Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling

Junhao Song, Yu Zhou, William Knottenbelt, Yudong Cao
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:172112-172132, 2026.

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v306-song26ag, title = {Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling}, author = {Song, Junhao and Zhou, Yu and Knottenbelt, William and Cao, Yudong}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {172112--172132}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/song26ag/song26ag.pdf}, url = {https://proceedings.mlr.press/v306/song26ag.html}, 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.} }
Endnote
%0 Conference Paper %T Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling %A Junhao Song %A Yu Zhou %A William Knottenbelt %A Yudong Cao %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-song26ag %I PMLR %P 172112--172132 %U https://proceedings.mlr.press/v306/song26ag.html %V 306 %X 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.
APA
Song, J., Zhou, Y., Knottenbelt, W. & Cao, Y.. (2026). Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:172112-172132 Available from https://proceedings.mlr.press/v306/song26ag.html.

Related Material