![Figure S1: The Reed–Solomon decoder. (a) Measured forward Toffoli cost per step: one cycle of the 222-cycle synchronized EEA baseline of Khattar et al. [13] , or one round of our 70-round BM decoder. (b) Locator degree (top) and number of stored discrepancies…](/img/2026-10/5f5730ab04cb07.webp)
LLM-guided search finds cheaper quantum circuits in seven of eight benchmark tasks
A language model proposes circuit designs, a strict classical checker verifies and scores them, and the results beat prior designs while making a previously impractical classical algorithm usable in quantum form.
Quantum algorithms spend much of their budget on ordinary calculations, such as arithmetic and decoding, that must be rebuilt as reversible circuits. A new paper pairs a large language model, which writes circuit-building programs, with an independent evaluator that checks correctness and counts Toffoli gates and qubits. Across eight tasks in chemistry, optimization, simulation, numerical computation and number theory, the discovered circuits used both fewer Toffolis and fewer qubits than the prior state of the art in seven. In the eighth, the search produced a new reversible design for modular inversion based on divsteps, a classical method previously considered impractical in this setting.
