Today for AI
HOT RADAR
llmHEAT 6.3°

AI CURATED HOT STORY · 10/12/2026

DeepMind's AlphaProof Nexus Solves Dozens of Open Math Problems via Gemini 3.1 and Lean Verification, Passing Peer Review

1 reports archived1 independent sourcesupdated 10/12/2026, 17:35:54
Synthesis & Latest Updates
1 Sources Cross-Validated

Google DeepMind's AlphaProof Nexus solved dozens of long-standing open math problems, including nine Erdős conjectures, and passed peer review in Science. Powered by Gemini 3.1 Pro and utilizing the Lean formal proof language for iterative error correction, the system demonstrated autonomous reasoning capabilities even without specialized tools, marking a significant milestone in AI-driven mathematical discovery.

LATEST/Google DeepMind's AlphaProof Nexus solved dozens of long-standing open math problems, including nine Erdős conjectures, and passed peer review in Science. Powered by Gemini 3.1 Pro and utilizing the Lean formal proof language for iterative error correction, the system demonstrated autonomous reasoning capabilities even without specialized tools, marking a significant milestone in AI-driven mathematical discovery.

HEAT TRENDHourly heat curve

27 fully observed hours
Now
6.3
Peak
11.619:00
24h change
-43%

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. The DecoderT2·92 pts
    • AlphaProof Nexus solved 9 Erdős problems (two unsolved for 56 years) and 44 OEIS integer sequence conjectures.
    • The core architecture uses Gemini 3.1 Pro for drafting and the Lean formal checker for real-time error feedback to refine proofs.
    • The study passed peer review in Science, distinguishing it from previous AI math works that only released preprints or sparked boycotts.