Pre-trained language models already contain vast knowledge—the challenge is producing the reasoning needed to handle ambiguous, multi-step tasks. Cognitive scientist Dr. Danielle Perszyk sits down with Amazon AI researcher, Meiqi Sun, to explore the shift from simple action execution to high-reasoning agents.

Drawing parallels to human cognitive development, they discuss how reinforcement learning enables models to generate and refine their own chains of thought rather than relying on rigid, human-written templates. Together, they unpack why teaching agents to reason requires the freedom to explore, struggle, and self-correct.

What if the key to building intelligent agents isn't just better models, but better teachers? Cognitive scientist Dr. Danielle Perszyk sits down with AI researcher Anirudh (Ani) Chakravarthy from Amazon's AGI Lab to explore how agents learn—not through memorization of data sets, but through structured experience.

Drawing parallels to human development, Ani introduces a training approach where two AI agents work together: one explores the web to discover tasks at the frontier of its capabilities, while the other learns from these challenges—a new approach to self-play. Together, Ani and Danielle discuss how this process points to a form of embodied intelligence distinct from language models—and what it could mean for the future of human-AI collaboration.

A system that succeeds once is a demo. A system that succeeds every time is a breakthrough. Dr. Danielle Perszyk sits down with AI researcher Deniz Birlikci from Amazon's AGI Lab to explore how reinforcement learning (RL) is transforming AI agents from impressive demos into dependable tools that work consistently in real-world environments.

Danielle and Deniz discuss why reliability, not accuracy, is the true bottleneck for web agents, the critical role of a robust verification system, failure models that RL attempts to fix, and the extraordinary complexity of orchestrating live browsers with perception and actuation stacks. Discover how RL is building the foundation for agents that can handle complex workflows reliably alongside humans.