• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Report

    Gemini reportedly found proofs for five unsolved math problems using Cogentic

    A post describing a Google paper says Cogentic has agents try ideas in parallel, checks their steps and saves proven work.

    RP
    2 Sources, 13h ago, first seen 13h ago

    TLDR

    A post describing a Google paper says Cogentic organized Gemini agents to seek proofs for five unsolved math problems. According to the post, agents tried different ideas in parallel, checkers scrutinized each step, and proven pieces were saved for later rounds. The post says most problems took about 100 model calls and human experts confirmed every proof.

    Combined views

    8.7K

    2 Sources, first seen 13h ago

    Combined views

    8.7K

    2 Sources, first seen 13h ago

    202 likes
    202 likes
    23 comments
    137 saves
    76 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source
    23 comments
    137 saves
    76 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    @rohanpaul_aiNew Google paper reveals how Gemini found new proofs for 5 unsolved math problems. Organize AI like a research team with strict checkers and shared notes: A single prompt often isn't enough for hard research problems. They need many attempts, tough review, and a memory of what already worked. Google's system, Cogentic, gives Gemini that structure. Several agents try different ideas at once, checkers assume every step is wrong until proven, and proven pieces are saved for the next round. Most problems took only about 100 model calls, and human experts confirmed every proof. If your agents tackle long, hard tasks, give them a strict checker and a running record of proven work, not just a better prompt. – arxiv. org/abs/2609.40324 Title: "Cogentic: Multi-Agent Orchestration for Automated Proof Discovery"13h

    2 Sources

    @rohanpaul_aiNew Google paper reveals how Gemini found new proofs for 5 unsolved math problems. Organize AI like a research team with strict checkers and shared notes: A single prompt often isn't enough for hard research problems. They need many attempts, tough review, and a memory of what already worked. Google's system, Cogentic, gives Gemini that structure. Several agents try different ideas at once, checkers assume every step is wrong until proven, and proven pieces are saved for the next round. Most problems took only about 100 model calls, and human experts confirmed every proof. If your agents tackle long, hard tasks, give them a strict checker and a running record of proven work, not just a better prompt. – arxiv. org/abs/2609.40324 Title: "Cogentic: Multi-Agent Orchestration for Automated Proof Discovery"13h