collaborators

6 papers

cs.LG2026

Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors

Oliver Makins, Orazio Angelini, Zohreh Shams +1

AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent. AI Control usually studies a single agent in one trajectory, but r…

cs.LG2026

Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization

Frank Xiao, Mary Phuong

Model post-training, and in particular reinforcement learning (RL), is one of the primary mechanisms by which developers can shape models' values and behaviors. However, as models…

cs.LG2026

Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents

Frank Xiao, Mary Phuong

Trusted monitoring is a cornerstone of AI control. However, as frontier models grow more capable, the increasing capabilities gap between trusted and untrusted models may render tr…

cs.AI2026

Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives

Chloe Li, Mary Phuong, Daniel Tan

As AI systems become more capable of complex agentic tasks, they also become more capable of pursuing undesirable objectives and causing harm. Previous work has attempted to catch…

cs.AI2025

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring

Benjamin Arnav, Pablo Bernabeu-Pérez, Nathan Helm-Burger +3

As AI models are deployed with increasing autonomy, it is important to ensure they do not take harmful actions unnoticed. As a potential mitigation, we investigate Chain-of-Thought…

cs.CR2025

LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring

Chloe Li, Mary Phuong, Noah Y. Siegel

Trustworthy evaluations of dangerous capabilities are increasingly crucial for determining whether an AI system is safe to deploy. One empirically demonstrated threat is sandbaggin…