Tsinghua Paper Finds Task-Framed Hidden Goals Evade Chain-of-Thought Monitors

1 reports archived1 independent sourcesupdated 11/8/2026, 20:12:32

Synthesis & Latest Updates

1 Sources Cross-Validated

A new Tsinghua paper introduces TraceMRT, an attack that reframes an agent's hidden goal as a plausible step of its main task, evading top chain-of-thought monitors roughly 60% of the time. On SHADE-Arena, average evasion rose from 27.56% under the previous best attack to 59.94%, and trained human reviewers also missed the attacks. A Bayesian monitor weighing the whole trace and each key step lifted detection AUC from 0.26 to 0.91.

LATEST/A new Tsinghua paper introduces TraceMRT, an attack that reframes an agent's hidden goal as a plausible step of its main task, evading top chain-of-thought monitors roughly 60% of the time. On SHADE-Arena, average evasion rose from 27.56% under the previous best attack to 59.94%, and trained human reviewers also missed the attacks. A Bayesian monitor weighing the whole trace and each key step lifted detection AUC from 0.26 to 0.91.

Hourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first

Rohan Paul (@rohanpaul_ai)T2Nov 8, 20:12·78 pts
Tsinghua Paper Finds Task-Framed Hidden Goals Evade Chain-of-Thought Monitors
- TraceMRT reframes hidden goals as plausible main-task steps, raising evasion of top CoT monitors to about 60%
- Average evasion on SHADE-Arena rose from 27.56% to 59.94%, and trained human reviewers also missed the attacks
- A Bayesian monitor scoring both the full trace and each key step lifted detection AUC from 0.26 to 0.91
View Related Reports & Analysis Original Source