# [A Visual Guide to LLM Agents](https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-reasoning-llms) (Extends Chapters 7 and 8)

In chapters 7 and 8, we show how you can extend the capabilities of LLMs by giving them tools, memory, and more. We briefly talked about methodologies for enabling autonomous behavior, like Reason and Act (ReAct). 

[A Visual Guide to LLM Agents](https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-llm-agents) dives deeper into making LLMs autonomous (called Agents) through various methods.

It starts with a brief overview of main components of an agent...

<a href="https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-llm-agents"><img src="../images/bonus_agents.png" width="50%" height="50%"></a>

... and continuous to describe each of these components in greater detail (**tools**, **memory**, and **planning**)

<a href="https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-llm-agents"><img src="../images/bonus_agents1.png" width="50%" height="50%"></a>

For tools, the use of the **Model Context Protocol** (MCP) is explored in depth as it showcases and increasingly popular method for enabling tool-use in Agents.

<a href="https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-llm-agents"><img src="../images/bonus_agents2.png" width="50%" height="50%"></a>

**Planning** is central in this guide as it is the main component that enables the autonomous behavior of LLM Agents.

<a href="https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-llm-agents"><img src="../images/bonus_agents3.png" width="50%" height="50%"></a>

Enabling autonomous behavior is only step 1 and this guide concludes by describing multi-agent collaboration where multiple Agents work together to reach a predefined goal.

<a href="https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-llm-agents"><img src="../images/bonus_agents4.png" width="50%" height="50%"></a>