Under the Hood of Open Models: Building Scalable Multi‑Agent Architectures

​Join for a live walkthrough of open models, datasets, and tools that help developers design, deploy, and iterate on multi‑agent AI systems at scale. Learn how to use open resources—training recipes, open datasets, and reinforcement learning environments—into your existing stacks to speed up prototyping, evaluation, and production workflows.

​During the livestream, NVIDIA experts will cover:

• ​How to adapt open models and data for specialized agent workflows

• ​New tools and libraries that streamline reinforcement learning, experimentation loops, and automated evaluation.

• ​Practical ways to access and run these models through NVIDIA partners and popular inference platforms

• ​Live Q&A focused on best practices for building agentic AI systems.

​This session delivers recipes and resources to help you build with open, transparent, and customizable AI components.

​Get Started with Learning Paths: 

​Build an AI Agent https://nvda.ws/3LB3QAf 

​Build a RAG Agent https://nvda.ws/4nV0wNz