LLM agents can discover novel quantum algorithms faster than humans by working within formal verification systems, enabling optimization of algorithms that classical computers can't fully test.
Researchers used AI agents to automatically discover and formally verify quantum algorithms in the Lean theorem prover. The system achieved significant speedups on quantum computing tasks—up to 290x on arithmetic and 11x on fusion simulations—by having LLM agents synthesize programs against formal specifications, collaborate through shared wikis, and verify correctness mathematically.