Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Generation of quantum low-code models

Stefan Bolz

Published Jan 1, 2026• 0 citations
Publisher

Abstract

Quantum computing is inherently complex, making the development of algorithms for quantum computing a challenging and error-prone process. Low-code platforms aim to simplify software development and improve accessibility for inexperienced developers by abstracting much of the complexity associated with traditional programming environments. This approach has recently been applied to the development of quantum algorithms, where quantum low-code modeling frameworks like Qonstruct can prevent users from making mistakes by representing quantum code as streamlined visual elements. However, low-code frameworks often still require some domain-specific expertise. In recent years, Large Language Models (LLMs) have rapidly gained widespread adoption as another way to facilitate and speed up software development. Because they can accept instructions in everyday natural language to generate functional code, very little technical experience is required to use them. Nevertheless, LLM-generated code often contains mistakes and requires further examination and testing, which can be challenging for inexperienced developers. In order to combine the benefits of both approaches, this master’s thesis develops an LLM-based low-code model generation feature in the quantum low-code modeler Qonstruct. The goal is to enable users to provide model specifications in natural language, which are then used to generate low-code quantum models. The proposed model generation pipeline tries to minimize mistakes made by the LLM by including structural and semantic validation steps and a follow-up question mechanism. In a user study the generation feature’s feasibility and performance are evaluated and compared with manual low-code modeling done by human subjects.

DOI
10.18419/opus-19650

Related papers

Qiskit Code Assistant: Training LLMs for generating Quantum Computing Code

Nicolas Dupuis, Luca Buratti, Sanjay Vishwakarma +5 more

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.

arXiv:2405.19495•IEEE LLM Aided Design Workshop (LAD)•Jun 28, 2024•42 citations

Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction

Charlie Campbell, Hao Chen, Wayne Luk +1 more

Multi-agent frameworks with Large Language Models (LLMs) have become promising tools for generating generalpurpose programming languages using test-driven development, allowing developers to create more accurate and robust code. However, their potential has not been fully unleashed for domainspecific programming languages, where specific domain exhibits unique optimization opportunities for customized improvement. In this paper, we take the first step in exploring multi-agent code generation for quantum programs. By identifying the unique optimizations in quantum designs such as quantum error correction, we introduce a novel multi-agent framework tailored to generating accurate, fault-tolerant quantum code. Each agent in the framework focuses on distinct optimizations, iteratively refining the code using a semantic analyzer with multi-pass inference, alongside an error correction code decoder. We also examine the effectiveness of traditional techniques, like Chain-ofThought (CoT) and Retrieval-Augmented Generation (RAG) in the context of quantum programming, uncovering observations that are different from general-purpose code generation. To evaluate our approach, we develop a test suite to measure the impact each optimization has on the accuracy of the generated code. Our findings indicate that techniques such as structured CoT significantly improve the generation of quantum algorithms by up to $50 \%$. In contrast, we have also found that certain techniques such as RAG show limited improvement, yielding an accuracy increase of only $4 \%$. Moreover, we showcase examples of AIassisted quantum error prediction and correction, demonstrating the effectiveness of our multi-agent framework in reducing the errors of generated quantum programs.

ACM/IEEE Design Automation Conference (DAC)•Jun 22, 2025•13 citations

Revisiting Quantum Code Generation: Where Should Domain Knowledge Live?

Oscar Novo, Oscar Bastidas-Jossa, Alberto Calvo +2 more

Recent advances in large language models (LLMs) have enabled the automation of an increasing number of programming tasks, including code generation for scientific and engineering domains. In rapidly evolving software ecosystems such as quantum software development, where frameworks expose complex abstractions, a central question is how best to incorporate domain knowledge into LLM-based assistants while preserving maintainability as libraries evolve. In this work, we study specialization strategies for Qiskit code generation using the Qiskit-HumanEval benchmark. We compare a parameter-specialized fine-tuned baseline introduced in prior work against a range of recent general-purpose LLMs enhanced with retrieval-augmented generation (RAG) and agent-based inference with execution feedback. Our results show that modern general-purpose LLMs consistently outperform the parameter-specialized baseline. While the fine-tuned model achieves approximately 47% pass@1 on Qiskit-HumanEval, recent general-purpose models reach 60-65% under zero-shot and retrieval-augmented settings, and up to 85% for the strongest evaluated model when combined with iterative execution-feedback agents -representing an improvement of more than 20% over zero-shot general-purpose performance and more than 35% over the parameter-specialized baseline. Agentic execution feedback yields the most consistent improvements, albeit at increased runtime cost, while RAG provides modest and model-dependent gains. These findings indicate that performance gains can be achieved without domain-specific fine-tuning, instead relying on inference-time augmentation, thereby enabling a more flexible and maintainable approach to LLM-assisted quantum software development.

cs.LGCross-listedarXiv:2603.22184•Mar 24, 2026•1 citation

Benchmarking the Benchmarks for Quantum Code Generation with LLMs

Yunhe Feng, Xiaokun Yang, Kewei Sha +1 more

Large Language Models (LLMs) are increasingly deployed as quantum coding copilots, assisting researchers by generating complex programs for frameworks such as Qiskit, PennyLane, and OpenQASM. However, accurately evaluating the practical utility of these models remains a significant challenge. Existing benchmarks are highly fragmented, ranging from syntax-centric unit tests to simulator- and hardware-aware metrics, making results difficult to compare across different languages and hardware targets. To address this fragmentation, this paper systematically reviews recent evaluation suites and post-training methodologies for quantum code generation. We distill current evaluation criteria into four practical dimensions: syntax and API validity, semantic and physical correctness, resource and hardware feasibility, and execution-based feedback. Building upon these dimensions, we present a unified taxonomy that maps current benchmarks to emerging model adaptation techniques, specifically retrieval-augmented generation (RAG), fine-tuning, multi-agent workflows, and reinforcement learning (RL). Our analysis highlights a clear shift: moving away from prompt-only baselines and toward agentic workflows driven by quantum-verifiable rewards. This shift directly targets the semantic gap between superficially compilable code and physically executable quantum programs. In addition, we identify key research opportunities-such as standardized semantic metrics and integration with quantum error correction-aimed at fostering a more reproducible, verifiable, and hardware-grounded ecosystem for automated quantum software development.

IEEE Dallas Circuits and Systems Conference (DCAS)•Apr 10, 2026•0 citations

Large Language Models for Quantum Software Engineering: Opportunities and Challenges in Modeling, Generation, Testing, and Repair

Jiaming Ye, Qiang Hu, Fuyuan Zhang +5 more

Large Language Models (LLMs) have already reshaped many aspects of traditional software engineering, from code generation and debugging to automated testing and maintenance. As an important research sub-domain in the software engineering area, quantum software engineering (QSE) is poised to undergo a similar transformation. As QSE moves toward broader adoption, including the generation of quantum code, program testing, and automated program repair, LLMs will likely play a key supporting role in its development. However, despite encouraging early attempts, the community still lacks a roadmap for using LLMs in QSE. Without such a roadmap, opportunities may be missed, challenges may remain unrevealed, and risks may be overlooked. In this article, we present our vision for how LLMs can advance QSE, focusing on four core tasks: program modeling and analysis, program generation, testing, and repair. We outline the opportunities and unique challenges, identify the risks inherent in this integration, and propose a research agenda to guide the community toward realizing the full potential of LLM-powered QSE.

ACM Transactions on Software Engineering and Methodology•Jul 15, 2026•1 citation

LLM-Powered Quantum Code Transpilation

Nazanin Siavash, Armin Moin

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, generalpurpose transpilation in the quantum computing ecosystem.

arXiv:2507.12480•IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•2 citations
Quantum computing is inherently complex, making the development of algorithms for quantum computing a challenging and error-prone process. Low-code platforms aim to simplify software development and improve accessibility for inexperienced developers by abstracting much of the complexity associated with traditional programming environments. This approach has recently been applied to the development of quantum algorithms, where quantum low-code modeling frameworks like Qonstruct can prevent users from making mistakes by representing quantum code as streamlined visual elements. However, low-code frameworks often still require some domain-specific expertise. In recent years, Large Language Models (LLMs) have rapidly gained widespread adoption as another way to facilitate and speed up software development. Because they can accept instructions in everyday natural language to generate functional code, very little technical experience is required to use them. Nevertheless, LLM-generated code often contains mistakes and requires further examination and testing, which can be challenging for inexperienced developers. In order to combine the benefits of both approaches, this master’s thesis develops an LLM-based low-code model generation feature in the quantum low-code modeler Qonstruct. The goal is to enable users to provide model specifications in natural language, which are then used to generate low-code quantum models. The proposed model generation pipeline tries to minimize mistakes made by the LLM by including structural and semantic validation steps and a follow-up question mechanism. In a user study the generation feature’s feasibility and performance are evaluated and compared with manual low-code modeling done by human subjects.
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.
Multi-agent frameworks with Large Language Models (LLMs) have become promising tools for generating generalpurpose programming languages using test-driven development, allowing developers to create more accurate and robust code. However, their potential has not been fully unleashed for domainspecific programming languages, where specific domain exhibits unique optimization opportunities for customized improvement. In this paper, we take the first step in exploring multi-agent code generation for quantum programs. By identifying the unique optimizations in quantum designs such as quantum error correction, we introduce a novel multi-agent framework tailored to generating accurate, fault-tolerant quantum code. Each agent in the framework focuses on distinct optimizations, iteratively refining the code using a semantic analyzer with multi-pass inference, alongside an error correction code decoder. We also examine the effectiveness of traditional techniques, like Chain-ofThought (CoT) and Retrieval-Augmented Generation (RAG) in the context of quantum programming, uncovering observations that are different from general-purpose code generation. To evaluate our approach, we develop a test suite to measure the impact each optimization has on the accuracy of the generated code. Our findings indicate that techniques such as structured CoT significantly improve the generation of quantum algorithms by up to 50%50 \%50%. In contrast, we have also found that certain techniques such as RAG show limited improvement, yielding an accuracy increase of only 4%4 \%4%. Moreover, we showcase examples of AIassisted quantum error prediction and correction, demonstrating the effectiveness of our multi-agent framework in reducing the errors of generated quantum programs.
Recent advances in large language models (LLMs) have enabled the automation of an increasing number of programming tasks, including code generation for scientific and engineering domains. In rapidly evolving software ecosystems such as quantum software development, where frameworks expose complex abstractions, a central question is how best to incorporate domain knowledge into LLM-based assistants while preserving maintainability as libraries evolve. In this work, we study specialization strategies for Qiskit code generation using the Qiskit-HumanEval benchmark. We compare a parameter-specialized fine-tuned baseline introduced in prior work against a range of recent general-purpose LLMs enhanced with retrieval-augmented generation (RAG) and agent-based inference with execution feedback. Our results show that modern general-purpose LLMs consistently outperform the parameter-specialized baseline. While the fine-tuned model achieves approximately 47% pass@1 on Qiskit-HumanEval, recent general-purpose models reach 60-65% under zero-shot and retrieval-augmented settings, and up to 85% for the strongest evaluated model when combined with iterative execution-feedback agents -representing an improvement of more than 20% over zero-shot general-purpose performance and more than 35% over the parameter-specialized baseline. Agentic execution feedback yields the most consistent improvements, albeit at increased runtime cost, while RAG provides modest and model-dependent gains. These findings indicate that performance gains can be achieved without domain-specific fine-tuning, instead relying on inference-time augmentation, thereby enabling a more flexible and maintainable approach to LLM-assisted quantum software development.
Large Language Models (LLMs) are increasingly deployed as quantum coding copilots, assisting researchers by generating complex programs for frameworks such as Qiskit, PennyLane, and OpenQASM. However, accurately evaluating the practical utility of these models remains a significant challenge. Existing benchmarks are highly fragmented, ranging from syntax-centric unit tests to simulator- and hardware-aware metrics, making results difficult to compare across different languages and hardware targets. To address this fragmentation, this paper systematically reviews recent evaluation suites and post-training methodologies for quantum code generation. We distill current evaluation criteria into four practical dimensions: syntax and API validity, semantic and physical correctness, resource and hardware feasibility, and execution-based feedback. Building upon these dimensions, we present a unified taxonomy that maps current benchmarks to emerging model adaptation techniques, specifically retrieval-augmented generation (RAG), fine-tuning, multi-agent workflows, and reinforcement learning (RL). Our analysis highlights a clear shift: moving away from prompt-only baselines and toward agentic workflows driven by quantum-verifiable rewards. This shift directly targets the semantic gap between superficially compilable code and physically executable quantum programs. In addition, we identify key research opportunities-such as standardized semantic metrics and integration with quantum error correction-aimed at fostering a more reproducible, verifiable, and hardware-grounded ecosystem for automated quantum software development.
Large Language Models (LLMs) have already reshaped many aspects of traditional software engineering, from code generation and debugging to automated testing and maintenance. As an important research sub-domain in the software engineering area, quantum software engineering (QSE) is poised to undergo a similar transformation. As QSE moves toward broader adoption, including the generation of quantum code, program testing, and automated program repair, LLMs will likely play a key supporting role in its development. However, despite encouraging early attempts, the community still lacks a roadmap for using LLMs in QSE. Without such a roadmap, opportunities may be missed, challenges may remain unrevealed, and risks may be overlooked. In this article, we present our vision for how LLMs can advance QSE, focusing on four core tasks: program modeling and analysis, program generation, testing, and repair. We outline the opportunities and unique challenges, identify the risks inherent in this integration, and propose a research agenda to guide the community toward realizing the full potential of LLM-powered QSE.
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, generalpurpose transpilation in the quantum computing ecosystem.