> 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/table-of-contents.md).

# Table of Contents

A complete listing of all parts, chapters, and sections in *Neuro-Symbolic AI in Practice*.

***

## Part I — Motivation

* [Chapter 1: Why Neuro-Symbolic AI?](/neuro-symbolic-ai-in-practice/part-i-motivation/chapter-1.md)
  * [1.1 LLM Planning Limitations](/neuro-symbolic-ai-in-practice/part-i-motivation/chapter-1/1-1-llm-limitations.md)
  * [1.2 The Neurosymbolic Agenda](/neuro-symbolic-ai-in-practice/part-i-motivation/chapter-1/1-2-neurosymbolic-agenda.md)
  * [1.3 The LLM-Modulo Framework](/neuro-symbolic-ai-in-practice/part-i-motivation/chapter-1/1-3-llm-modulo.md)
  * [1.4 Neural vs. Symbolic — A Fair Comparison](/neuro-symbolic-ai-in-practice/part-i-motivation/chapter-1/1-4-neural-vs-symbolic.md)
  * [1.5 The Extended Thinking Complication](/neuro-symbolic-ai-in-practice/part-i-motivation/chapter-1/1-5-extended-thinking.md)

***

## Part II — Background

* [Chapter 2: A History of Success](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-2.md)
  * [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)
* [Chapter 3: Formal Foundations](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-3.md)
  * [3.1 The AI Planning Problem](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-3/3-1-planning-problem.md)
  * [3.2 Computational Complexity](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-3/3-2-complexity.md)
  * [3.3 Planning Problem Classes](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-3/3-3-problem-classes.md)
  * [3.4 Hierarchical Task Network Planning](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-3/3-4-htn.md)
  * [3.5 Extensions: Temporal, Numeric & Multi-Agent](/neuro-symbolic-ai-in-practice/part-ii-background/chapter-3/3-5-extensions.md)

***

## Part III — Core Approaches

* [Chapter 4: Neuro-Symbolic AI in Practice](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4.md)
  * [4.1 Symbolic Helps Neural](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-1-symbolic-helps-neural.md) *(includes Neural-Symbolic VQA (NS-VQA); Constrained Decoding (PICARD); STaR / RLEF Self-Improvement; Neural Network Formal Verification; NeMo-Guardrails)*
  * [4.2 Neural Helps Symbolic](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-2-neural-helps-symbolic.md)
    * [4.2.1 Differentiable Reasoning](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-2-neural-helps-symbolic/4-2-differentiable-reasoning.md) *(includes A-NeSI — Scalable Approximate NeSy Inference; LOGIC-LM / SatLM / LINC — LLM-to-Logic-Solver; Neural Predicate Invention)*
    * [4.2.2 Neural Subroutines in Symbolic Systems](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-2-neural-helps-symbolic/4-2-neural-subroutines.md) *(includes Neural Algorithmic Reasoning (CLRS))*
    * [4.2.3 Answer Set Programming](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-2-neural-helps-symbolic/4-2-asp.md)
  * [4.3 Hybrid / Co-Processing Architectures](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-3-hybrid-architectures.md)
    * [4.3.1 System 1 / System 2 — AlphaProof](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-3-hybrid-architectures/4-3-system1-system2.md)
    * [4.3.2 Knowledge Graph Integration](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-3-hybrid-architectures/4-3-knowledge-graphs.md)
    * [4.3.3–4.3.14 Case Studies & Applications](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-3-hybrid-architectures/4-3-applications.md) *(includes §4.3.9 Eureka, §4.3.10 SWE-bench, §4.3.11 Selection-Inference & ProgPrompt, §4.3.12 Latplan — Classical Planning from Pixel Observations, §4.3.13 DECI / CITRIS — Neuro-Symbolic Causal Reasoning, §4.3.14 PRMs — Process Reward Models for Step-Level Verification)*
  * [4.4 Pure Neural World Models](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-4-pure-neural.md)
    * [4.4.1 Differentiable Abstract Interpretation](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-4-pure-neural/4-4-differentiable-abstract-interpretation.md)
      * [4.4.1.1–4.4.1.2 Foundations & LDT Architecture](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-4-pure-neural/4-4-differentiable-abstract-interpretation/4-4-foundations.md)
      * [4.4.1.3–4.4.1.5 Results, Lineage & Design Guide](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-4-pure-neural/4-4-differentiable-abstract-interpretation/4-4-design-principles.md)
    * [4.4.2 JEPA World Models](/neuro-symbolic-ai-in-practice/part-iii-core-approaches/chapter-4/4-4-pure-neural/4-4-jepa-world-models.md)

***

## Part IV — Synthesis

* [Chapter 5: Synthesis, Outlook & Where to Start](/neuro-symbolic-ai-in-practice/part-iv-synthesis/chapter-5.md)
  * [5.1 The Four Paradigms in Context](/neuro-symbolic-ai-in-practice/part-iv-synthesis/chapter-5/5-1-synthesis.md)
  * [5.2 Open Problems](/neuro-symbolic-ai-in-practice/part-iv-synthesis/chapter-5/5-2-open-problems.md)
  * [5.3 A Five-Year Outlook (2026–2031)](/neuro-symbolic-ai-in-practice/part-iv-synthesis/chapter-5/5-3-outlook.md)
  * [5.4 Practitioner's Guide: Where to Start](/neuro-symbolic-ai-in-practice/part-iv-synthesis/chapter-5/5-4-practitioners-guide.md)

***

## Part V — Decision Guide

* [Chapter 6: Which NeSy Architecture for My Problem?](/neuro-symbolic-ai-in-practice/part-v-decision-guide/chapter-6-decision-guide.md)
  * [Step-by-Step Decision Table](/neuro-symbolic-ai-in-practice/part-v-decision-guide/chapter-6-decision-guide.md#decision-guide)
  * [Seven Possible Outcomes at a Glance](/neuro-symbolic-ai-in-practice/part-v-decision-guide/chapter-6-decision-guide.md#at-a-glance--seven-possible-outcomes)
  * [Comparison Table](/neuro-symbolic-ai-in-practice/part-v-decision-guide/chapter-6-decision-guide.md#comparison-table)
  * [Pattern Selection by Domain](/neuro-symbolic-ai-in-practice/part-v-decision-guide/chapter-6-decision-guide.md#pattern-selection-by-domain)
  * [Warning Signs: When Not to Use Neuro-Symbolic](/neuro-symbolic-ai-in-practice/part-v-decision-guide/chapter-6-decision-guide.md#warning-signs-when-neuro-symbolic-is-not-the-right-choice)
  * [Quick-Start Checklist](/neuro-symbolic-ai-in-practice/part-v-decision-guide/chapter-6-decision-guide.md#quick-start-decision-checklist)

***

## Back Matter

* [Glossary](/neuro-symbolic-ai-in-practice/back-matter/glossary.md)
* [References](/neuro-symbolic-ai-in-practice/back-matter/references.md)
* [Additional Resources & Planners](/neuro-symbolic-ai-in-practice/back-matter/appendix.md)


---

# 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/table-of-contents.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.