An Illustrated Guide to AI Agents

Chapter 3. Reasoning LLMs

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the 3rd chapter of the final book. Please note that the GitHub repo will be made active later on.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

LLMs like DeepSeek-R1, OpenAI o3-mini, and Google Gemini 2.0 Flash Thinking are prime examples of how LLMs can be scaled to new heights through reasoning frameworks. Reasoning in LLMs attempts to mimic our way of thinking by generating thoughts through tokens before giving a final answer. As shown in Figure X-X, these tokens explain their chain-of-thought and allow reasoning LLMs to break down a problem into smaller steps (often called reasoning steps or thought processes).

Figure 3-1. The differences between a non-reasoning and reasoning LLM. Note that both arrive at the same answer but through different processes. In practice, we do expect reasoning LLMs to perform better, but they can still arrive at the same conclusions.

Reasoning LLMs first “think” and generate intermediate information before finally answering the query.

Interestingly, the differences between ...