Discovering State-of-the-Art Quantum Circuits with Large Language Models: An Evolutionary Framework

Forum topic · 小凯 · 2026-10-17

Summary

A paper by Andi Gu, Alek H. Kemeny, Susanne F. Yelin, and Mikhail D. Lukin (arXiv:2610.22367) introduces an evolutionary framework where large language models (LLMs) propose quantum circuit designs that are verified and scored by an independent evaluator. The framework addresses a key challenge in quantum algorithm development: optimizing computational primitives under reversibility constraints that do not exist in classical computation. Applied to tasks spanning numerical computation, chemistry, optimization, quantum simulation, and number theory, the approach discovered circuits that significantly reduce Toffoli gate counts and qubit requirements compared to the state of the art in seven of eight tasks. In the eighth task, the search found a novel reversible architecture for modular inversion over prime fields, making divsteps—a classical algorithm previously impractical for reversible integer arithmetic—viable. The results open the door to evaluator-guided LLM co-design of new algorithmic structures for quantum computing.

Paper Overview

Field: Machine Learning Authors: Andi Gu, Alek H. Kemeny, Susanne F. Yelin, Mikhail D. Lukin arXiv: 2610.22367

Abstract

Significant efforts are currently being directed toward the implementation of large-scale quantum information processors, but realizing useful quantum advantage also requires the development of efficient quantum algorithms. While for many practical problems the dominant resource costs are associated with a small set of computational primitives, optimizing them in the quantum setting presents unique challenges, including a reversibility constraint absent from ordinary classical computation.

Here the authors introduce an evolutionary framework in which large language models (LLMs) propose circuit designs and an independent evaluator verifies and scores them. The framework is applied to tasks spanning numerical computation, chemistry, optimization, quantum simulation, and number theory.

Key Results

In seven of eight tasks, the discovered circuits significantly reduce Toffoli gate counts and qubit numbers compared to the state of the art.
In the eighth task, the search discovered a new reversible architecture for modular inversion over prime fields, making divsteps—a classical algorithm previously impractical for reversible integer arithmetic—feasible.

Significance

These results open the door to evaluator-guided LLM co-design of new algorithmic structures for quantum computing.

--- *Source: forum post on zhichai.net, auto-collected 2026-10-17.*