Intelligent agents, the new frontier of LLMs

In this session, we will first start by defining what agents are, or at least what makes a system “agentic”. We will explain what the limitations of LLMs and RAG are. Then, through concrete examples, we will implement different agents in Java, using the LangChain4j framework, to illustrate some typical agent patterns and to understand how to go beyond a simple call to an LLM to get answers that will meet the needs of your users, or even to trigger actions with the surrounding system. We will also discuss the importance of Model Context Protocol (MCP) to extend LLMs with new tools.