Large language models (LLMs) promise transformative change to fields as diverse as medical diagnosis, legal services, and software development. One reason for such an impact is LLMs’ ability to make highly technical endeavors more accessible to a broader audience. Accessibility has long been a goal for the growing fields of quantum computing, informatics, and engineering, especially as more quantum systems become publicly available via cloud interfaces. Between programming quantum computers and using LLMs, the latter seems the more accessible task: while leveraging an LLM’s fullest potential requires experience with prompt engineering, any literate person can provide queries and read responses. By contrast, designing and executing quantum programs—outside of those available online—requires significant background knowledge, from selection of operations for algorithm implementation to configuration choices for particular hardware specifications and providers. Current research is exploring LLM utility for classical software development, but there has been relatively little investigation into the same for quantum programming. Consequently, this work is a first look at how well an uncustomized, publicly available LLM can write straightforward quantum circuits. We examine how well OpenAI’s ChatGPT (GPT-4) can write quantum circuits for two hardware providers: the superconducting qubit machines of IBM and the photonic devices of Xanadu. We find that ChatGPT currently fares substantially better with the former.
Large language models (LLMs) promise transformative change to fields as diverse as medical diagnosis, legal services, and software development. One reason for such an impact is LLMs’ ability to make highly technical endeavors more accessible to a broader audience. Accessibility has long been a goal for the growing fields of quantum computing, informatics, and engineering, especially as more quantum systems become publicly available via cloud interfaces. Between programming quantum computers and using LLMs, the latter seems the more accessible task: while leveraging an LLM’s fullest potential requires experience with prompt engineering, any literate person can provide queries and read responses. By contrast, designing and executing quantum programs—outside of those available online—requires significant background knowledge, from selection of operations for algorithm implementation to configuration choices for particular hardware specifications and providers. Current research is exploring LLM utility for classical software development, but there has been relatively little investigation into the same for quantum programming. Consequently, this work is a first look at how well an uncustomized, publicly available LLM can write straightforward quantum circuits. We examine how well OpenAI’s ChatGPT (GPT-4) can write quantum circuits for two hardware providers: the superconducting qubit machines of IBM and the photonic devices of Xanadu. We find that ChatGPT currently fares substantially better with the former.
Quantum computers promise massive computational speedup for problems in many critical domains, such as physics, chemistry, cryptanalysis, healthcare, etc. However, despite decades of research, they remain far from entering an era of utility. The lack of mature software, architecture, and systems solutions capable of translating quantum-mechanical properties of algorithms into physical state transformations on qubit devices remains a key factor underlying the slow pace of technological progress. The problem worsens due to significant reliance on domain-specific expertise, especially for software developers, computer architects, and systems engineers. To address these limitations and accelerate large-scale high-performance quantum system design, we ask:
Can large language models (LLMs) help with solving quantum software, architecture, and systems problems?
In this work, we present a case study assessing the performance of LLMs on quantum system reasoning tasks. We evaluate nine frontier LLMs and compare their performance to graduate UT Austin students on a set of quantum computing problems. Finally, we recommend several directions along which research and engineering development efforts must be pursued.
Abstract Quantum computing is an exciting non-Von Neu-mann paradigm, offering provable speedups over classical computing for specific problems. However, the practical limits of classical simulatability for quantum circuits remain unclear, especially with current noisy quantum devices. In this work, we explore the potential of leveraging Large Language Models (LLMs) to simulate the output of a quantum Turing machine using Grover’s quantum circuits, known to provide quadratic speedups over classical counterparts. To this end, we developed GroverGPT, a specialized model based on LLaMA’s 8-billion-parameter architecture, trained on over 15 trillion tokens. Unlike brute-force state-vector simulations, which demand substantial computational resources, GroverGPT employs pattern recognition to approximate quantum search algorithms without explicitly representing quantum states. Analyzing 97K quantum search instances, GroverGPT consistently outperformed OpenAI’s GPT-4o (45% accuracy), achieving nearly 100% accuracy on 6-and 10-qubit datasets when trained on 4-qubit or larger datasets. It also demonstrated strong generalization, surpassing 95% accuracy for systems with over 20 qubits when trained on 3-to 6-qubit data. Analysis indicates GroverGPT captures quantum features of Grover’s search rather than classical patterns, supported by novel prompting strategies to enhance performance. Although accuracy declines with increasing system size, these findings offer insights into the practical boundaries of classical simulatability. This work suggests task-specific LLMs can surpass general-purpose models like GPT-4o in quantum algorithm learning and serve as powerful tools for advancing quantum research.
Code Large Language Models (Code LLMs) have emerged as powerful tools, revolutionizing the software development landscape by automating the coding process and reducing time and effort required to build applications. This paper focuses on training Code LLMs to specialize in the field of quantum computing. We begin by discussing the unique needs of quantum computing programming, which differ significantly from classical programming approaches or languages. A Code LLM specializing in quantum computing requires a foundational understanding of quantum computing and quantum information theory. However, the scarcity of available quantum code examples and the rapidly evolving field, which necessitates continuous dataset updates, present significant challenges. Moreover, we discuss our work on training Code LLMs to produce high-quality quantum code using the Qiskit library. This work includes an examination of the various aspects of the LLMs used for training and the specific training conditions, as well as the results obtained with our current models. To evaluate our models, we have developed a custom benchmark, similar to HumanEval, which includes a set of tests specifically designed for the field of quantum computing programming using Qiskit. Our findings indicate that our model outperforms existing state-of-the-art models in quantum computing tasks. We also provide examples of code suggestions, comparing our model to other relevant code LLMs. Finally, we introduce a discussion on the potential benefits of Code LLMs for quantum computing computational scientists, researchers, and practitioners. We also explore various features and future work that could be relevant in this context.
Abstract Quantum computing is steadily transitioning from theoretical exploration to experimental deployment, bringing with it distinct engineering challenges. This shift has led to the emergence of Quantum Software Engineering (QSE), a research area that adapts and extends software engineering principles to the quantum domain. In parallel, Large Language Models (LLMs) have become widely adopted in classical software development workflows. Although their potential to assist QSE tasks is increasingly discussed, existing evidence remains fragmented across research venues and practitioner sources. This study presents a Multivocal Literature Review that systematically synthesizes peer-reviewed and grey literature to characterize how LLMs are used in QSE and assess their reported limitations. We identified and analyzed 24 primary sources, mapped their contributions onto the quantum software development lifecycle, examined the distribution of adopted LLM families, and synthesized recurring limitations. The results show that LLM adoption in QSE is predominantly code-centric, with most studies focusing on program synthesis, repair, and refactoring, while lifecycle phases such as requirements engineering, architectural reasoning, and comprehensive validation receive limited attention. Reported challenges include semantic inaccuracies, execution failures on real quantum backends, sensitivity to prompt formulation, and limited domain coverage. Moreover, the empirical landscape is largely shaped by proprietary models, raising concerns regarding reproducibility and longitudinal comparability. Overall, current evidence suggests that LLMs function primarily as assistive tools for bounded tasks rather than as robust, lifecycle-spanning engineering agents in quantum software development.
Large language models (LLMs) have increasingly been applied to automatic programming code generation. This task can be viewed as a language generation task that bridges natural language, human knowledge, and programming logic. However, it remains underexplored in domains that require interaction with hardware devices, such as quantum programming, where human coders write Python code that is executed on a quantum computer. To address this gap, we introduce QCoder Benchmark, an evaluation framework that assesses LLMs on quantum programming with feedback from simulated hardware devices. Our benchmark offers two key features. First, it supports evaluation using a quantum simulator environment beyond conventional Python execution, allowing feedback of domain-specific metrics such as circuit depth, execution time, and error classification, which can be used to guide better generation. Second, it incorporates human-written code submissions collected from real programming contests, enabling both quantitative comparisons and qualitative analyses of LLM outputs against human-written codes. Our experiments reveal that even advanced models like GPT-4o achieve only around 18.97% accuracy, highlighting the difficulty of the benchmark. In contrast, reasoning-based models such as o3 reach up to 78% accuracy, outperforming averaged success rates of human-written codes (39.98%). We release the QCoder Benchmark dataset and public evaluation API to support further research. (Codes and datasets are available at https://qcoder-bench.github.io/ )
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.