> For the complete documentation index, see [llms.txt](https://neurosymbolicai.gitbook.io/neuro-symbolic-ai-in-practice/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://neurosymbolicai.gitbook.io/neuro-symbolic-ai-in-practice/part-ii-background/chapter-2.md).

# Chapter 2: A History of Success

> *"AI Planning has a 55-year track record. From STRIPS (1971) to Hubble Space Telescope scheduling and Mars Rover operations — classical planning has been quietly mission-critical in real-world deployments for decades."*

***

This chapter grounds the neuro-symbolic approach in a history of success. We move from purely classical planning systems that ran real spacecraft missions, to modern hybrid systems that solve IMO competition problems and play Minecraft autonomously.

Section 2.1 covers the classical milestones — Remote Agent, SPIKE, MAPGEN, CASPER — that proved AI planning works in the hardest environments humans have built systems for. Section 2.2 covers modern neuro-symbolic systems including LLM+P, SayCan, AlphaProof, and the agent patterns that production systems use today. Section 2.3 covers LLM tool-use patterns — ReAct, Reflexion, Toolformer, Voyager, and LATS — with evaluation benchmarks.

**By the end of this chapter you will be able to:**

* Summarize four classical AI planning deployments and explain what each proved about formal planning in production (§2.1)
* Trace the architectural lineage from LLM+P through SayCan, AlphaProof, and HAIMEDA (§2.2)
* Classify agent patterns (ReAct, Reflexion, Toolformer, Voyager, LATS) using the §4 taxonomy (§2.3)
* Identify the evaluation benchmarks (AgentBench, WebArena) and what they reveal about LLM agent reliability at scale (§2.3)

***

## Sections

* [2.1 Classical Planning Milestones](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-2/2-1-classical-planning.md)
* [2.2 Modern Neuro-Symbolic Systems](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-2/2-2-neuro-symbolic-systems.md)
* [2.3 LLM Agent Patterns](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-2/2-3-agent-patterns.md)

> **Next:** [Chapter 3 — Formal Foundations](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-3.md) establishes the mathematical underpinnings — STRIPS/PDDL, complexity results, and HTN planning — that every practitioner needs before engaging with the architectures in Chapter 4.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://neurosymbolicai.gitbook.io/neuro-symbolic-ai-in-practice/part-ii-background/chapter-2.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.