Google reports LEAP multi-agent breakthroughs in formal mathematics
Google says its LEAP multi-agent framework, developed with Google Cloud AI and paired with Argon, autonomously produced an end-to-end, machine-checked Lean 4 formalization of the Weil conjectures spanning about 1.8 million lines through 28,800 subagent invocations. The system also synthesized more than 919,000 lines of Lean for the first formalization of a recent proof of Hilbert’s tenth problem over general rings of integers, and reproduced a formalization concerning finite-time blowup in the 3D Navier–Stokes equations. Google also reports that Deep Review is available in Antigravity as a /teamwork document-review pattern.
The reported results show Google extending multi-agent systems from informal proofs into large-scale, machine-checked formal mathematics, while Deep Review applies similar document-analysis capabilities to research drafts.
Scaling formal verification and manuscript review
Checking a computer-assisted manuscript by hand places a heavy burden on peer reviewers, and subtle flaws can hide inside long calculations. Formalizing mathematics in Lean 4 turns a proof into code that a computer kernel checks line by line. Once human mathematicians confirm that the formal theorem statement matches the original problem, the proof only compiles if every logical step holds.
Many of the deepest open problems in mathematics govern how physical waves propagate, how dynamical systems evolve, and whether polynomial equations have integer solutions. Working directly from informal proofs, our multi-agent framework, LEAP, developed with colleagues in Google Cloud AI and paired with Argon, has made progress in these core areas.
Notably, /teamwork-LEAP fully autonomously produced an end-to-end, machine-checked formalization of the Weil conjectures, the landmark results on counting solutions of polynomial equations over finite fields that culminated in Pierre Deligne's 1974 proof. This formalization spans about 1.8 million lines of Lean, produced across 28,800 subagent invocations. The system also synthesized over 919,000 lines of Lean to produce the first formalization of a recent proof of Hilbert's tenth problem over general rings of integers. It also independently reproduces an end-to-end formalization of a recent proof of finite-time blowup for the 3D Navier–Stokes equations with smooth forcing, part of one of the seven Millennium Prize Problems and open for about 90 years.
#Google#Google Cloud AI#LEAP#Argon#Antigravity#Deep Review#Lean 4