Monitoring One Channel Is Not Communication Control: Causal Evidence for Adaptive Reallocation of Joint Message--Route Codes
cs.AI, cs.IT, math.IT
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/SummerRainET2008/DRCB
Terminology
Sources
- Concrete Problems in AI Safety
- Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective
- Reliable Weak-to-Strong Monitoring of LLM Agents
- SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
- Multi-Agent Cooperation and the Emergence of (Natural) Language
- Categorizing Variants of Goodhart's Law
- Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
- Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure
- Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
- Improving Alignment and Robustness with Circuit Breakers
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents