Harvard, Anthropic, and QuEra Use LLMs to Discover Quantum Circuits with Up to 9,100x Lower Resource Costs

Researchers from Harvard, Anthropic, and QuEra Computing developed an AI framework that uses Large Language Models (LLMs) to discover and optimize fault-tolerant quantum circuits. This framework significantly reduces the resource costs of core computational primitives, achieving up to 9,100x lower costs compared to hand-crafted baselines. The LLMs achieved this by proposing complete Python programs for circuits, which were then evaluated and refined through an evolutionary process, leading to th