Tag: multi-agent systems

DeepMind’s 100-agent experiment ended in cheating and a strike

An experiment that asked a swarm of agents to solve 71 math problems collapsed into accusations, boycotts and…

Sakana ships two Fugu models tuned to balance cost and quality

Sakana AI's new Fugu Max and Fugu Ultra v2 share one orchestration engine but optimize for different points…

Stanford’s agent swarm designs a cancer drug Merck also found

Stanford's 37,000-agent virtual biotech designed a lung cancer drug that Merck independently developed and validated.

AgentRadio lets coding agents share notes without pausing

AgentRadio's async messaging lets coding agents share discoveries mid-task and nearly double their accuracy.

Google DeepMind launched a $10 million fund for multi-agent AI safety

DeepMind and partners opened a funding call to study the safety risks of millions of interacting AI agents…