Ravid Shwartz-Ziv's research interests in AI memory, personalization, continual learning, and updating knowledge without destructive interference.
Training agents in learned world models: how model errors and rollout budgets shape policy learning.
A perspective on specialization, adaptation, and how to define useful goals for AI research.
We study a mobile AI agent that separates planning, execution, verification, and reflection to improve reliability on AndroidWorld tasks.
A research system that combines retrieval and specialized agents for structured policy debate.