Article · Original
The article text is unavailable in this language; an existing version is shown.
@Moore_Irish 🫡🫡
Post says Google's Cogentic system used Gemini to find new proofs for five unsolved math problemsMachine translation
Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.
A post describing a Google paper says Cogentic has multiple agents try proof ideas in parallel, checks each step and saves verified work for later rounds. It also says most problems took about 100 model calls and human experts confirmed every proof; those results still need to be checked against the paper and expert records.
@rohanpaul_ai what a pleasant friday morning reading to stumble upon today, thanks sir.
View replied-to post on X
New 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"
View context on X