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).
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).
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.
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× 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 → 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.
Quantum computing remains in the Noisy Intermediate-Scale Quantum (NISQ) era, with performance constrained by noise. Addressing this limitation requires hardware-facing capabilities beyond gate sequences: mid-circuit measurement and classical feedback for quantum error correction (QEC), precise timing for dynamical decoupling (DD), and pulse-level waveform access for calibration. OpenQASM 3 exposes these capabilities through a hardware-level programming interface. Despite rapid progress in large language models (LLMs) for code generation, datasets targeting these advanced features remain lacking. We introduce QASM-Eval, the first comprehensive dataset to train and evaluate LLMs on OpenQASM 3, targeting completion of hardware-facing constructs within a supplied program context. QASM-Eval comprises an expert-curated test set of 1,200 tasks and a training set of over 4,000 tasks, covering classical logic, timing scheduling, pulse control, and complex tasks inspired by quantum-control workflows. An extended verifier automatically checks syntax, quantum measurement distributions, and program timelines. Our evaluation identifies substantial headroom for OpenQASM 3 code generation and significant gains from targeted fine-tuning. Fine-tuned Llama-3-8B outperforms zero-shot GPT-5.6-Terra, while fine-tuned Llama-3-70B achieves 61.17% overall pass@1 and approaches few-shot-augmented GPT-5.6-Terra. QASM-Eval provides a benchmark and training resource for specification-guided code generation over the hardware-facing constructs of OpenQASM 3, supporting the development of LLM assistants for quantum programming. Data and code: https://github.com/fuzhenxiao/QASM-Eval
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.
Quantum Generative Adversarial Networks (QGANs) incorporate quantum models, predominantly parameterized quantum circuits (PQCs), into adversarial learning frameworks for generative modeling within Noisy Intermediate Scale Quantum (NISQ) limitations. In the past three years, QGAN research has transitioned towards hybrid quantum-classical architectures, patch-based and latent-based scaling methodologies, and stability-focused objectives, including Wasserstein losses, gradient penalties, mutual-information regularization, and learned priors. This survey examines representative QGAN literature from 2023 to 2025, emphasizing algorithmic objectives, reported experimental results, evaluation methodologies, and practical constraints. This paper proposes a multidimensional taxonomy for organizing recent QGAN research based on architectural design, training objectives, scalability strategies, and evaluation practices. It highlights persistent issues in benchmarking, scalability, and hardware realism by comparing datasets, metrics, and architectural patterns across studies, offering a structured overview of the current QGAN research landscape.
Scientific code generation can produce executable programs that fail to compute the intended scientific object. We study this problem in language-model synthesis of Clifford circuits, which prepare the stabilizer states used in quantum error correction and admit exact classical verification. In our target-conditioned framework, each target is given as compact signed stabilizer generators, and an exact verifier checks the generated OpenQASM circuits. We supervise models with Aaronson-Gottesman chain-of-thought (AG-CoT) traces checked by the verifier, and continue training on model generations that the verifier accepts. Across two independently trained model families (3B and 7B), AG-CoT supervision multiplies greedy-decode state-equivalence accuracy by four to six times over circuit-only baselines, and verifier-filtered continuation training adds a further consistent gain atop both. A complementary 32B study shows that supervised models achieve near-perfect syntax and Clifford validity while the strongest direct model reaches 6.14% state equivalence per target, rising to over 10% under verifier-guided selection with multiple candidates. These results show that algorithmic trace supervision gives a large, statistically significant gain in both model families and that verifier-filtered continuation adds a further repeated gain. The persistent gap between Clifford validity and state equivalence confirms that exact verification is necessary: a circuit can be syntactically and physically valid yet prepare the wrong quantum state.