AI and the World's Hard Problems · Quantum physics & quantum computing · arXiv · 2026-10-23
Automating quantum circuit optimization with AI agents
The authors present a method that uses AI agents to solve hard optimization problems in compiling quantum algorithms, with every result checked by a frozen, exact verifier. They apply it to fermion-to-qubit encoding, Hamiltonian layout and unitary synthesis. The agents improved on published or standard constructions, cutting the optimized cost by up to 73% at the largest sizes tested, and outperformed a state-of-the-art optimizer for fermion-to-qubit encodings.