🗺️ Learning Roadmap

🍌 From Basic Concepts → Agent Architecture → Tool Calling → Memory Management → Multi-Agent → Reinforcement Learning → Production Deploy → Goal Achieved!

Follow the banana guide 🍌 step by step, and you'll master AI Agent development from zero to hero!

📖 Read Online (Recommended)

🚀 Auto-Tracking Frontier: Daily arXiv Paper Updates

• 📡 Daily Automated Search: A scheduled pipeline scans arXiv daily for new papers on Agent architectures, tool use, memory systems, multi-agent collaboration, reinforcement learning for agents, and more.
• 📝 Auto-Updated Content: Relevant findings are automatically integrated into the corresponding chapters, keeping the book's frontier sections fresh and up-to-date.
• 🔔 Never Miss a Breakthrough: No need to manually track dozens of research feeds — this repo does it for you, so you can focus on learning and building.

💡 This means the content you read here is not static — it evolves continuously with the latest advances in the AI Agent field.

🔭 Frontier Research Directions

This book not only covers foundational knowledge, but also tracks the cutting-edge research frontiers across each domain. Here are the key directions we follow:

✨ Key Features

• 🎯 Step by Step: From LLM fundamentals to multi-Agent systems, each chapter has a clear knowledge progression
• 💻 Code First: Every core concept comes with runnable Python code examples
• 🎨 Rich Illustrations: 120+ hand-drawn SVG architecture diagrams / flowcharts / sequence diagrams for intuitive understanding
• 🎬 Interactive Animations: 5 built-in interactive HTML animations (Perceive-Think-Act cycle, ReAct reasoning, Function Calling, RAG flow, GRPO sampling)
• 🔬 Paper Reviews: Key chapters include frontier paper deep-dives (ReAct, Reflexion, MemGPT, GRPO, etc.)
• 🏗️ Complete Projects: 3 comprehensive hands-on projects (AI Coding Assistant, Intelligent Data Analysis Agent, Multimodal Agent)
• 🛡️ Production Ready: Covers security, evaluation, deployment, and other production essentials
• 🧪 Cutting Edge: Covers Context Engineering, Agentic-RL (GRPO/DPO/PPO), MCP/A2A/ANP, and other 2025–2026 latest advances
• 📐 Formula Support: KaTeX-rendered math formulas for clear reading of policy gradient, KL divergence derivations in RL chapters
• 🔄 Continuously Updated: Tracking the latest changes in LangChain, LangGraph, MCP, and other frameworks

📸 Selected Content Preview

Below are selected showcases from the book's 120+ hand-drawn SVG illustrations, all original to this book.

🧠 Agent Core Architecture

Perceive-Think-Act Loop (Chapter 1) Agent's core mechanism: Perceive environment → LLM reasoning → Execute action → Loop until goal achieved

ReAct Reasoning Framework (Chapter 6) Thought → Action → Observation alternating loop, enabling Agents to think while acting

🛠️ Tool Calling & RAG

Function Calling Complete Flow (Chapter 4) 6-step complete flow from user input to tool invocation to final response, with message structure illustration

RAG Retrieval-Augmented Generation (Chapter 7) Offline indexing + Online retrieval dual-phase architecture, making LLM answers evidence-based

💾 Memory System & Context Engineering

Three-Layer Memory Architecture (Chapter 5) Working memory → Short-term memory → Long-term memory, with important info sinking down and semantic retrieval pulling up

Prompt Engineering vs Context Engineering (Chapter 8) From "how to say it" to "what the LLM sees" — the paradigm shift of the Agent era

🤝 Multi-Agent & Communication Protocols

Three Multi-Agent Communication Patterns (Chapter 14) Message Queue (async decoupling) / Shared Blackboard (data sharing) / Direct Call (real-time collaboration)

MCP / A2A / ANP Protocol Comparison (Chapter 15) Three-layer protocol stack: ANP for discovery → A2A for task collaboration → MCP for tool invocation

🧪 Reinforcement Learning & Frameworks

GRPO Training Architecture (Chapter 10) No Critic model needed, computes advantage via intra-group normalization, only 1.5× model size in VRAM

LangGraph Three Core Concepts (Chapter 12) State (shared state) · Node (processing unit) · Edge (execution flow control)

🎬 Interactive Animations

This book includes 5 interactive HTML animations to help you intuitively understand the dynamic processes of core concepts:

💡 Interactive animations are only available in the online e-book. Local builds can also preview them.

🚀 Quick Start

Local Build

Install Dependencies:

# Install mdBook (choose one)
cargo install mdbook
# Or macOS: brew install mdbook

# Install mdbook-katex plugin (for math formula rendering)
cargo install mdbook-katex

# Clone the repository
git clone https://github.com/Haozhe-Xing/agent_learning.git
cd agent_learning

One-click Local Preview (Recommended):

# Build both Chinese and English versions and start unified server (default port 3000)
./serve.sh

# Specify custom port
./serve.sh 8080

# Enable file watching, auto-rebuild on source file changes (requires fswatch or inotifywait)
./serve.sh --watch
./serve.sh 8080 --watch

After starting, visit:

• 🌐 Language Selection Home: http://localhost:3000 (auto-redirects based on browser language)
• 🇨🇳 Chinese Version: http://localhost:3000/zh/
• 🇺🇸 English Version: http://localhost:3000/en/

💡 File watching dependency installation:

# macOS
brew install fswatch

# Ubuntu / Debian
sudo apt-get install inotify-tools

Environment Setup (For Code Practice)

# Python 3.11+
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install core dependencies
pip install langchain langchain-openai langgraph openai anthropic

# Configure API Key
export OPENAI_API_KEY="your-key-here"

🔥 Core Topics at a Glance

📊 Technology Stack

🤝 Contributing

All forms of contribution are welcome!

• 🐛 Found a bug: Submit an Issue
• 💡 Content suggestions: Start a Discussion
• 📝 Improve content: Fork → Edit → Submit PR
• ⭐ Support the project: Give this repo a Star!

Contributing Guide

# Fork and clone
git clone https://github.com/YOUR_USERNAME/agent_learning.git  # Replace with your username

# Create a feature branch
git checkout -b feature/improve-chapter-4

# Local preview (unified Chinese & English service)
./serve.sh

# Commit changes
git commit -m "feat: improve Chapter 4 tool calling code examples"

# Push and create PR
git push origin feature/improve-chapter-4

Content Organization Conventions

• Each chapter is placed in a separate directory src/zh/chapter_xxx/ (Chinese) or src/en/chapter_xxx/ (English)
• Chapter overview goes in README.md, sections are numbered as 01_xxx.md, 02_xxx.md
• Chinese SVG illustrations go in src/zh/svg/, English versions in src/en/svg/, naming format: chapter_xxx_description.svg
• Chinese interactive animations go in src/zh/animations/, English versions in src/en/animations/

English Translation Contributions

The English version is being continuously translated. Translation contributions are welcome!

Steps to translate a chapter:

1. Find the corresponding .md file under src/en/ (content shows placeholder 🚧 Translation in progress)
2. Translate the Chinese version from src/zh/ and replace the placeholder content
3. If the chapter references SVG images, create corresponding English SVGs in src/en/svg/ (replace Chinese text with English)
4. If the chapter references interactive animations, create corresponding English HTML in src/en/animations/
5. Preview locally with ./serve.sh, visit http://localhost:3000/en/ to check the English version
6. Submit PR with title format: translate: Translate Chapter X - [Chapter Name]

Placeholder template format (English file content before translation):

# [Chapter Title]

> 🚧 **Translation in progress.**
> This chapter is not yet available in English.
> Please check back later, or switch to the [Chinese version](../../zh/...) for the full content.

📄 License

This project is open-sourced under the MIT License.

⭐ Star History

If this project helps you, please give it a Star ⭐ — it's the greatest encouragement for the author!