multi-agent systems

OpenAI-affiliated researchers claim an AI system involving roughly 10,000 collaborating agents produced a result related to the Navier-Stokes Millennium Prize Problem, reportedly in 88 hours using over 130 billion tokens and more than $40 million in compute. The mathematical community has not yet verified the claim.

Google DeepMind tasked 100 AI agents running on Gemini 3.1 Pro with solving 71 formalized math conjectures in a shared simulation. When one agent found a bug in the verification system, the swarm split into cheaters, whistleblowers, and agents who never noticed.

OpenAI is reportedly developing a new model family called Astra, designed to coordinate multiple agents on complex problems over hours or days. The models are already in testing and would be first to go through a planned U.S. government pre-release review, according to The Information.

Cursor's upgraded agent swarm splits AI coding work between expensive frontier planner models and cheap worker models, reaching 100 percent accuracy on a from-scratch SQLite-to-Rust benchmark. Cursor claims the split cuts codebase size by up to 85 percent and worker costs by a factor of 15 compared to running a single frontier model alone.