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:2607.10057

Quantum Circuit Vision: Cost-Aware Evaluation of Visual AI Agents for Quantum Code Generation

Dongping Liu, Aoyu Zhang, Luyao Zhang

quant-phcs.AIcs.CVcs.LGSubmitted Jul 11, 2026• Announced Jul 14, 2026• 0 citations
arXivHTMLPDF

Abstract

Can AI agents visually comprehend quantum circuit diagrams and generate verified executable code--and at what cost? We present Quantum Circuit Vision, a cost-aware evaluation framework for multimodal AI agents on quantum circuit visual understanding. We construct a 132-circuit benchmark spanning 13 categories ($1$--$10$ qubits) with executable Amazon Braket code and unitary-fidelity verification. Evaluating three frontier Claude-family models at different capability-cost tiers with $n=5$ repeated trials, we find that the mid-tier model (Sonnet 4.6, $1.30\times$ credits) offers the most favorable balance on the cost-accuracy frontier: 91% pass rate on the core subset at 18% of the per-call cost of the strongest model (Opus 4.6), whose accuracy advantage is not statistically significant (paired $t$: $p=0.083$). Logistic regression confirms that circuit depth--not qubit count--is the primary predictor of failure ($p<0.001$). Chain-of-thought prompting shows no statistically significant effect (all $p>0.18$, $n=5$), suggesting that visual pattern recognition outweighs explicit reasoning strategy for structurally coupled diagrams. We propose a cascade routing strategy (cheap $\rightarrow$ expensive models) that achieves 84% accuracy at 38% of single-model cost, demonstrating that model routing dominates prompt engineering as a cost lever. We release QCV-Dataset (132 circuits, 5 modalities, 1,931 files) on Hugging Face Hub as an open evaluation infrastructure with structured metadata for discoverability, interoperability, and responsible AI documentation, and all evaluation code, cost logs, and verification scripts on GitHub for full reproducibility.

Related papers

Generative AI for Quantum Circuits and Quantum Code: A Technical Review and Taxonomy

Juhani Merilehto

We review thirteen generative systems and five supporting datasets for quantum circuit and quantum code generation, identified through a structured scoping review of Hugging Face, arXiv, and provenance tracing (January-February 2026). We organize the field along two axes: artifact type (Qiskit code, OpenQASM programs, circuit graphs); crossed with training regime (supervised fine-tuning, verifier-in-the-loop RL, diffusion/graph generation, agentic optimization); and systematically apply a three-layer evaluation framework covering syntactic validity, semantic correctness, and hardware executability. The central finding is that while all reviewed systems address syntax and most address semantics to some degree, none reports end-to-end evaluation on quantum hardware (Layer 3b), leaving a significant gap between generated circuits and practical deployment. Scope note: quantum code refers throughout to quantum program artifacts (QASM, Qiskit); we do not cover generation of quantum error-correcting codes (QEC).

arXiv:2603.16216•Mar 17, 2026•0 citations

Quantum Circuit Learning: HCI-Driven Visualization and Agentic AI Assistance for Software Engineers

Ahmed Bhouri

Although most software engineering work today targets classical systems, quantum computing has become an area of growing interest for developers who want to understand alternative computational models. This thesis addresses the difficulty of learning to construct and reason about quantum circuits by focusing on small, illustrative circuit-based algorithms (Bell states, GHZ states, and a reduced Grover’s search) as structured examples around which an interactive learning platform is built. The aim is to support step-by-step understanding of these circuits while investigating how large language models (LLMs) can assist with circuit generation and explanation. The work presents a web-based platform that allows users to incrementally build circuits, visualize their layer-by-layer evolution, and inspect key properties such as gate composition and measurement probabilities. On top of this platform, two LLM-based assistance strategies are implemented: a stateless baseline that operates solely on naturallanguage prompts, and a context-aware, agentic mode that receives structured information about the current circuit and simulation results. Their behavior is compared in an offline evaluation on a fixed set of exemplar tasks, using a rubric that scores correctness of the resulting circuits, relevance of explanations to the actual circuit, and pedagogical clarity. The results indicate that the agentic, state-aware integration produces more accurate, better-grounded, and more instructionally useful outputs than the stateless baseline on the examined tasks. The thesis contributes an example-driven approach to quantum computing education for software engineers, an inspection-oriented platform design, and empirical evidence that platform-state-aware LLM agents can provide higher-quality assistance than purely prompt-based interaction in this domain.

•Mar 30, 2026•0 citations

Quantum assistant: Specialization of multimodal vision-language models for quantum computing

Samuel Lima Braz, João Paulo Leite

Code assistants for quantum computing operate exclusively on text, disregarding visual representations (circuit diagrams, Bloch spheres, and histograms) that permeate the domain’s documentation. This work is presented as a resource-and-pilot study with three contributions: (1) the first public multimodal dataset for Qiskit-oriented quantum programming, containing 8,366 samples (45% with images) across function completion, code generation, and question answering tasks, released under Apache 2.0; (2) a reproducible synthetic generation pipeline that extracts content from public Qiskit documentation, transcribes images via a multimodal model, generates question-answer pairs, and validates code through automatically generated unit tests; and (3) a feasibility study of parameter-efficient VLM specialization, in which rsLoRA (rank 32, two epochs) on Qwen3-VL-8B-Instruct is retained as the best configuration under a controlled method-selection comparison of five LoRA variants. On the text-only external benchmarks Qiskit HumanEval and Qiskit HumanEval Hard, which measure quantum-code specialization rather than visual understanding, the fine-tuned model reaches 41.72% and 30.46% Pass@1 respectively, above the IBM-specialized Qwen2.5-Coder-14B-Qiskit (40.40% / 25.83%) and granite-3.3-8b-qiskit (17.88% / 9.93%), and + 17.22 / + 15.89 pp over the Qwen3-VL-8B-Instruct base. Visual capability is assessed on the synthetic multimodal test split, where multimodal samples reach 64.29% Pass@1 versus 46.33% on text-only samples ( + 17.96 pp); a matched training ablation that withholds the multimodal portion of the training set localizes + 6.25 pp of that gap to the multimodal training signal. The dataset, models, and code are available under the Apache 2.0 license.

Expert Systems with Applications•Aug 13, 2026•0 citations

End-to-End Fidelity Analysis of Quantum Circuit Optimization: From Gate-Level Transformations to Pulse-Level Control

Rylan Malarchick

We present an analysis of quantum circuit fidelity across the full compilation stack, from high-level gate optimization through pulse-level control. We connect a C++ circuit optimizer to a per-gate Lindblad master-equation fidelity model whose decoherence channels are cross-validated against qiskit-dynamics and whose absolute predictions are benchmarked against execution on real hardware. Across a campaign of 4,452 experiment runs over 371 benchmark circuits, gate cancellation provides the dominant improvement ($d = 1.66$, 72% of circuits improved), while circuit size and pulse duration are the strongest negative predictors of process fidelity (input gates $r = -0.78$; pulse duration $r = -0.73$, $R^2 = 0.53$). A formal ablation study shows that pass ordering has no significant effect on two-qubit gate reduction (Kruskal--Wallis $p = 0.302$). Comparing against Qiskit transpilation levels, we show that two-qubit gate count, not total gate count, is the hardware-relevant metric: our optimizer attains superior two-qubit reduction on structured circuits (87.8% on QFT, 100% on QAOA) whereas Qiskit's larger total-gate reduction is dominated by single-qubit ($u_3$) consolidation. Finally, executing eight circuits on the IQM Resonance Garnet processor (8/8 jobs completed, job identifiers released) reveals that the model is a consistent upper bound: it preserves the relative difficulty ordering of circuits but overestimates absolute fidelity by a mean of 0.49, quantifying the error budget (crosstalk, leakage, readout) outside a $T_1$/$T_2$/depolarizing model. We release the framework, data, and scripts as open source.

quant-pharXiv:2601.20871•Jan 20, 2026•0 citations

AI Agents for Variational Quantum Circuit Design

Marco Knipfer, Alexander Roman, Konstantin T. Matchev +2 more

Variational quantum circuits (VQCs) constitute a central building block of near-term quantum machine learning (QML), yet the principled design of expressive and trainable architectures remains a major open challenge. The VQC design space grows combinatorially with the number of qubits, layers, entanglement structures, and gate parameterizations, rendering manual circuit construction inefficient and often suboptimal. We introduce an autonomous agent-based framework for VQC architecture search that integrates high-level reasoning with a quantum simulation environment. The agent proposes candidate circuit architectures, evaluates them through fully automated training and validation pipelines, and iteratively improves its design strategy via performance-driven feedback. Empirically, we show that the agent autonomously evolves circuit architectures from simple initial ansätze toward increasingly expressive designs, progressively trying to improve task performance. This demonstrates that agentic AI can effectively navigate and refine the VQC design landscape with minimal human intervention, providing a scalable methodology for automated quantum model development in the Noisy Intermediate-Scale Quantum (NISQ) regime.

quant-pharXiv:2602.19387•Feb 24, 2026•0 citations

Automating quantum circuit optimization with AI agents

Marcos Crichigno, Steve Flammia

Compiling quantum algorithms for real devices involves hard optimization problems that can decide whether an algorithm runs at scale. We present a general method for solving such problems with AI agents, with every result certified. It builds on autoresearch loops, in which agents iteratively improve programs against a fixed evaluator and which have recently improved quantum cryptanalysis circuits, and adds two elements: a frozen, exact verifier certifies every result, and this verifier, together with the challenge around it, is built by an agent that formulates the problem with a researcher and validates the verifier against a solved case, deliberately broken solutions and published results before any solution exists. The method applies to any optimization problem whose solutions can be verified exactly and efficiently. We apply it to three compilation problems in quantum simulation, namely fermion-to-qubit encoding, Hamiltonian layout and unitary synthesis. In each, the agents improved substantially on published or standard constructions, reducing the cost being optimized by up to 73% at the largest sizes tested and outperforming a state-of-the-art optimizer for fermion-to-qubit encodings. Every submission is a program accompanied by its agent's notes, so the ideas behind each improvement are recorded in human-readable form; later agents built on them, and we describe them here. These results open the way to automated, certified discovery across quantum circuit design and beyond.

quant-pharXiv:2610.31352•Oct 23, 2026•0 citations
Can AI agents visually comprehend quantum circuit diagrams and generate verified executable code--and at what cost? We present Quantum Circuit Vision, a cost-aware evaluation framework for multimodal AI agents on quantum circuit visual understanding. We construct a 132-circuit benchmark spanning 13 categories (111--101010 qubits) with executable Amazon Braket code and unitary-fidelity verification. Evaluating three frontier Claude-family models at different capability-cost tiers with n=5n=5n=5 repeated trials, we find that the mid-tier model (Sonnet 4.6, 1.30×1.30\times1.30× credits) offers the most favorable balance on the cost-accuracy frontier: 91% pass rate on the core subset at 18% of the per-call cost of the strongest model (Opus 4.6), whose accuracy advantage is not statistically significant (paired ttt: p=0.083p=0.083p=0.083). Logistic regression confirms that circuit depth--not qubit count--is the primary predictor of failure (p<0.001p<0.001p<0.001). Chain-of-thought prompting shows no statistically significant effect (all p>0.18p>0.18p>0.18, n=5n=5n=5), suggesting that visual pattern recognition outweighs explicit reasoning strategy for structurally coupled diagrams. We propose a cascade routing strategy (cheap →\rightarrow→ expensive models) that achieves 84% accuracy at 38% of single-model cost, demonstrating that model routing dominates prompt engineering as a cost lever. We release QCV-Dataset (132 circuits, 5 modalities, 1,931 files) on Hugging Face Hub as an open evaluation infrastructure with structured metadata for discoverability, interoperability, and responsible AI documentation, and all evaluation code, cost logs, and verification scripts on GitHub for full reproducibility.
We review thirteen generative systems and five supporting datasets for quantum circuit and quantum code generation, identified through a structured scoping review of Hugging Face, arXiv, and provenance tracing (January-February 2026). We organize the field along two axes: artifact type (Qiskit code, OpenQASM programs, circuit graphs); crossed with training regime (supervised fine-tuning, verifier-in-the-loop RL, diffusion/graph generation, agentic optimization); and systematically apply a three-layer evaluation framework covering syntactic validity, semantic correctness, and hardware executability. The central finding is that while all reviewed systems address syntax and most address semantics to some degree, none reports end-to-end evaluation on quantum hardware (Layer 3b), leaving a significant gap between generated circuits and practical deployment. Scope note: quantum code refers throughout to quantum program artifacts (QASM, Qiskit); we do not cover generation of quantum error-correcting codes (QEC).
Although most software engineering work today targets classical systems, quantum computing has become an area of growing interest for developers who want to understand alternative computational models. This thesis addresses the difficulty of learning to construct and reason about quantum circuits by focusing on small, illustrative circuit-based algorithms (Bell states, GHZ states, and a reduced Grover’s search) as structured examples around which an interactive learning platform is built. The aim is to support step-by-step understanding of these circuits while investigating how large language models (LLMs) can assist with circuit generation and explanation. The work presents a web-based platform that allows users to incrementally build circuits, visualize their layer-by-layer evolution, and inspect key properties such as gate composition and measurement probabilities. On top of this platform, two LLM-based assistance strategies are implemented: a stateless baseline that operates solely on naturallanguage prompts, and a context-aware, agentic mode that receives structured information about the current circuit and simulation results. Their behavior is compared in an offline evaluation on a fixed set of exemplar tasks, using a rubric that scores correctness of the resulting circuits, relevance of explanations to the actual circuit, and pedagogical clarity. The results indicate that the agentic, state-aware integration produces more accurate, better-grounded, and more instructionally useful outputs than the stateless baseline on the examined tasks. The thesis contributes an example-driven approach to quantum computing education for software engineers, an inspection-oriented platform design, and empirical evidence that platform-state-aware LLM agents can provide higher-quality assistance than purely prompt-based interaction in this domain.
Code assistants for quantum computing operate exclusively on text, disregarding visual representations (circuit diagrams, Bloch spheres, and histograms) that permeate the domain’s documentation. This work is presented as a resource-and-pilot study with three contributions: (1) the first public multimodal dataset for Qiskit-oriented quantum programming, containing 8,366 samples (45% with images) across function completion, code generation, and question answering tasks, released under Apache 2.0; (2) a reproducible synthetic generation pipeline that extracts content from public Qiskit documentation, transcribes images via a multimodal model, generates question-answer pairs, and validates code through automatically generated unit tests; and (3) a feasibility study of parameter-efficient VLM specialization, in which rsLoRA (rank 32, two epochs) on Qwen3-VL-8B-Instruct is retained as the best configuration under a controlled method-selection comparison of five LoRA variants. On the text-only external benchmarks Qiskit HumanEval and Qiskit HumanEval Hard, which measure quantum-code specialization rather than visual understanding, the fine-tuned model reaches 41.72% and 30.46% Pass@1 respectively, above the IBM-specialized Qwen2.5-Coder-14B-Qiskit (40.40% / 25.83%) and granite-3.3-8b-qiskit (17.88% / 9.93%), and + 17.22 / + 15.89 pp over the Qwen3-VL-8B-Instruct base. Visual capability is assessed on the synthetic multimodal test split, where multimodal samples reach 64.29% Pass@1 versus 46.33% on text-only samples ( + 17.96 pp); a matched training ablation that withholds the multimodal portion of the training set localizes + 6.25 pp of that gap to the multimodal training signal. The dataset, models, and code are available under the Apache 2.0 license.
We present an analysis of quantum circuit fidelity across the full compilation stack, from high-level gate optimization through pulse-level control. We connect a C++ circuit optimizer to a per-gate Lindblad master-equation fidelity model whose decoherence channels are cross-validated against qiskit-dynamics and whose absolute predictions are benchmarked against execution on real hardware. Across a campaign of 4,452 experiment runs over 371 benchmark circuits, gate cancellation provides the dominant improvement (d=1.66d = 1.66d=1.66, 72% of circuits improved), while circuit size and pulse duration are the strongest negative predictors of process fidelity (input gates r=−0.78r = -0.78r=−0.78; pulse duration r=−0.73r = -0.73r=−0.73, R2=0.53R^2 = 0.53R2=0.53). A formal ablation study shows that pass ordering has no significant effect on two-qubit gate reduction (Kruskal--Wallis p=0.302p = 0.302p=0.302). Comparing against Qiskit transpilation levels, we show that two-qubit gate count, not total gate count, is the hardware-relevant metric: our optimizer attains superior two-qubit reduction on structured circuits (87.8% on QFT, 100% on QAOA) whereas Qiskit's larger total-gate reduction is dominated by single-qubit (u3u_3u3​) consolidation. Finally, executing eight circuits on the IQM Resonance Garnet processor (8/8 jobs completed, job identifiers released) reveals that the model is a consistent upper bound: it preserves the relative difficulty ordering of circuits but overestimates absolute fidelity by a mean of 0.49, quantifying the error budget (crosstalk, leakage, readout) outside a T1T_1T1​/T2T_2T2​/depolarizing model. We release the framework, data, and scripts as open source.
Variational quantum circuits (VQCs) constitute a central building block of near-term quantum machine learning (QML), yet the principled design of expressive and trainable architectures remains a major open challenge. The VQC design space grows combinatorially with the number of qubits, layers, entanglement structures, and gate parameterizations, rendering manual circuit construction inefficient and often suboptimal. We introduce an autonomous agent-based framework for VQC architecture search that integrates high-level reasoning with a quantum simulation environment. The agent proposes candidate circuit architectures, evaluates them through fully automated training and validation pipelines, and iteratively improves its design strategy via performance-driven feedback. Empirically, we show that the agent autonomously evolves circuit architectures from simple initial ansätze toward increasingly expressive designs, progressively trying to improve task performance. This demonstrates that agentic AI can effectively navigate and refine the VQC design landscape with minimal human intervention, providing a scalable methodology for automated quantum model development in the Noisy Intermediate-Scale Quantum (NISQ) regime.
Compiling quantum algorithms for real devices involves hard optimization problems that can decide whether an algorithm runs at scale. We present a general method for solving such problems with AI agents, with every result certified. It builds on autoresearch loops, in which agents iteratively improve programs against a fixed evaluator and which have recently improved quantum cryptanalysis circuits, and adds two elements: a frozen, exact verifier certifies every result, and this verifier, together with the challenge around it, is built by an agent that formulates the problem with a researcher and validates the verifier against a solved case, deliberately broken solutions and published results before any solution exists. The method applies to any optimization problem whose solutions can be verified exactly and efficiently. We apply it to three compilation problems in quantum simulation, namely fermion-to-qubit encoding, Hamiltonian layout and unitary synthesis. In each, the agents improved substantially on published or standard constructions, reducing the cost being optimized by up to 73% at the largest sizes tested and outperforming a state-of-the-art optimizer for fermion-to-qubit encodings. Every submission is a program accompanied by its agent's notes, so the ideas behind each improvement are recorded in human-readable form; later agents built on them, and we describe them here. These results open the way to automated, certified discovery across quantum circuit design and beyond.