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:2602.03466

Quantum Circuit Generation via test-time learning with large language models

Adriano Macarone-Palmieri, Rosario Lo Franco

quant-phstat.MLSubmitted Feb 3, 2026• Announced Feb 4, 2026• 5 citations• Revised Jul 7, 2026 (v5)
v1 · Feb 3, 2026v2 · Feb 5, 2026v3 · Feb 6, 2026v4 · Feb 12, 2026v5 · Jul 7, 2026
arXivHTMLPDF

Abstract

Deploying large language models (LLMs) as optimizers for black-box scientific design problems requires efficient test-time refinement under expensive evaluations and without training data. We propose a \emph{memory-augmented test-time optimization} framework that combines episodic memory of high-scoring candidates, score-difference feedback, and restart-from-best sampling to improve iterative search. We evaluate the approach on quantum circuit synthesis, where the objective is to maximize the Meyer--Wallach (MW) global entanglement measure under an exponentially expensive black-box oracle. On 20-qubit circuits, the framework achieves $Q(ψ)=0.99$ without feedback. On the more challenging 25-qubit task, feedback and restart mechanisms enable multiple runs to reach $Q(ψ)=1.0$ within 45 oracle calls, while a budget-matched random hill-climbing baseline stalls below $Q(ψ)\approx0.29$. These results demonstrate that memory and evaluator feedback substantially improve the sample efficiency of LLM-based black-box optimization and establish quantum circuit synthesis as a challenging benchmark for test-time optimization.

Comments
9 pages, 1 figure

Related papers

An LLM System for Autonomous Variational Quantum Circuit Design

Kenya Sakka, Wataru Mizukami, Kosuke Mitarai

The design of high performing quantum circuits remains largely dependent on human expertise. We introduce an autonomous agentic framework that employs large language models (LLMs) to conduct iterative quantum circuit designs under explicit design constraints. Our system integrates seven components: Exploration, Generation, Discussion, Validation, Storage, Evaluation, and Review. These components form a closed-loop workflow that combines web-based knowledge acquisition, literature-grounded critique, executable code generation, and experimental feedback. We evaluate the framework on two tasks: quantum feature map construction for quantum machine learning and ansatz generation for variational quantum eigensolver applications in quantum chemistry. In image classification benchmarks, the best generated feature map outperforms representative quantum feature maps and, when scaled to larger qubit counts, surpasses the classical radial basis function kernel. In molecular ground state estimation across seven molecules, the generated ansatz attains competitive accuracy with widely used chemically inspired and hardware-efficient constructions while satisfying the imposed scaling constraints. These results establish LLM driven agentic system as a viable paradigm for automated quantum circuit design and illustrate how AI systems can participate in iterative scientific optimization workflows across scientific domains.

quant-pharXiv:2606.13380•Jun 12, 2026•6 citations

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL

Cong Yu, Valter Uotila, S. Deng +5 more

Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic solution. However, the fundamental challenges remain unaddressed: (i) parameterized quantum gates require precise numerical values for optimal performance, which also depend on multiple aspects, including the number of quantum gates, their parameters, and the layout/depth of the circuits. (ii) LLMs often generate low-quality or incorrect quantum circuits due to the lack of quantum domain-specific knowledge. We propose QUASAR, an agentic reinforcement learning (RL) framework for quantum circuits generation and optimization based on tool-augmented LLMs. To align the LLM with quantum-specific knowledge and improve the generated quantum circuits, QUASAR designs (i) a quantum circuit verification approach with external quantum simulators and (ii) a sophisticated hierarchical reward mechanism in RL training. Extensive evaluation shows improvements in both syntax and semantic performance of the generated quantum circuits. When augmenting a 4B LLM, QUASAR has achieved the validity of 99.31% in Pass@1 and 100% in Pass@10, outperforming industrial LLMs of GPT-4o, GPT-5 and DeepSeek-V3 and several supervised-fine-tuning (SFT)-only and RL-only baselines.

arXiv:2510.00967•Oct 1, 2025•14 citations

RubriQ: Rubric-Guided Group Relative Policy Optimization for Constraint-Aware Quantum Circuit Synthesis

Ziqing Guo, Ziwen Pan

Designing fault-tolerant quantum circuits that are both algorithmically correct and hardware compatible remains a major bottleneck in the transition to scalable quantum computing. We introduce RubriQ, a scalable framework that formulates circuit synthesis as a large language model (LLM) code-generation task, optimized via group relative policy optimization (GRPO). Unlike conventional black-box neural critics, RubriQ employs a domain-grounded programmatic rubric as the reinforcement learning reward function, evaluating circuits for T-gate reduction, hardware topology compliance, and unitary fidelity. To support high-throughput training, RubriQ integrates GPU-accelerated CUDA-Q simulation directly into the reinforcement learning (RL) loop and is deployed on NERSC Perlmutter using DeepSpeed ZeRO2 across multinode NVIDIA A100 clusters. On benchmark tasks, RubriQ achieves a mean T-gate compression of 3.31x, significantly outperforming sparse-reward RL baselines (2.05x), converging 2-3x faster, and maintaining less than 1\% hardware-constraint violations. Validated on IBM and IonQ quantum processors, RubriQ establishes an automated, high-performance computing (HPC)-driven pipeline for generating hardware-ready, fault-tolerant quantum circuits at scale.

quant-pharXiv:2607.07554•Jul 9, 2026•0 citations

Agent-Q: Fine-Tuning Large Language Models for Quantum Circuit Generation and Optimization

Linus Jern, Valter Uotila, Cong Yu +1 more

Large language models (LLMs) have achieved remarkable outcomes in complex problems, including math, coding, and analyzing large amounts of scientific reports. Yet, few works have explored the potential of LLMs in quantum computing. The most challenging problem is to leverage LLMs to automatically generate quantum circuits at a large scale. Fundamentally, the existing pre-trained LLMs lack the knowledge of quantum circuits. In this paper, we address this challenge by fine-tuning LLMs and injecting the domain-specific knowledge of quantum computing. We describe Agent-Q, an LLM fine-tuning system to generate and optimize quantum circuits. In particular, agentQ implements the mechanisms to generate training data sets and constructs an end-to-end pipeline to fine-tune pre-trained LLMs to generate parameterized quantum circuits for various optimization problems. Agent-Q provides$\mathbf{1 4, 0 0 0}$quantum circuits covering a large spectrum of the quantum optimization landscape: 12 optimization problem instances and their optimized QAOA, VQE, and adaptive VQE circuits. Based thereon, Agent-Q fine-tunes LLMs and constructs syntactically correct parametrized quantum circuits in OpenQASM 3.0. We have evaluated the quality of the LLM-generated circuits and parameters by comparing them to the optimized expectation values and distributions. Experimental results show superior performance of Agent-Q, compared to several state-of-the-art LLMs and better parameters than random. Agent-Q can be integrated into an agentic workflow, and the generated parametrized circuits with initial parameters can be used as a starting point for further optimization, e.g., as templates in quantum machine learning and as benchmarks for compilers and hardware.

arXiv:2504.11109•IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•20 citations

Beyond Reinforcement Learning: Fast and Scalable Quantum Circuit Synthesis

Lukas Theißinger, Thore Gerlach, David Berghaus +1 more

Quantum unitary synthesis addresses the problem of translating abstract quantum algorithms into sequences of hardware-executable quantum gates. Solving this task exactly is infeasible in general due to the exponential growth of the underlying combinatorial search space. Existing approaches suffer from misaligned optimization objectives, substantial training costs and limited generalization across different qubit counts. We mitigate these limitations by using supervised learning to approximate the minimum description length of residual unitaries and combining this estimate with stochastic beam search to identify near optimal gate sequences. Our method relies on a lightweight model with zero-shot generalization, substantially reducing training overhead compared to prior baselines. Across multiple benchmarks, we achieve faster wall-clock synthesis times while exceeding state-of-the-art methods in terms of success rate for complex circuits.

quant-pharXiv:2602.15146•Feb 18, 2026•3 citations

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
Deploying large language models (LLMs) as optimizers for black-box scientific design problems requires efficient test-time refinement under expensive evaluations and without training data. We propose a \emph{memory-augmented test-time optimization} framework that combines episodic memory of high-scoring candidates, score-difference feedback, and restart-from-best sampling to improve iterative search. We evaluate the approach on quantum circuit synthesis, where the objective is to maximize the Meyer--Wallach (MW) global entanglement measure under an exponentially expensive black-box oracle. On 20-qubit circuits, the framework achieves Q(ψ)=0.99Q(ψ)=0.99Q(ψ)=0.99 without feedback. On the more challenging 25-qubit task, feedback and restart mechanisms enable multiple runs to reach Q(ψ)=1.0Q(ψ)=1.0Q(ψ)=1.0 within 45 oracle calls, while a budget-matched random hill-climbing baseline stalls below Q(ψ)≈0.29Q(ψ)\approx0.29Q(ψ)≈0.29. These results demonstrate that memory and evaluator feedback substantially improve the sample efficiency of LLM-based black-box optimization and establish quantum circuit synthesis as a challenging benchmark for test-time optimization.
The design of high performing quantum circuits remains largely dependent on human expertise. We introduce an autonomous agentic framework that employs large language models (LLMs) to conduct iterative quantum circuit designs under explicit design constraints. Our system integrates seven components: Exploration, Generation, Discussion, Validation, Storage, Evaluation, and Review. These components form a closed-loop workflow that combines web-based knowledge acquisition, literature-grounded critique, executable code generation, and experimental feedback. We evaluate the framework on two tasks: quantum feature map construction for quantum machine learning and ansatz generation for variational quantum eigensolver applications in quantum chemistry. In image classification benchmarks, the best generated feature map outperforms representative quantum feature maps and, when scaled to larger qubit counts, surpasses the classical radial basis function kernel. In molecular ground state estimation across seven molecules, the generated ansatz attains competitive accuracy with widely used chemically inspired and hardware-efficient constructions while satisfying the imposed scaling constraints. These results establish LLM driven agentic system as a viable paradigm for automated quantum circuit design and illustrate how AI systems can participate in iterative scientific optimization workflows across scientific domains.
Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic solution. However, the fundamental challenges remain unaddressed: (i) parameterized quantum gates require precise numerical values for optimal performance, which also depend on multiple aspects, including the number of quantum gates, their parameters, and the layout/depth of the circuits. (ii) LLMs often generate low-quality or incorrect quantum circuits due to the lack of quantum domain-specific knowledge. We propose QUASAR, an agentic reinforcement learning (RL) framework for quantum circuits generation and optimization based on tool-augmented LLMs. To align the LLM with quantum-specific knowledge and improve the generated quantum circuits, QUASAR designs (i) a quantum circuit verification approach with external quantum simulators and (ii) a sophisticated hierarchical reward mechanism in RL training. Extensive evaluation shows improvements in both syntax and semantic performance of the generated quantum circuits. When augmenting a 4B LLM, QUASAR has achieved the validity of 99.31% in Pass@1 and 100% in Pass@10, outperforming industrial LLMs of GPT-4o, GPT-5 and DeepSeek-V3 and several supervised-fine-tuning (SFT)-only and RL-only baselines.
Designing fault-tolerant quantum circuits that are both algorithmically correct and hardware compatible remains a major bottleneck in the transition to scalable quantum computing. We introduce RubriQ, a scalable framework that formulates circuit synthesis as a large language model (LLM) code-generation task, optimized via group relative policy optimization (GRPO). Unlike conventional black-box neural critics, RubriQ employs a domain-grounded programmatic rubric as the reinforcement learning reward function, evaluating circuits for T-gate reduction, hardware topology compliance, and unitary fidelity. To support high-throughput training, RubriQ integrates GPU-accelerated CUDA-Q simulation directly into the reinforcement learning (RL) loop and is deployed on NERSC Perlmutter using DeepSpeed ZeRO2 across multinode NVIDIA A100 clusters. On benchmark tasks, RubriQ achieves a mean T-gate compression of 3.31x, significantly outperforming sparse-reward RL baselines (2.05x), converging 2-3x faster, and maintaining less than 1\% hardware-constraint violations. Validated on IBM and IonQ quantum processors, RubriQ establishes an automated, high-performance computing (HPC)-driven pipeline for generating hardware-ready, fault-tolerant quantum circuits at scale.
Large language models (LLMs) have achieved remarkable outcomes in complex problems, including math, coding, and analyzing large amounts of scientific reports. Yet, few works have explored the potential of LLMs in quantum computing. The most challenging problem is to leverage LLMs to automatically generate quantum circuits at a large scale. Fundamentally, the existing pre-trained LLMs lack the knowledge of quantum circuits. In this paper, we address this challenge by fine-tuning LLMs and injecting the domain-specific knowledge of quantum computing. We describe Agent-Q, an LLM fine-tuning system to generate and optimize quantum circuits. In particular, agentQ implements the mechanisms to generate training data sets and constructs an end-to-end pipeline to fine-tune pre-trained LLMs to generate parameterized quantum circuits for various optimization problems. Agent-Q provides14,000\mathbf{1 4, 0 0 0}14,000quantum circuits covering a large spectrum of the quantum optimization landscape: 12 optimization problem instances and their optimized QAOA, VQE, and adaptive VQE circuits. Based thereon, Agent-Q fine-tunes LLMs and constructs syntactically correct parametrized quantum circuits in OpenQASM 3.0. We have evaluated the quality of the LLM-generated circuits and parameters by comparing them to the optimized expectation values and distributions. Experimental results show superior performance of Agent-Q, compared to several state-of-the-art LLMs and better parameters than random. Agent-Q can be integrated into an agentic workflow, and the generated parametrized circuits with initial parameters can be used as a starting point for further optimization, e.g., as templates in quantum machine learning and as benchmarks for compilers and hardware.
Quantum unitary synthesis addresses the problem of translating abstract quantum algorithms into sequences of hardware-executable quantum gates. Solving this task exactly is infeasible in general due to the exponential growth of the underlying combinatorial search space. Existing approaches suffer from misaligned optimization objectives, substantial training costs and limited generalization across different qubit counts. We mitigate these limitations by using supervised learning to approximate the minimum description length of residual unitaries and combining this estimate with stochastic beam search to identify near optimal gate sequences. Our method relies on a lightweight model with zero-shot generalization, substantially reducing training overhead compared to prior baselines. Across multiple benchmarks, we achieve faster wall-clock synthesis times while exceeding state-of-the-art methods in terms of success rate for complex circuits.
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.