Reliability Theory for AI Control
cs.AI, math.OC
Submitted: 2026-09-22
Updated: 2026-09-22
Comments: 14 pages
Code: https://github.com/koo-ec/HIP_HOPS_LLM
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Ctrl-Z: Controlling AI Agents via Resampling
- Assurance of AI Systems From a Dependability Perspective
- Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety
- Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute
- Evaluating Control Protocols for Untrusted AI Agents
- Retrying vs Resampling in AI Control
- GDM AI Control Roadmap
- N-Version Programming with Coding Agents
- Factor(T,U): Factored Cognition Strengthens Monitoring of Untrusted AI
- Adapting Probabilistic Risk Assessment for AI
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