LLM-Powered Quantum Code Transpilation

2025-07-12

AI Summary

The quantum software development kit (QSDK) ecosystem—comprising heterogeneous frameworks such as Qiskit, Cirq, and PennyLane—suffers from poor cross-platform interoperability. Conventional rule-based transpilers exhibit high maintenance overhead and limited generalizability. Method: We propose the first programming-language-agnostic, large language model (LLM)-based quantum code translation framework. It eliminates hand-crafted rules by leveraging pre-trained quantum-domain knowledge and contextual reasoning capabilities of LLMs to achieve functionally equivalent SDK-to-SDK translation. Contribution/Results: Experiments demonstrate high translation accuracy across multiple QSDKs, substantially reducing maintenance costs while exhibiting strong generalization and scalability. Our framework establishes an intelligent, automated interoperability infrastructure for hybrid quantum-classical software systems, advancing the quantum software ecosystem toward automation and intelligence.

Technology Category

• Machine Learning: Quantum Machine Learning
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• 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

Abstract

There exist various Software Development Kits (SDKs) tailored to different quantum computing platforms. These are known as Quantum SDKs (QSDKs). Examples include but are not limited to Qiskit, Cirq, and PennyLane. However, this diversity presents significant challenges for interoperability and cross-platform development of hybrid quantum-classical software systems. Traditional rule-based transpilers for translating code between QSDKs are time-consuming to design and maintain, requiring deep expertise and rigid mappings in the source and destination code. In this study, we explore the use of Large Language Models (LLMs) as a flexible and automated solution. Leveraging their pretrained knowledge and contextual reasoning capabilities, we position LLMs as programming language-agnostic transpilers capable of converting quantum programs from one QSDK to another while preserving functional equivalence. Our approach eliminates the need for manually defined transformation rules and offers a scalable solution to quantum software portability. This work represents a step toward enabling intelligent, general-purpose transpilation in the quantum computing ecosystem.

Problem

• Diverse QSDKs hinder quantum software interoperability
• Rule-based transpilers require manual expertise and rigid mappings
• LLMs enable automated, scalable quantum code translation

Innovation

• LLMs automate quantum code transpilation between QSDKs
• Eliminates manual rule-based transformation for portability
• Uses pretrained models for language-agnostic SDK conversion