum algorithms. Our approach (FunSearch) autonomously discovers hardware-efficient ans""atze with new features of scalability and system-size-independent number of variational parameters entirely from scratch. Demonstrations on the Ising and XY spin chains with n = 9 qubits yield circuits containing 4 parameters, achieving near-exact energy extrapolation across system sizes. Implementations on quantum hardware (Zuchongzhi chip) validate practicality, where two-qubit quantum gate noises can be effectively mitigated via zero-noise extrapolations for a spin chain system as large as 20 sites. This framework bridges algorithmic design and experimental constraints, complementing contemporary quantum architecture search frameworks to advance scalable quantum simulations.

Problem

• Automating quantum circuit design using LLMs and evolution
• Overcoming rigidity and scalability in variational algorithms
• Enabling hardware-efficient ansatze for scalable quantum simulations

Innovation

• LLM-driven evolutionary optimization for quantum circuits
• Hardware-efficient ansatze with scalable parameters
• Noise mitigation via zero-noise extrapolation