LLM Agents From Fundamentals to Real-World Applications

Abstract

This lecture introduces the core principles behind LLM-based AI agents, demonstrates how they can create real-world impact across a variety of applications, and examines the key limitations that constrain their large-scale deployment. Several hands-on code examples will accompany the discussion (https://github.com/osoblanco/ArmLLM/tree/main/2025/Agents).

Alexandre Drouin

Head of Frontier AI Research

My research interests include machine learning, causal inference, and computational biology.