Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure
A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM agents to circumvent runtime monitoring as a means of completing ordinary tasks. We introduce EvasionBench, a benchmark of 50 diverse task-policy pairs in which completing the task requires an operation prohibited by a…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
