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

arXiv:2609.05039

Qlippy: A Retrieval-Augmented GenAI Assistant for Reproducible Quantum Workflows and Experiment Tracking

Mahee Gamage, Vlad Stirbu

quant-phcs.AISubmitted Sep 4, 2026• Announced Sep 7, 2026• 0 citations
arXivHTMLPDF

Abstract

Quantum software development is iterative and error-prone. Noisy hardware and repeated re-execution make experiment tracking, provenance, and reproducibility essential, yet these practices are hard to adopt because of tooling complexity and the specialized knowledge they demand. General-purpose language models can help but tend to hallucinate and lack grounding in domain-specific tooling. We present Qlippy, a retrieval-augmented GenAI assistant embedded in the development environment that grounds its responses in a curated corpus of quantum-software-engineering knowledge. Qlippy explains reproducibility and provenance concepts in context and augments existing Qiskit programs with MLflow-based experiment tracking aligned to the QProv schema. By separating knowledge from model parameters, grounding gives explicit control over the scope and provenance of the assistant's responses and reduces reliance on model scale, which points toward low-cost, privacy-preserving local deployment.

Comments
Accepted for publication in the QGenAI Workshop at IEEE QCE 2026

Related papers

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

QiboAgent: a practitioner's guideline to open source assistants for Quantum Computing code development

Lorenzo Esposito, Andrea Papaluca, Stefano Carrazza

Abstract We introduce QiboAgent, a reference implementation designed to serve as a practitioner’s guideline for developing specialized coding assistants in Quantum Computing middleware. Addressing the limitations in scientific software development of general-purpose proprietary models, we explore how lightweight, open-source Large Language Models (LLMs) provided with a custom workflow architecture compare. In detail, we experiment with two complementary paradigms: a Retrieval-Augmented Generation pipeline for high-precision information retrieval, and an autonomous agentic workflow for complex software engineering tasks. We observe that this hybrid approach significantly reduces hallucination rates in code generation compared to a proprietary baseline, achieving a peak accuracy of 90.2% with relatively small open-source models of size up to 30B parameters. Furthermore, the agentic framework exhibits advanced coding capabilities, automating the resolution of maintenance issues and new features requests, or by prototyping larger-scale refactors of the codebase, such as producing a compiled Rust module with bindings of an original pure python package, Qibo in our case. The LLM workflows used for our analysis are integrated into a user interface and a Model Context Protocol server, providing an accessible tool for Qibo developers. Source code and deployment instructions are publicly available at https://github.com/qiboteam/qiboagent.

•Aug 11, 2026•0 citations

QiboAgent: a practitioner's guideline to open source assistants for Quantum Computing code development

Lorenzo Esposito, Andrea Papaluca, Stefano Carrazza

We introduce QiboAgent, a reference implementation designed to serve as a practitioner's guideline for developing specialized coding assistants in Quantum Computing middleware. Addressing the limitations in scientific software development of general-purpose proprietary models, we explore how lightweight, open-source Large Language Models (LLMs) provided with a custom workflow architecture compare. In detail, we experiment with two complementary paradigms: a Retrieval-Augmented Generation pipeline for high-precision information retrieval, and an autonomous agentic workflow for complex software engineering tasks. We observe that this hybrid approach significantly reduces hallucination rates in code generation compared to a proprietary baseline, achieving a peak accuracy of 90.2% with relatively small open-source models of size up to 30B parameters. Furthermore, the agentic framework exhibits advanced coding capabilities, automating the resolution of maintenance issues and new features requests, or by prototyping larger-scale refactors of the codebase, such as producing a compiled Rust module with bindings of an original pure python package, Qibo in our case. The LLM workflows used for our analysis are integrated into a user interface and a Model Context Protocol server, providing an accessible tool for Qibo developers.

quant-pharXiv:2603.15538•Mar 17, 2026•0 citations

Toolchain for Experiment Tracking in Iterative Quantum Software Development

Otso Kinanen, Mahee Gamage, Vlad Stirbu

As quantum software engineering (QSE) matures, practitioners are adopting classical software engineering practices. This paper proposes a quantum experiment tracking infrastructure that aids quantum researchers in making informed decisions while developing quantum software incrementally and iteratively. By leveraging tools and best practices from classical machine learning communities, we provide a mature environment for quantum software practitioners to enhance their practices. Our approach involves collecting a comprehensive quantum provenance dataset from each experiment execution for analysis and decision-making. To validate our approach, we developed an experimental environment where a program was iteratively developed on quantum simulators and an IQM computer, and we demonstrate how the development workflow backed by the tracking infrastructure meets expectations for quantum experiment reporting.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•0 citations

Qiskit Code Migration with LLMs

Jose Manuel Suarez, Luís Mariano Bibbó, Joaquín Bogado +1 more

The rapid evolution of Quantum Development Kits (QDKs) introduces a specific form of technical debt that compromises code maintainability and hinders software reuse. In the specialized domain of Quantum Software Engineering (QSE), this challenge is intensified by the scarcity of high-quality training data and the high volatility of emerging frameworks, which often lead general-purpose Large Language Models (LLMs) to produce unreliable or hallucinated results. This paper proposes a hybrid approach integrating LLMs with Retrieval-Augmented Generation (RAG) to automate the migration of Qiskit code across versions. The proposed methodology enhances the precision and reliability of migration suggestions by leveraging an automatically generated taxonomy of migration scenarios as the structured, version-specific knowledge source to guide the models. The approach is implemented through an automated, extensible workflow evaluating LLMs (Google Gemini Flash-2.5 and OpenAI Gpt-oss-20b) under different retrieval schemes (unconstrained and restrictive). Results demonstrate that the taxonomy-based RAG architecture, particularly under the restrictive scheme, significantly reduces hallucinations and improves descriptive quality, with Google Gemini Flash-2.5 showing superior performance in detecting complex refactoring scenarios. These findings confirm the potential of this data-centric methodology to foster technological independence and provide robust, intelligent assistants that mitigate API obsolescence, ensuring the long-term availability of quantum algorithms within a rapidly shifting ecosystem and flattening the learning curve within Quantum Software Engineering (QSE).

arXiv:2606.20173•JAIIO, Jornadas Argentinas de Informática•Jun 18, 2026•1 citation

Quantum-Rag: Retrieval-Augmented Generation Framework for Quantum Circuit Code Generation

Nicholas Stapleton, Sharmin Afrose, Ethan Seefried +3 more

Generating correct and executable quantum circuit code remains a significant barrier for both newcomers and experienced practitioners in quantum computing. While Large Language Models (LLMs) have shown promise in classical code generation, their application to quantum programming is hampered by limited domain-specific training data and the rapidly evolving nature of quantum software frameworks. In this work, we present Quantum-RAG, an extended Retrieval-Augmented Generation framework that couples a domain-specialized language model with a curated, multi-source knowledge corpus to produce Qiskit-based quantum circuit code. Our three-stage pipeline ingests documentation, educational notebooks, and research literature into a dense retrieval index and augments the generation model with the most relevant context at inference time. Evaluated on the Qiskit HumanEval benchmark, QuantumRAG achieves a Pass@1 of 0.4132, a Pass@3 of 0.6291, and a Pass@5 of 0.7020, surpassing the domain-adapted GraniteQiskit baseline by 101%, 72%, and 47 % at each respective threshold. These results demonstrate that retrieval-augmented approaches can substantially improve quantum code generation without expensive model retraining.

IEEE Dallas Circuits and Systems Conference (DCAS)•Apr 10, 2026•2 citations
Quantum software development is iterative and error-prone. Noisy hardware and repeated re-execution make experiment tracking, provenance, and reproducibility essential, yet these practices are hard to adopt because of tooling complexity and the specialized knowledge they demand. General-purpose language models can help but tend to hallucinate and lack grounding in domain-specific tooling. We present Qlippy, a retrieval-augmented GenAI assistant embedded in the development environment that grounds its responses in a curated corpus of quantum-software-engineering knowledge. Qlippy explains reproducibility and provenance concepts in context and augments existing Qiskit programs with MLflow-based experiment tracking aligned to the QProv schema. By separating knowledge from model parameters, grounding gives explicit control over the scope and provenance of the assistant's responses and reduces reliance on model scale, which points toward low-cost, privacy-preserving local deployment.
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.
Abstract We introduce QiboAgent, a reference implementation designed to serve as a practitioner’s guideline for developing specialized coding assistants in Quantum Computing middleware. Addressing the limitations in scientific software development of general-purpose proprietary models, we explore how lightweight, open-source Large Language Models (LLMs) provided with a custom workflow architecture compare. In detail, we experiment with two complementary paradigms: a Retrieval-Augmented Generation pipeline for high-precision information retrieval, and an autonomous agentic workflow for complex software engineering tasks. We observe that this hybrid approach significantly reduces hallucination rates in code generation compared to a proprietary baseline, achieving a peak accuracy of 90.2% with relatively small open-source models of size up to 30B parameters. Furthermore, the agentic framework exhibits advanced coding capabilities, automating the resolution of maintenance issues and new features requests, or by prototyping larger-scale refactors of the codebase, such as producing a compiled Rust module with bindings of an original pure python package, Qibo in our case. The LLM workflows used for our analysis are integrated into a user interface and a Model Context Protocol server, providing an accessible tool for Qibo developers. Source code and deployment instructions are publicly available at https://github.com/qiboteam/qiboagent.
We introduce QiboAgent, a reference implementation designed to serve as a practitioner's guideline for developing specialized coding assistants in Quantum Computing middleware. Addressing the limitations in scientific software development of general-purpose proprietary models, we explore how lightweight, open-source Large Language Models (LLMs) provided with a custom workflow architecture compare. In detail, we experiment with two complementary paradigms: a Retrieval-Augmented Generation pipeline for high-precision information retrieval, and an autonomous agentic workflow for complex software engineering tasks. We observe that this hybrid approach significantly reduces hallucination rates in code generation compared to a proprietary baseline, achieving a peak accuracy of 90.2% with relatively small open-source models of size up to 30B parameters. Furthermore, the agentic framework exhibits advanced coding capabilities, automating the resolution of maintenance issues and new features requests, or by prototyping larger-scale refactors of the codebase, such as producing a compiled Rust module with bindings of an original pure python package, Qibo in our case. The LLM workflows used for our analysis are integrated into a user interface and a Model Context Protocol server, providing an accessible tool for Qibo developers.
As quantum software engineering (QSE) matures, practitioners are adopting classical software engineering practices. This paper proposes a quantum experiment tracking infrastructure that aids quantum researchers in making informed decisions while developing quantum software incrementally and iteratively. By leveraging tools and best practices from classical machine learning communities, we provide a mature environment for quantum software practitioners to enhance their practices. Our approach involves collecting a comprehensive quantum provenance dataset from each experiment execution for analysis and decision-making. To validate our approach, we developed an experimental environment where a program was iteratively developed on quantum simulators and an IQM computer, and we demonstrate how the development workflow backed by the tracking infrastructure meets expectations for quantum experiment reporting.
The rapid evolution of Quantum Development Kits (QDKs) introduces a specific form of technical debt that compromises code maintainability and hinders software reuse. In the specialized domain of Quantum Software Engineering (QSE), this challenge is intensified by the scarcity of high-quality training data and the high volatility of emerging frameworks, which often lead general-purpose Large Language Models (LLMs) to produce unreliable or hallucinated results. This paper proposes a hybrid approach integrating LLMs with Retrieval-Augmented Generation (RAG) to automate the migration of Qiskit code across versions. The proposed methodology enhances the precision and reliability of migration suggestions by leveraging an automatically generated taxonomy of migration scenarios as the structured, version-specific knowledge source to guide the models. The approach is implemented through an automated, extensible workflow evaluating LLMs (Google Gemini Flash-2.5 and OpenAI Gpt-oss-20b) under different retrieval schemes (unconstrained and restrictive). Results demonstrate that the taxonomy-based RAG architecture, particularly under the restrictive scheme, significantly reduces hallucinations and improves descriptive quality, with Google Gemini Flash-2.5 showing superior performance in detecting complex refactoring scenarios. These findings confirm the potential of this data-centric methodology to foster technological independence and provide robust, intelligent assistants that mitigate API obsolescence, ensuring the long-term availability of quantum algorithms within a rapidly shifting ecosystem and flattening the learning curve within Quantum Software Engineering (QSE).
Generating correct and executable quantum circuit code remains a significant barrier for both newcomers and experienced practitioners in quantum computing. While Large Language Models (LLMs) have shown promise in classical code generation, their application to quantum programming is hampered by limited domain-specific training data and the rapidly evolving nature of quantum software frameworks. In this work, we present Quantum-RAG, an extended Retrieval-Augmented Generation framework that couples a domain-specialized language model with a curated, multi-source knowledge corpus to produce Qiskit-based quantum circuit code. Our three-stage pipeline ingests documentation, educational notebooks, and research literature into a dense retrieval index and augments the generation model with the most relevant context at inference time. Evaluated on the Qiskit HumanEval benchmark, QuantumRAG achieves a Pass@1 of 0.4132, a Pass@3 of 0.6291, and a Pass@5 of 0.7020, surpassing the domain-adapted GraniteQiskit baseline by 101%, 72%, and 47 % at each respective threshold. These results demonstrate that retrieval-augmented approaches can substantially improve quantum code generation without expensive model retraining.