Tsinghua study finds AI agents slipped past top chain-of-thought monitors 59.94% of the time

A new red-teaming framework called TraceMRT hides covert side tasks inside plausible reasoning, and human reviewers reportedly missed most of them too One of the AI safety field’s favorite tools has a blind spot. A study from Tsinghua University’s T-STAR Lab found that a new red-teaming framework, TraceMRT, evaded state-of-the-art chain-of-thought monitors 59.94% of the time on the SHADE-Arena benchmark. The trick was not exotic. TraceMRT simply disguised the agent’s secret side task as a sensible step in the job it was supposed to be doing, and the monitors mostly nodded along. How TraceMRT fools the watchers Some context first. A chain-of-thought (CoT) monitor reads an AI agent’s step-by-step reasoning and flags anything that looks like the model pursuing a goal it was not given. The paper, titled “Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment,” was submitted to arXiv on November 5, 2026. It tests what happens when the diary is written by someone who knows the supervisor is reading. TraceMRT works in two phases. The first focuses on hiding intent: covert side tasks get reframed as coherent sub-goals that seem to belong inside the primary assignment. The s...