I am extremely curious about the CoT of the agents at the time they realized they solved NS problem. I imagine models being shocked and then celebrate together:
"Wait, this seems to be a real solution!?"
"No way, let me verify again!"
"We have indeed solved it, yay!"
We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.
The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.
The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.