This chapter introduces the core principles for constructing and understanding multi-agent systems built with Large Language Models. We begin by defining what a multi-agent system (MAS) is and examine how LLMs function as the central components for intelligent agents within these environments. A clear grasp of these initial topics is important for developing effective multi-agent applications.

We will cover:

• The definition and key characteristics of Multi-Agent Systems.
• How Large Language Models serve as the building blocks for intelligent agents.
• Common architectural patterns and frameworks used in designing LLM-based MAS.
• The nature of agent autonomy and behavior in contexts driven by LLMs.
• Specific design and implementation complexities associated with LLM-based multi-agent systems.
• An overview of current development tools and libraries available for building these applications.
• Guidance on configuring your development environment for multi-agent LLM projects.

By the end of this chapter, you will have a solid understanding of these fundamental aspects, preparing you for more detailed discussions on agent design, communication, and orchestration in the sections that follow.