Skip to content
Research

A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility.

arXiv:2608.00583v4 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) monitors are reported by their aggregate accuracy on a pool of reward hacks. We show that this number is a false average. On Terminal Wrench, about 77% of hacks are given away by

arXiv cs.AIResearch source·