AI Agents

Memory, Personalization, and Continual Learning

Ravid Shwartz-Ziv's research interests in AI memory, personalization, continual learning, and updating knowledge without destructive interference.

On Training in Imagination

Training agents in learned world models: how model errors and rollout budgets shape policy learning.

AI Must Embrace Specialization via Superhuman Adaptable Intelligence

A perspective on specialization, adaptation, and how to define useful goals for AI research.

Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition

We study a mobile AI agent that separates planning, execution, verification, and reflection to improve reliability on AndroidWorld tasks.

A superpersuasive autonomous policy debating system

A research system that combines retrieval and specialized agents for structured policy debate.