How Intervention History Changes AI Agent Sabotage on Subsequent Tasks

AI control evaluations often reset agents' memory between tasks, although deployed agents may retain records of prior interventions. We ask whether learning that an earlier attack was caught changes an agent's ability to evade defer-to-trusted DtT, a protocol that replaces suspicious work with a...

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

As Large Language Models LLMs are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals...