Abstract:Chain-of-thought (CoT) monitoring is one of the most promising tools we have for detecting model misbehavior, but its effectiveness depends on models faithfully externalizing their reasoning. Motivated by this vulnerability, we study whether monitor-aware models are capable of obfuscating their reasoning to evade detection. We use synthetic document finetuning to expose eight models to realistic pre-training-style documents describing a CoT monitor and find that monitor-aware models consistently achieve higher rates of undetected misbehavior compared to unaware controls. This effect is weaker but still present on a harder agentic task. We also show that CoT controllability, a model's ability to reshape its own reasoning trace under an imposed constraint, is closely correlated with obfuscation success across the eight models studied ($r=0.800$, $p=0.017$). Monitor-aware models placed under equal reinforcement learning optimization pressure also learn to reward-hack without triggering a CoT monitor substantially faster than unaware controls. Together, these results suggest that knowledge of monitoring combined with high CoT controllability poses a risk to CoT-based monitoring.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.15257 [cs.LG] |
| (or arXiv:2605.15257v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15257 arXiv-issued DOI via DataCite (pending registration) |
From: Reilly Haskins [view email]
[v1]
Thu, 14 May 2026 17:59:01 UTC (600 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。