We present the first universal quantum compiler based on Generative Pre-trained Transformer (GPT) architecture that provides cross-framework optimization and translation capabilities for quantum circuits. Our Quantum Compiler GPT (QC-GPT) unifies four major quantum computing frameworks—Qiskit Terra, Cirq, tket and PyQuil— into a single Al-driven compilation system. The model demonstrates significant improvements in circuit optimization, achieving 23-47% reduction in gate count, 18-35% reduction in circuit depth, and 12-28% improvement in estimated fidelity compared to existing compilers. QC-GPT also enables seamless translation between quantum frameworks with 96.3% accuracy while providing human-readable explanations for optimization decisions. Our approach leverages a quantum-aware transformer architecture with 512M parameters, trained on 104,000 circuit optimization examples across all supported frameworks. This work represents the first successful application of large language models to universal quantum compilation, opening new possibilities for Al-assisted quantum software development.
We present the first universal quantum compiler based on Generative Pre-trained Transformer (GPT) architecture that provides cross-framework optimization and translation capabilities for quantum circuits. Our Quantum Compiler GPT (QC-GPT) unifies four major quantum computing frameworks—Qiskit Terra, Cirq, tket and PyQuil— into a single Al-driven compilation system. The model demonstrates significant improvements in circuit optimization, achieving 23-47% reduction in gate count, 18-35% reduction in circuit depth, and 12-28% improvement in estimated fidelity compared to existing compilers. QC-GPT also enables seamless translation between quantum frameworks with 96.3% accuracy while providing human-readable explanations for optimization decisions. Our approach leverages a quantum-aware transformer architecture with 512M parameters, trained on 104,000 circuit optimization examples across all supported frameworks. This work represents the first successful application of large language models to universal quantum compilation, opening new possibilities for Al-assisted quantum software development.
Large Language Models (LLMs) such as ChatGPT have transformed how we interact with and understand the capabilities of Artificial Intelligence (AI). However, the intersection of LLMs with the burgeoning field of Quantum Machine Learning (QML) is only in its nascent stages. This paper presents an exploration of this niche by detailing a comprehensive framework for implementing the foundational Transformer architecture -- integral to ChatGPT -- within a quantum computing paradigm. We meticulously design quantum circuits that implement adapted versions of the transformer's core components and the generative pre-training phase. By integrating quantum computing with LLMs, we aspire to open new avenues for research in QML and contribute to the ongoing evolution of AI technologies.
The recent times of fast development of quantum computers has been followed by many researchers who want to run the larger and more difficult quantum algorithms on it and they have promised such speedup several times. Notwithstanding this, commercial quantum computers are currently fraught with instability and errors. This paper is centered on development of the customized compiler for quantum computing with aid of Qiskit Terra, a QIS framework. We target central classes such as circuit representation structures, programming techniques based on OpenQASM, challenges in the QC architecture, high-level routing optimization, and the structure of the Qiskit Terra compiler. In every circuit, the optimization is provided by methods of Qiskit Terra, including Trivial Layout, Noise Adaptive Layout, Dense Layout, and Custom Layout. These optimization levels address many problems that emerge when circuits are being compiled and executed, and thus, the optimization levels seek to boost circuit efficiency, reduce the count of gates, and enhance the overall performance. The introduction of numerous optimization passes starting from unroller passes that translate gates, the layout passes that map virtual to physical qubits, and the optimization algorithm aimed at the runtime reduction. Modern quantum compilation technologies are being currently developed based on economic (and theoretical) analyses to underpin the investigation and development of optimal quantum computation procedures.
Quantum programming languages and their compilers form the critical software layer between abstract quantum algorithm specifications and physical hardware execution -- yet compiler quality varies enormously across the quantum software ecosystem, with suboptimal compilation directly increasing circuit depth, gate count, and consequently error rates on NISQ hardware. This paper proposes the Quantum Compiler Design and Evaluation (QCDE) framework, a systematic methodology for quantum compiler optimisation across four compilation stages: gate synthesis (decomposing abstract gates to hardware-native gate sets), routing (mapping virtual qubits to physical qubits under connectivity constraints), scheduling (ordering gates to minimise decoherence), and cross-layer optimisation (combining all stages with error mitigation awareness). QCDE evaluates six quantum compilers (Qiskit transpiler L1-L3, TKET, BQSKit, Cirq, Quilc, and a novel QCDE-Opt compiler) on 48 benchmark circuits from the QOAS, HQCAD, and QNNDE algorithm ecosystems. QCDE-Opt achieves 18.4% lower CX gate count vs. Qiskit L3 (best existing compiler) through a novel error-aware peephole optimisation pass. BQSKit provides the best synthesis quality at 28.4% CX reduction but 12.4x compilation overhead. TKET achieves the best balance of quality and speed (8.4% CX reduction, 1.8x overhead). QCDE provides a compiler selection guide and the QCDE-Opt compiler as an open-source contribution.
Large Language Models (LLMs) contribute significantly to the development of conversational AI and has great potentials to assist the scientific research in various areas. This paper attempts to address the following questions: What opportunities do the current generation of generative pre-trained transformers (GPTs) offer for the developments of noisy intermediate-scale quantum (NISQ) technologies? Additionally, what potentials does the forthcoming generation of GPTs possess to push the frontier of research in fault-tolerant quantum computing (FTQC)? In this paper, we implement a QGAS model, which can rapidly propose promising ansatz architectures and evaluate them with application benchmarks including quantum chemistry and quantum finance tasks. Our results demonstrate that after a limited number of prompt guidelines and iterations, we can obtain a high-performance ansatz which is able to produce comparable results that are achieved by state-of-the-art quantum architecture search methods. This study provides a simple overview of GPT's capabilities in supporting quantum computing research while highlighting the limitations of the current GPT at the same time. Additionally, we discuss futuristic applications for LLM in quantum research.
Quantum computing holds transformative potential, but its adoption is hindered by the complexity of generating efficient, hardware-specific code. This work presents a modular, extensible compiler framework that bridges high-level quantum languages with diverse hardware architectures. The framework consists of three modules: a front-end for parsing quantum code into a hardware-agnostic intermediate representation (IR), an optimization module for enhancing quantum circuits through gate synthesis, qubit routing, and error mitigation, and a back-end for generating hardware-specific instructions. Major contributions include a hardware-agnostic IR for cross-platform compatibility, optimization techniques to reduce gate complexity and noise, and hardware-specific adaptations to improve execution fidelity. A practical demonstration optimizes quantum circuits, highlighting the impact of hardware constraints. Comparative analysis of IBM Quantum and IonQ platforms underscores the role of qubit connectivity and noise resilience in algorithmic performance. This scalable framework enhances quantum software development and efficient hardware utilization.
Abstract: The evolution of quantum computing depends not only on advancements in hardware but also on breakthroughs in compiler design that can translate high-level quantum algorithms into efficient, executable circuits. This research introduces a novel approach to quantum compiler design that leverages AI guidance in tandem with superalgebraic symmetries to optimize gate synthesis, resource usage, and noise resilience. By embedding superalgebraic representations—mathematical structures that unify bosonic and fermionic transformations—into the compilation pipeline, and training AI models to recognize optimal symmetry-preserving transformations, we construct a quantum compiler that is adaptive, structure-aware, and scalable. This framework enhances circuit depth minimization, gate reduction, and fidelity preservation in real-time quantum compilation workflows. Keywords: Quantum Compiler, Superalgebras, Artificial Intelligence, Gate Optimization, Quantum Circuits, Symmetry-Preserving Transformations, Qubit Mapping, Quantum Machine Learning