Planning and Reasoning

Tool use allows an LLM to increase its capabilities. They are typically called using JSON-like requests.

But how does the LLM, in an agentic system, decide which tool to use and when?

This is where planning comes in. Planning in LLM Agents involves breaking a given task up into actionable steps.

This plan allows the model to iteratively reflect on past behavior and update the current plan if necessary.

To enable planning in LLM Agents, let’s first look at the foundation of this technique, namely reasoning.

Planning actionable steps requires complex reasoning behavior. As such, the LLM must be able to showcase this behavior before taking the next step in planning out the task.

“Reasoning” LLMs are those that tend to “think” before answering a question.

This reasoning behavior can be enabled by roughly two choices: fine-tuning the LLM or specific prompt engineering.

With prompt engineering, we can create examples of the reasoning process that the LLM should follow. Providing examples (also called few-shot prompting) is a great method for steering the LLM’s behavior.

This methodology of providing examples of thought processes is called Chain of Thoughts (CoT) and enables more complex reasoning behavior.

Chain-of-thought can also be enabled without any examples (zero-shot prompting) by simply stating “Let’s think step-by-step".

When training an LLM, we can either give it a sufficient amount of datasets that include thought-like examples or the LLM can discover its own thinking process.

A great example is DeepSeek-R1 where rewards are used to guide the usage of thinking processes.