Screwtape: Adversarial Transcript Editing for Monitor Red-Teaming.
arXiv:2610.20941v1 Announce Type: cross Abstract: We present Screwtape, a pipeline that converts real agent transcripts into attacks that evade action-only monitors. An LLM attacker edits a transcript so that the agent causes a specified harm, such as leaking
arXiv cs.AIResearch source·