11 Agent planning and feedback

 

This chapter covers

  • Planning for an LLM and implementing it in agents and assistants
  • Using the OpenAI Assistants platform via custom actions
  • Implementing/testing a generic planner on LLMs
  • Using the feedback mechanism in advanced models
  • Planning, reasoning, evaluation, and feedback in building agentic systems

Now that we’ve examined how large language models (LLMs) can reason and plan, this chapter takes this concept a step further by employing planning within an agent framework. Planning should be at the core of any agent/assistant platform or toolkit. We’ll start by looking at the basics of planning and how to implement a planner through prompting. Then, we’ll see how planning operates using the OpenAI Assistants platform, which automatically incorporates planning. From there, we’ll build and implement a general planner for LLMs.

Planning can only go so far, and an often-unrecognized element is feedback. Therefore, in the last sections of the chapter, we explore feedback and implement it within a planner. You must be familiar with the content of chapter 10, so please review it if you need to, and when you’re ready, let’s begin planning.

11.1 Planning: The essential tool for all agents/assistants

11.2 Understanding the sequential planning process

11.3 Building a sequential planner

11.4 Reviewing a stepwise planner: OpenAI Strawberry

11.5 Applying planning, reasoning, evaluation, and feedback to assistant and agentic systems

11.5.1 Application of assistant/agentic planning

11.5.2 Application of assistant/agentic reasoning

11.5.3 Application of evaluation to agentic systems

11.5.4 Application of feedback to agentic/assistant applications

11.6 Exercises

Summary