Automating quantum circuit optimization with AI agents
Abstract
Compiling quantum algorithms for real devices involves hard optimization problems that can decide whether an algorithm runs at scale. We present a general method for solving such problems with AI agents, with every result certified. It builds on autoresearch loops, in which agents iteratively improve programs against a fixed evaluator and which have recently improved quantum cryptanalysis circuits, and adds two elements: a frozen, exact verifier certifies every result, and this verifier, together with the challenge around it, is built by an agent that formulates the problem with a researcher and validates the verifier against a solved case, deliberately broken solutions and published results before any solution exists. The method applies to any optimization problem whose solutions can be verified exactly and efficiently. We apply it to three compilation problems in quantum simulation, namely fermion-to-qubit encoding, Hamiltonian layout and unitary synthesis. In each, the agents improved substantially on published or standard constructions, reducing the cost being optimized by up to 73% at the largest sizes tested and outperforming a state-of-the-art optimizer for fermion-to-qubit encodings. Every submission is a program accompanied by its agent's notes, so the ideas behind each improvement are recorded in human-readable form; later agents built on them, and we describe them here. These results open the way to automated, certified discovery across quantum circuit design and beyond.
Related
- Bridge of Ψ's: Quantum Circuit Optimization with Schrödinger Bridges
- Circuit Design Problems in Binary Polynomial Quantum Optimization
- Evaluating the Effect of the Order of Optimization Passes in Quantum Circuit Optimization
- Entanglement-Aware Quantum Circuit Optimization through Globally Optimal Partitioning
- Circuit-depth optimization of quantum partial-search algorithms
BibTeX
@misc{crichigno2026automating,
title = {{Automating quantum circuit optimization with AI agents}},
author = {Marcos Crichigno and Steve Flammia},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.31352},
eprint = {2610.31352},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.31352},
}
RIS
TY - UNPB
TI - Automating quantum circuit optimization with AI agents
AU - Marcos Crichigno
AU - Steve Flammia
PY - 2026
DA - 2026/10/22
PB - arXiv
DO - 10.48550/arxiv.2610.31352
UR - https://arxiv.org/abs/2610.31352
AB - Compiling quantum algorithms for real devices involves hard optimization problems that can decide whether an algorithm runs at scale. We present a general method for solving such problems with AI agents, with every result certified. It builds on autoresearch loops, in which agents iteratively improve programs against a fixed evaluator and which have recently improved quantum cryptanalysis circuits, and adds two elements: a frozen, exact verifier certifies every result, and this verifier, together with the challenge around it, is built by an agent that formulates the problem with a researcher and validates the verifier against a solved case, deliberately broken solutions and published results before any solution exists. The method applies to any optimization problem whose solutions can be verified exactly and efficiently. We apply it to three compilation problems in quantum simulation, namely fermion-to-qubit encoding, Hamiltonian layout and unitary synthesis. In each, the agents improved substantially on published or standard constructions, reducing the cost being optimized by up to 73% at the largest sizes tested and outperforming a state-of-the-art optimizer for fermion-to-qubit encodings. Every submission is a program accompanied by its agent's notes, so the ideas behind each improvement are recorded in human-readable form; later agents built on them, and we describe them here. These results open the way to automated, certified discovery across quantum circuit design and beyond.
ER -