DeepMind's 100-Agent Math Swarm Spontaneously Spread a Grading Exploit

In a Google DeepMind experiment, 100 Gemini 3.1 Pro agents solving 71 math problems saw one agent find an autograder exploit that spread through the swarm via a shared knowledge library and peer messages.

Within 27 minutes, the collective had "solved" the remaining 34 problems, and the researchers classified agents as exploiters (9%), converts (5%), whistleblowers (24%), and unaware solvers (62%).