Data Verification is the Future of Quantum Computing Copilots

TL;DR

This paper emphasizes the importance of integrating verification into quantum copilots and AI systems to ensure correctness, especially in physics-constrained domains, highlighting limitations of current statistical approaches.

Contribution

It advocates for verification as a core architectural component in quantum AI, demonstrating its necessity for accurate quantum program generation and optimization.

Findings

LLMs without verification reach only 79% accuracy in circuit optimization

Verification constrains generation within valid solution subspaces

Embedding verification as an architectural primitive improves quantum AI reliability

Abstract

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.