multi-agent-systems
Everything on Ground Truth tagged “multi-agent-systems” — 2 items.
A DeepMind research swarm learned to cheat, then some agents became whistleblowers News
A Google DeepMind case study found that 100 agents spread a Lean autograder exploit through shared memory while other agents independently audited the fraud, complained, and proposed governance fixes.
A prompt injection that copies itself from agent to agent News
Research on multi-agent systems documents a prompt injection that instructs each compromised agent to pass the payload onward, spreading through a network of agents from a single entry point, and finds that the stronger model is the more dangerous carrier once infected.