When Should a Human Take Back Control? Optimal Delegation under Turbulent AI Risk
cs.LG, cs.AI, math.OC
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- Hawkes processes in finance
- Ctrl-Z: Controlling AI Agents via Resampling
- Why Do Multi-Agent LLM Systems Fail?
- Hallucination Cascade: Analyzing Error Propagation in Multi-Agent LLM Systems
- Markov approximation for controlled Hawkes Jump-Diffusions with general kernels
- Randomisation with moral hazard: a path to existence of optimal contracts
- Continuous control with deep reinforcement learning
- Learning to Defer in Congested Systems: The AI-Human Interplay
- Agency Problems and Adversarial Bilevel Optimization under Uncertainty and Cyber Threats
- Is Self-Repair a Silver Bullet for Code Generation?
- The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
- OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- Open Problems in Frontier AI Risk Management
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks