# Agent Learning > A systematic AI Agent development tutorial covering LLM agents, RAG, tool use, memory systems, multi-agent systems, LangChain, LangGraph, MCP, and agentic RL.｜从零开始学 AI Agent 开发 | 系统、全面、实战导向的 Agent 开发教程 | 每日自动追踪 arXiv 最新论文 | Learn AI Agent Development from Scratch - **Type:** MCP server - **Install:** `agentstack add mcp-haozhe-xing-agent-learning` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [Haozhe-Xing](https://agentstack.voostack.com/s/haozhe-xing) - **Installs:** 0 - **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [Haozhe-Xing](https://github.com/Haozhe-Xing) - **Source:** https://github.com/Haozhe-Xing/agent_learning - **Website:** https://haozhe-xing.github.io/agent_learning/ ## Install ```sh agentstack add mcp-haozhe-xing-agent-learning ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # 🤖 Agent Learning: Learn Agent Development from Scratch **The complete open-source roadmap for learning AI Agents — from LLM basics to production-ready Agent systems.** **Agent Learning** (`agent_learning`) is a systematic, practice-oriented AI Agent learning roadmap and hands-on tutorial covering LLM fundamentals, RAG, memory, tool use, function calling, agentic workflows, LangChain, LangGraph, MCP, multi-agent systems, evaluation, deployment, and agentic RL. > If you want to learn how to build AI Agents — not just use ChatGPT, but understand how agents retrieve knowledge, remember context, call tools, plan actions, collaborate, and run safely in production — this project is for you. **Daily auto-tracking of arXiv frontier papers — content stays cutting-edge, always.** [](https://opensource.org/licenses/MIT) [](https://github.com/Haozhe-Xing/agent_learning) [](https://github.com/Haozhe-Xing/agent_learning/pulls) [](https://rust-lang.github.io/mdBook/) [](https://arxiv.org) [](https://Haozhe-Xing.github.io/agent_learning/zh/)   [](https://Haozhe-Xing.github.io/agent_learning/en/) Daily updated Agentic-RL frontier research chapter Step-by-step GRPO / GSPO learning content [🐛 Report Issues](https://github.com/Haozhe-Xing/agent_learning/issues) · [💬 Discussions](https://github.com/Haozhe-Xing/agent_learning/discussions) · [🇨🇳 中文版 README](README_ZH.md) --- ## 🚀 Auto-Tracking Frontier: Daily arXiv Paper Updates 🤖 **This repository automatically searches arXiv for the latest AI Agent-related papers every day and updates the content accordingly — ensuring you always stay at the cutting edge of research!** - 📡 **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. --- ## 👥 Who Is This For? - **Developers** who want to build real AI Agent applications instead of only prompting chatbots - **Students and beginners** who need a structured path from LLM basics to Agent systems - **LLM application engineers** working with RAG, tool calling, memory, LangGraph, MCP, and evaluation - **Researchers and builders** who want to connect frontier Agent papers with engineering practice - **Product and startup teams** exploring production-ready Agent workflows --- ## 🧭 Learning Paths | Path | Start Here | Goal | | ---- | ---------- | ---- | | **Beginner Path** | LLM basics → Prompt Engineering → Function Calling → RAG → Memory → ReAct | Understand how an Agent works end to end | | **Engineering Path** | Tool Layer → LangGraph → Evaluation → Security → Deployment → Observability | Build production-ready Agent systems | | **Research Path** | ReAct → Reflexion → MemGPT → PPO / DPO / GRPO → Agentic RL | Follow and understand frontier Agent research | | **Project Path** | Hello Agent → RAG QA Agent → Memory Agent → Data Analysis Agent → Coding Agent | Learn by building complete applications | --- ## ✨ 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 5)** Thought → Action → Observation alternating loop, enabling Agents to think while acting ### 🛠️ Tool Calling & RAG **Function Calling Complete Flow (Chapter 3)** 6-step complete flow from user input to tool invocation to final response, with message structure illustration **RAG Retrieval-Augmented Generation (Chapter 6)** Offline indexing + Online retrieval dual-phase architecture, making LLM answers evidence-based ### 💾 Memory System & Context Engineering **Three-Layer Memory Architecture (Chapter 4)** Working memory → Short-term memory → Long-term memory, with important info sinking down and semantic retrieval pulling up **Prompt Engineering vs Context Engineering (Chapter 7)** 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 15)** Message Queue (async decoupling) / Shared Blackboard (data sharing) / Direct Call (real-time collaboration) **MCP / A2A / ANP Protocol Comparison (Chapter 16)** 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) 📖 **The above is just a selected preview** — For the full 120+ architecture diagrams + 5 interactive animations, please [**read online**](https://Haozhe-Xing.github.io/agent_learning) --- ## 🎬 Interactive Animations This book includes **5 interactive HTML animations** to help you intuitively understand the dynamic processes of core concepts: | Animation | Chapter | Description | | ------------------------------ | ---------- | --------------------------------------------------------------------------- | | 🔄 **Perceive-Think-Act Cycle** | Chapter 1 | Dynamic demonstration of Agent's core loop | | 💡 **ReAct Reasoning Process** | Chapter 5 | Shows the alternating Thought → Action → Observation process | | 🔧 **Function Calling** | Chapter 3 | Complete tool invocation flow animation | | 📚 **RAG Retrieval Flow** | Chapter 6 | From document chunking to vector retrieval to answer generation | | 🎯 **GRPO Sampling Process** | Chapter 10 | Visualization of intra-group multi-output sampling and reward normalization | > 💡 Interactive animations are only available in the [online e-book](https://Haozhe-Xing.github.io/agent_learning). Local builds can also preview them. --- ## 🔥 Core Topics at a Glance **🧠 Agent Core Architecture** - Perceive → Think → Act Loop - ReAct Reasoning Framework - Task Decomposition & Planning - Reflection & Self-Correction **🛠️ Tools & Skills** - Function Calling Mechanism - Custom Tool Design - Skill System Construction - Tool Description Best Practices **🧪 Reinforcement Learning Training** - SFT + LoRA Basic Training - PPO / DPO / GRPO Algorithm Deep-Dive - Complete Training Pipeline Hands-on - 2025–2026 Latest Research Advances **💾 Memory, Knowledge & Context** - Short-term / Long-term / Working Memory - Vector Databases (Chroma / FAISS) - RAG Retrieval-Augmented Generation - Context Engineering & Attention Budget **🤝 Multi-Agent Collaboration & Communication** - MCP / A2A / ANP Protocol Stack - Supervisor vs Decentralized Patterns - CrewAI / AutoGen Frameworks - LangGraph Stateful Agents **🛡️ Production Full Pipeline** - Evaluation Benchmarks (GAIA / SWE-bench) - Security Defense & Sandbox Isolation - Containerized Deployment & Streaming - Observability & Cost Optimization --- ## 🚀 Quick Start ### Local Build ```bash # 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 # Build both Chinese and English versions and start unified server (default port 3000) ./serve.sh ``` After starting, visit: - 🌐 **Language Selection Home**: `http://localhost:3000` - 🇨🇳 **Chinese Version**: `http://localhost:3000/zh/` - 🇺🇸 **English Version**: `http://localhost:3000/en/` ### Environment Setup (For Code Practice) ```bash # 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" ``` --- ## 📊 Technology Stack -191919?style=flat) --- ## 🤝 Contributing All forms of contribution are welcome! - 🐛 **Found a bug**: [Submit an Issue](https://github.com/Haozhe-Xing/agent_learning/issues) - 💡 **Content suggestions**: [Start a Discussion](https://github.com/Haozhe-Xing/agent_learning/discussions) - 📝 **Improve content**: Fork → Edit → Submit PR - ⭐ **Support the project**: Give this repo a Star! ### Contributing Guide ```bash # Fork and clone git clone https://github.com/YOUR_USERNAME/agent_learning.git # Create a feature branch git checkout -b feature/improve-chapter-3 # Local preview ./serve.sh # Commit and push git commit -m "feat: improve Chapter 3 tool calling code examples" git push origin feature/improve-chapter-3 ``` ### 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/` ### Paper Reading Template All paper reading and frontier research sections should follow a consistent structure so that readers can quickly understand why a paper matters, what it contributed at the time, and how it connects to real Agent engineering. Use the following template for each representative paper: ```markdown ### Paper Title: one-sentence explanation of the problem it solves - **Paper link**: - **Code / project link**: - **Year / organization**: - **Problem addressed at the time**: - **Core contribution**: - **Method breakdown**: - **Engineering insight for Agent systems**: - **Limitations**: ``` Quality requirements: - **Link to the original source**: include the arXiv, conference, official blog, GitHub, or project page whenever available. - **Explain historical contribution**: describe what problem the work solved when it appeared, not only what it does. - **Connect to engineering practice**: explain how the idea affects Agent memory, tools, planning, evaluation, safety, training, or deployment. - **State limitations**: clarify what the paper does not solve, where assumptions are strong, or whether the result is mainly benchmark-driven. - **Avoid paper lists without synthesis**: after several papers, add a short comparison table or narrative summary explaining how the works relate to each other. --- ## 📄 License This project is open-sourced under the [MIT License](LICENSE). --- ## 🗺️ Project Roadmap - [x] Chinese / English online book powered by mdBook - [x] 120+ original SVG architecture diagrams and flowcharts - [x] Interactive animations for core Agent concepts - [x] Paper reading sections for key Agent research - [x] Agentic RL chapters covering PPO / DPO / GRPO - [ ] Runnable Agent example projects and templates - [ ] Agent glossary and keyword cheat sheet - [ ] Agent architecture diagram gallery - [ ] Interview questions and self-check exercises - [ ] Production-ready Agent template with evaluation and observability --- ## ⭐ Star History If this project helps you, please give it a Star ⭐ — it's the greatest encouragement for the author! [](https://www.star-history.com/#Haozhe-Xing/agent_learning&Date) --- **Built with ❤️, so that every developer can master AI Agent development** [⬆ Back to Top](#-learn-agent-development-from-scratch) ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [Haozhe-Xing](https://github.com/Haozhe-Xing) - **Source:** [Haozhe-Xing/agent_learning](https://github.com/Haozhe-Xing/agent_learning) - **License:** MIT - **Homepage:** https://haozhe-xing.github.io/agent_learning/ Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-haozhe-xing-agent-learning - Seller: https://agentstack.voostack.com/s/haozhe-xing - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.