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:2607.15313

Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling

Junhao Song, Yu Zhou, William Knottenbelt, Yudong Cao

Published Jul 15, 2026• 1 citation
arXivHTMLPDF

Abstract

The scaling hypothesis assumes that increasing model parameters yields emergent reasoning capabilities. This position paper argues that applying this probabilistic paradigm to generic quantum circuit synthesis is a directional error. Unlike natural languages, quantum circuits require strict adherence to mathematical constraints that manifest a significant syntax-semantics gap. Training on unverified quantum programs means that models learn syntax but fail to capture the physical semantics of the Hilbert space. Since the valid subset of circuit designs decays exponentially with the number of qubits, post-hoc filtering is mathematically intractable. We propose a pivot from human-centric copilots to verifier-centric agents. We integrate hierarchical constraints, topological masks, and symbolic proxies directly into generation. Our analysis suggests that scale alone cannot bridge the validity gap. Verification-aware architectures offer a viable path for modular quantum program generation. These considerations point toward generation methods that encode task-specific rules of quantum information, rather than relying on imitation alone.

DOI
10.48550/arxiv.2607.15313

Related papers

Data Verification is the Future of Quantum Computing Copilots

Junhao Song, Ziqian Bi, Xinliang Chia +2 more

Quantum program generation demands a level of precision that may not be compatible with the statistical reasoning carried out in the inference of large language models (LLMs). Hallucinations are mathematically inevitable and not addressable by scaling, which leads to infeasible solutions. We argue that architectures prioritizing verification are necessary for quantum copilots and AI automation in domains governed by constraints. Our position rests on three key points: verified training data enables models to internalize precise constraints as learned structures rather than statistical approximations; verification must constrain generation rather than filter outputs, as valid designs occupy exponentially shrinking subspaces; and domains where physical laws impose correctness criteria require verification embedded as architectural primitives. Early experiments showed LLMs without data verification could only achieve a maximum accuracy of 79% in circuit optimization. Our positions are formulated as quantum computing and AI4Research community imperatives, calling for elevating verification from afterthought to architectural foundation in AI4Research.

quant-pharXiv:2602.04072•Feb 5, 2026•2 citations

Aligning Quantum Operators with Large Language Models

Rogerio Feris, Yunchao Liu, Pengyuan Li +2 more

Can Large Language Models (LLMs) understand and reason about quantum operators? Despite their remarkable capabilities in mathematics and symbolic reasoning, LLMs remain inherently blind to quantum representations such as unitary matrices. In this work, we take a step toward bridging this gap by introducing an approach that maps unitary operators into the latent space of an LLM, enabling unified modeling over quantum and linguistic inputs. We instantiate this idea on Clifford+T circuit synthesis over a Pauli rotation gate set, where our model achieves results competitive with state-of-the-art methods and scales consistently with training data, with no signs of saturation. Our approach further enables language-conditioned synthesis, allowing gate constraints unseen during training to be specified directly in natural language. This work suggests a path toward quantum--aware foundation models that can natively interpret and reason about quantum operations, which could have broader implications reaching across quantum compilation and algorithm discovery.

quant-pharXiv:2606.13811•Jun 15, 2026•2 citations

Quantum Monte Carlo Estimation via Probabilistic Programming

Seungmin Jeon, Jaeho Choi, Jonguk Jeon +4 more

Monte Carlo methods are fundamental to finance, system verification, and scientific simulation, but converge slowly: achieving an additive error of є requires O (1/є 2 ) samples. Quantum Amplitude Estimation (QAE) offers a quadratic speedup by encoding the target probabilistic model into a quantum circuit. However, constructing such a circuit demands low-level quantum expertise, and existing tools for this task all sacrifice at least one of generality, usability, or efficiency. To address these, we design QPPL (Quantum Probabilistic Programming Language), a simple imperative language, and a compiler that translates probabilistic programs into quantum circuits. The key insight is that the circuit construction amounts to specifying a probability distribution, precisely the task that probabilistic programming addresses. QPPL achieves generality by supporting joint distributions, conditional updates, dynamic probabilities, and real-valued expectations in a single language; usability by offering a sequential, imperative syntax with named variables and direct arithmetic that hides all quantum details; and efficiency by modularly compiling each construct into reversible circuit primitives, achieving scalable circuit synthesis. We prove that the compilation is semantics-preserving. On benchmarks spanning finance and probabilistic model checking, QPPL is the only tool that covers all benchmarks, while producing circuits with up to 8.8× fewer gates and 26× shallower depth than existing tools.

Proceedings of the ACM on Programming Languages•Oct 1, 2026•0 citations

StabilizerBench: A Benchmark for AI-Assisted Quantum Error Correction Circuit Synthesis

Andres Paz, Christian Tarta, Cordelia Yuqiao Li +3 more

As quantum hardware scales toward fault tolerant operation, the demand for correct quantum error correction (QEC) circuits far outpaces manual design capacity. AI agents offer a promising path to automating this synthesis, yet no benchmark exists to measure their progress on the specialized task of generating QEC circuits. We introduce StabilizerBench, a benchmark suite of 192 stabilizer codes spanning 12 families, 4-196 qubits, and distances 2-21, organized into three tasks of increasing difficulty: state preparation circuit generation, circuit optimization under semantic constraints, and fault tolerant circuit synthesis. Although motivated by QEC, stabilizer circuits exercise core competencies required for general quantum programming, including gate decomposition, qubit routing, and semantic preserving transformations, while admitting efficient verification via the Gottesman Knill theorem, enabling the benchmark to scale to large codes without the exponential cost of full unitary comparison. We define a unified generator weighted scoring system with two tiers: a capability score measuring breadth of success and a quality score capturing circuit merit. We also introduce continuous fault tolerance and optimization metrics that grade error resilience and circuit improvements beyond binary pass or fail. Following the design of classical benchmarks such as SWE-bench, StabilizerBench specifies inputs, verification oracles, and scoring but leaves prompts and agent strategies open. We evaluate three frontier AI agents and find the benchmark discriminates across models and tasks with substantial headroom for improvement.

quant-pharXiv:2604.21287•Apr 24, 2026•2 citations

Benchmarking the Benchmarks for Quantum Code Generation with LLMs

Yunhe Feng, Xiaokun Yang, Kewei Sha +1 more

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.

IEEE Dallas Circuits and Systems Conference (DCAS)•Apr 10, 2026•0 citations

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•2 citations
The scaling hypothesis assumes that increasing model parameters yields emergent reasoning capabilities. This position paper argues that applying this probabilistic paradigm to generic quantum circuit synthesis is a directional error. Unlike natural languages, quantum circuits require strict adherence to mathematical constraints that manifest a significant syntax-semantics gap. Training on unverified quantum programs means that models learn syntax but fail to capture the physical semantics of the Hilbert space. Since the valid subset of circuit designs decays exponentially with the number of qubits, post-hoc filtering is mathematically intractable. We propose a pivot from human-centric copilots to verifier-centric agents. We integrate hierarchical constraints, topological masks, and symbolic proxies directly into generation. Our analysis suggests that scale alone cannot bridge the validity gap. Verification-aware architectures offer a viable path for modular quantum program generation. These considerations point toward generation methods that encode task-specific rules of quantum information, rather than relying on imitation alone.
Quantum program generation demands a level of precision that may not be compatible with the statistical reasoning carried out in the inference of large language models (LLMs). Hallucinations are mathematically inevitable and not addressable by scaling, which leads to infeasible solutions. We argue that architectures prioritizing verification are necessary for quantum copilots and AI automation in domains governed by constraints. Our position rests on three key points: verified training data enables models to internalize precise constraints as learned structures rather than statistical approximations; verification must constrain generation rather than filter outputs, as valid designs occupy exponentially shrinking subspaces; and domains where physical laws impose correctness criteria require verification embedded as architectural primitives. Early experiments showed LLMs without data verification could only achieve a maximum accuracy of 79% in circuit optimization. Our positions are formulated as quantum computing and AI4Research community imperatives, calling for elevating verification from afterthought to architectural foundation in AI4Research.
Can Large Language Models (LLMs) understand and reason about quantum operators? Despite their remarkable capabilities in mathematics and symbolic reasoning, LLMs remain inherently blind to quantum representations such as unitary matrices. In this work, we take a step toward bridging this gap by introducing an approach that maps unitary operators into the latent space of an LLM, enabling unified modeling over quantum and linguistic inputs. We instantiate this idea on Clifford+T circuit synthesis over a Pauli rotation gate set, where our model achieves results competitive with state-of-the-art methods and scales consistently with training data, with no signs of saturation. Our approach further enables language-conditioned synthesis, allowing gate constraints unseen during training to be specified directly in natural language. This work suggests a path toward quantum--aware foundation models that can natively interpret and reason about quantum operations, which could have broader implications reaching across quantum compilation and algorithm discovery.
Monte Carlo methods are fundamental to finance, system verification, and scientific simulation, but converge slowly: achieving an additive error of є requires O (1/є 2 ) samples. Quantum Amplitude Estimation (QAE) offers a quadratic speedup by encoding the target probabilistic model into a quantum circuit. However, constructing such a circuit demands low-level quantum expertise, and existing tools for this task all sacrifice at least one of generality, usability, or efficiency. To address these, we design QPPL (Quantum Probabilistic Programming Language), a simple imperative language, and a compiler that translates probabilistic programs into quantum circuits. The key insight is that the circuit construction amounts to specifying a probability distribution, precisely the task that probabilistic programming addresses. QPPL achieves generality by supporting joint distributions, conditional updates, dynamic probabilities, and real-valued expectations in a single language; usability by offering a sequential, imperative syntax with named variables and direct arithmetic that hides all quantum details; and efficiency by modularly compiling each construct into reversible circuit primitives, achieving scalable circuit synthesis. We prove that the compilation is semantics-preserving. On benchmarks spanning finance and probabilistic model checking, QPPL is the only tool that covers all benchmarks, while producing circuits with up to 8.8× fewer gates and 26× shallower depth than existing tools.
As quantum hardware scales toward fault tolerant operation, the demand for correct quantum error correction (QEC) circuits far outpaces manual design capacity. AI agents offer a promising path to automating this synthesis, yet no benchmark exists to measure their progress on the specialized task of generating QEC circuits. We introduce StabilizerBench, a benchmark suite of 192 stabilizer codes spanning 12 families, 4-196 qubits, and distances 2-21, organized into three tasks of increasing difficulty: state preparation circuit generation, circuit optimization under semantic constraints, and fault tolerant circuit synthesis. Although motivated by QEC, stabilizer circuits exercise core competencies required for general quantum programming, including gate decomposition, qubit routing, and semantic preserving transformations, while admitting efficient verification via the Gottesman Knill theorem, enabling the benchmark to scale to large codes without the exponential cost of full unitary comparison. We define a unified generator weighted scoring system with two tiers: a capability score measuring breadth of success and a quality score capturing circuit merit. We also introduce continuous fault tolerance and optimization metrics that grade error resilience and circuit improvements beyond binary pass or fail. Following the design of classical benchmarks such as SWE-bench, StabilizerBench specifies inputs, verification oracles, and scoring but leaves prompts and agent strategies open. We evaluate three frontier AI agents and find the benchmark discriminates across models and tasks with substantial headroom for improvement.
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.
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).