This session will discuss what an agent is and the different cognitive architectures that an Agent could use to execute tasks. Covered topics include:

• What is an Agent (e.g., perception, Brain, Action, Environment)?
• Different types of agentic memory
• How does an Agent use tools (Toolformer, TALM)
• How to enable an Agent to plan and reason - Introduction to theory of mind
• Cognitive architectures - Multi-layered nature (recursion, multi vs single agent architectures)
• Agent patterns - Chains, routers, graphs
• Control mechanisms - Static vs dynamic
• Patterns of multi-agent collaboration
• Self-reflection and multi-agent hacks