A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control
cs.AI, cs.CL
Submitted: 2026-10-02
Updated: 2026-10-02
Code: https://github.com/zhezhou1106/spoof-cost
Sources
- Program Synthesis with Large Language Models
- Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
- Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
- The Llama 3 Herd of Models
- Monitoring Monitorability
- RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?
- Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?
- Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation
- Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?
- Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors
- Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking
- Detecting and Suppressing Reward Hacking with Gradient Fingerprints
- Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
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
- Agents' Last Exam
- 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