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

Code Optimization in Quantum Compilation Using Large Language Models

Hamza Arab, Lotfi Djeghri

Published Jul 2, 2026• 0 citations
Publisher
DOI
10.13140/rg.2.2.12763.73764

Related papers

Qubrio: High-Performance Quantum Compilation via Multi-Agent LLM Collaboration

Jixuan Ruan, Zhuo Cui, Zhengding Hu +10 more

Large Language Models (LLMs) offer an adaptable alternative to traditional quantum compilation heuristics, which bottleneck progress by demanding costly manual redesigns whenever hardware evolves. However, naive single-pass LLM approaches fail under the unique challenges introduced by quantum compilation. We introduce Qubrio, a practical agentic framework that significantly reduces heuristic redesigns through a three-level decomposition. By (1) partitioning programs into sequential operation stages, (2) deploying specialized agents for placement, routing and optimization, and (3) using disaggregated feedback for precise error correction, our system reliably navigates complex physical constraints. Beyond serving as a direct compiler, our LLM framework also uncovers novel strategies that facilitate convoy-style shuttling, substantially enhancing hardware concurrency without sacrificing fidelity. We further integrate these strategies into the previous state-of-the-art (SOTA) compiler, recovering a significant fraction of the LLM's performance advantages. On realistic workloads, our compiler achieves significant improvements in hardware runtime and program fidelity over the SOTA baseline PowerMove, seamlessly adapting to new hardware capabilities. Qubrio features an open user interface for practical use, and its code is publicly available at https://github.com/crosaa/Qubrio.

quant-pharXiv:2611.02269•Nov 3, 2026•0 citations

Code Optimization for Quantum Computing

Thomas Häner

•Jan 1, 2018•0 citations

Quantum Transpiler Optimization: On the Development, Implementation, and Use of a Quantum Research Testbed

Brandon K. Kamaka

•Mar 26, 2020•1 citation

A Universal Quantum Compiler GPT: Multi-Framework Optimization and Translation Using Large Language Models

Somrak Petchartee

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.

International Computer Science and Engineering Conference•Nov 2, 2025•0 citations

QPipe: LLM-Based Agentic Quantum Application Generation for Test Optimization

Ming Tao, Yuechen Li, Tao Yue +2 more

Quantum computing is increasingly explored for software engineering (SE) optimization, but translating natural-language (NL) task-level requirements into executable quantum applications still demands substantial quantum and programming expertise. We present QPipe, a large language model (LLM)-based multi-agent architecture that autonomously turns NL requirements into traceable quantum-application workflows through specialized agents for requirement parsing, formulation, code generation, review, execution, and verification. We evaluate QPipe on 20 NL requirements, each associated with a real-world benchmark and a test-optimization problem. QPipe successfully completes the key stages of quantum-application generation across requirements, achieving average rates of 100% for code compilation and 96.7% for application execution and final-result combination, with average generation costs of 260.1 seconds and 1.89M tokens per requirement. Among the generated quantum applications that execute successfully, the returned solutions outperform the offline genetic algorithm baseline in most cases. Ablation results further show that QPipe's advantage depends on retaining code-generation skills, task knowledge, review feedback, and multi-agent decomposition. These results indicate that agentic coordination can support generation of executable quantum applications for tackling test optimization problems from real-world benchmarks.

cs.SECross-listedarXiv:2607.00939•Jul 2, 2026•3 citations

Circuit Partitioning Using Large Language Models for Quantum Compilation and Simulations

Sinha, Pranav, Sumit Kumar Jha, Sunny Raj

We are in the midst of the noisy intermediate-scale quantum (NISQ) era, where quantum computers are limited by noisy gates, some of which are more error-prone than others and can render the final computation incomprehensible. Quantum circuit compilation algorithms attempt to minimize these noisy gates when mapping quantum algorithms onto quantum hardware but face computational challenges that restrict their application to circuits with no more than 5-6 qubits, necessitating the need to partition large circuits before the application of noisy quantum gate minimization algorithms. The existing generation of these algorithms is heuristic in nature and does not account for downstream gate minimization tasks. Large language models (LLMs) have the potential to change this and help improve quantum circuit partitions. This paper investigates the use of LLMs, such as Llama and Mistral, for partitioning quantum circuits by capitalizing on their abilities to understand and generate code, including QASM. Specifically, we teach LLMs to partition circuits using the quick partition approach of the Berkeley Quantum Synthesis Toolkit. Through experimental evaluations, we show that careful fine-tuning of open source LLMs enables us to obtain an accuracy of 53.4% for the partition task while over-the-shelf LLMs are unable to correctly partition circuits, using standard 1-shot and few-shot training approaches.

arXiv:2505.07711•May 12, 2025•3 citations
Large Language Models (LLMs) offer an adaptable alternative to traditional quantum compilation heuristics, which bottleneck progress by demanding costly manual redesigns whenever hardware evolves. However, naive single-pass LLM approaches fail under the unique challenges introduced by quantum compilation. We introduce Qubrio, a practical agentic framework that significantly reduces heuristic redesigns through a three-level decomposition. By (1) partitioning programs into sequential operation stages, (2) deploying specialized agents for placement, routing and optimization, and (3) using disaggregated feedback for precise error correction, our system reliably navigates complex physical constraints. Beyond serving as a direct compiler, our LLM framework also uncovers novel strategies that facilitate convoy-style shuttling, substantially enhancing hardware concurrency without sacrificing fidelity. We further integrate these strategies into the previous state-of-the-art (SOTA) compiler, recovering a significant fraction of the LLM's performance advantages. On realistic workloads, our compiler achieves significant improvements in hardware runtime and program fidelity over the SOTA baseline PowerMove, seamlessly adapting to new hardware capabilities. Qubrio features an open user interface for practical use, and its code is publicly available at https://github.com/crosaa/Qubrio.
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.
Quantum computing is increasingly explored for software engineering (SE) optimization, but translating natural-language (NL) task-level requirements into executable quantum applications still demands substantial quantum and programming expertise. We present QPipe, a large language model (LLM)-based multi-agent architecture that autonomously turns NL requirements into traceable quantum-application workflows through specialized agents for requirement parsing, formulation, code generation, review, execution, and verification. We evaluate QPipe on 20 NL requirements, each associated with a real-world benchmark and a test-optimization problem. QPipe successfully completes the key stages of quantum-application generation across requirements, achieving average rates of 100% for code compilation and 96.7% for application execution and final-result combination, with average generation costs of 260.1 seconds and 1.89M tokens per requirement. Among the generated quantum applications that execute successfully, the returned solutions outperform the offline genetic algorithm baseline in most cases. Ablation results further show that QPipe's advantage depends on retaining code-generation skills, task knowledge, review feedback, and multi-agent decomposition. These results indicate that agentic coordination can support generation of executable quantum applications for tackling test optimization problems from real-world benchmarks.
We are in the midst of the noisy intermediate-scale quantum (NISQ) era, where quantum computers are limited by noisy gates, some of which are more error-prone than others and can render the final computation incomprehensible. Quantum circuit compilation algorithms attempt to minimize these noisy gates when mapping quantum algorithms onto quantum hardware but face computational challenges that restrict their application to circuits with no more than 5-6 qubits, necessitating the need to partition large circuits before the application of noisy quantum gate minimization algorithms. The existing generation of these algorithms is heuristic in nature and does not account for downstream gate minimization tasks. Large language models (LLMs) have the potential to change this and help improve quantum circuit partitions. This paper investigates the use of LLMs, such as Llama and Mistral, for partitioning quantum circuits by capitalizing on their abilities to understand and generate code, including QASM. Specifically, we teach LLMs to partition circuits using the quick partition approach of the Berkeley Quantum Synthesis Toolkit. Through experimental evaluations, we show that careful fine-tuning of open source LLMs enables us to obtain an accuracy of 53.4% for the partition task while over-the-shelf LLMs are unable to correctly partition circuits, using standard 1-shot and few-shot training approaches.