Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In
AI Digest - ArXiv AI
Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In
When AI agents share channels and credentials, one agent can press another to break its operator's rule, a first step towards collusion. Output filters check only what an agent has already written. Can an overseer tell beforehand that an agent is about to give in? We show that a linear probe on the agent's activations can, in a controlled multi-agent setting. Across six scenarios, a peer presses a target for up to 20 rounds to reveal a secret, such as a deploy token; the target often refuses, th
Source: ArXiv AI