research
The Quantum Circuit Learns From the Hardware
A generative policy trained with a 70-qubit processor proposes far shorter circuits for molecular energy estimates, then reuses them on unseen organotin systems.
Summary
A generative policy trained with a 70-qubit processor proposes far shorter circuits for molecular energy estimates, then reuses them on unseen organotin systems.
Researchers trained transformer policies to generate quantum state-preparation circuits, first in simulation and then with an IBM Heron processor inside the loop at 46 and 70 qubits. The four main hardware-training runs used 120 million shots, while reward terms discouraged collapse to circuits that sampled only a simple reference state. Applied without retraining to organotin hydroxide models, 27 of 28 runs at 46 to 70 qubits landed within 15 millihartree of a density-matrix renormalization reference after one hardware-sampling round. The selected circuits used 34 to 72 times fewer two-qubit gates than a compared ansatz at 56 to 70 qubits; these are reported molecular-model results, not a general quantum advantage or a chemical discovery.
Why it matters
A generative policy trained with a 70-qubit processor proposes far shorter circuits for molecular energy estimates, then reuses them on unseen organotin systems.
Limits and context
- The four main hardware-training runs used 120 million shots, while reward terms discouraged collapse to circuits that sampled only a simple reference state.
- The selected circuits used 34 to 72 times fewer two-qubit gates than a compared ansatz at 56 to 70 qubits; these are reported molecular-model results, not a general quantum advantage or a chemical discovery.
Key claims
A generative policy trained with a 70-qubit processor proposes far shorter circuits for molecular energy estimates, then reuses them on unseen organotin systems.
Qualification: The four main hardware-training runs used 120 million shots, while reward terms discouraged collapse to circuits that sampled only a simple reference state.
Evidence: source-2026-11-12-001
Sources
- arXiv:2611.13755v1arXiv / Cornell University · primary research
Corrections
No corrections have been recorded for this story.