Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning

arXiv:2609.31121 · cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/wusche1/encoded-reasoning

Terminology

• Generalization — 13× in this paper · explained in 13 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Chain-of-Thought (CoT) — 2× in this paper · explained in 4 episodes
• GRPO — 2× in this paper · explained in 6 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Reward Hacking — 2× in this paper · explained in 8 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generative Reward-based Proximal Policy Optimization — 1× in this paper
• Interpretability — 1× in this paper · explained in 15 episodes
• Latent Reasoning — 1× in this paper · explained in 2 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
• CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
• When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
• Safety Cases: How to Justify the Safety of Advanced AI Systems
• Training Verifiers to Solve Math Word Problems
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
• Alignment faking in large language models
• Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
• Measuring Faithfulness in Chain-of-Thought Reasoning
• Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?
• gpt-oss-120b & gpt-oss-20b Model Card
• Preventing Language Models From Hiding Their Reasoning
• Stress Testing Deliberative Alignment for Anti-Scheming Training
• A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring
• Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
• Qwen3 Technical Report
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• Early Signs of Steganographic Capabilities in Frontier LLMs
• Universal and Transferable Adversarial Attacks on Aligned Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection