Google's AI agents discover verified quantum programs, cutting quantum arithmetic cost 290x
dair_ai · x · 2026-11-09
Google DeepMind and Google Quantum AI released a paper on discovering formally verified quantum programs with LLM agent teams.
Approach
- Classical computers can only test quantum algorithms on small instances, so simulation-scored search loops can't reach useful scales
- Researchers write a specification and cost target as a Lean theorem; agent teams propose programs, the Lean kernel verifies correctness and cost, and a separate comparator re-checks every accepted answer
- Agent teams share results and dead ends on a wiki and exchange ideas at scheduled conferences
Results
- Quantum arithmetic cost cut 290x vs. prior best baseline
- Simulations relevant to fusion, photochemistry, and drug metabolism improved 11x, 8x, and 2.5x
The authors argue that human-AI collaboration at scale, under mathematical proof rigor, enables designing algorithms that today's computers cannot test, shortening the path to practical quantum computing.
More from Research
- DefFlow: Robots Manipulate Ropes, Cloth into Precise 3D Goal Shapes via Point Flows — drsrinathsridha · 2026-11-09
- RLDM 2027 announces Brian Christian, author of The Alignment Problem, as speaker — dabelcs · 2026-11-09
- Nature review: AI has transformed maths — and may outgrow human insight — LucaAmb · 2026-11-09
- No vision, no tactile sensors: humanoid dexterity from proprioception alone at CoRL — Jan_R_Peters · 2026-11-09
- LowRAM: Huawei's KV cache compression gets 4x near-lossless value amortisation — Teresa Delgado · 2026-11-09
- Geometric abstraction cuts robot agent VLM queries 52.8% and speeds manipulation 33% — siddkaramcheti · 2026-11-09