The Hitchhiker's Guide to Agentic AI
摘要
本文档收录《Agentic AI 全栈指南：从基础到系统》一文，作者 Haggai Roitman 提供一本全面的实践者参考书，核心论点是构建优秀代理系统需理解管道每一层；从 LLM 基底（Transformer 架构、GPU 系统、训练与微调如 SFT、LoRA、MoE、模型压缩、推理优化）开始，再阐述对齐与推理层（RLHF、PPO、DPO 及变体、GRPO、奖励建模、RL 用于大推理模型含 CoT 和测试时扩展），然后深入代理 AI 部分（代理训练与轨迹 RL、RAG 与 Agentic RAG、记忆系统（in-context、外置、episodic、semantic）、代理 harness 设计与上下文管理、代理设计模式分类），并详细覆盖多代理协调（Model Context Protocol（MCP）、代理技能与工具使用、Agent-to-Agent（A2A）通信协议、多代理架构（集中、去中心、层次化）），最后介绍代理开发框架、代理 UI 设计、代理任务评估方法和生产部署；每章均配理论基础、实现指导、代码示例及主要文献引用。
荐读理由
书中给出Model Context Protocol (MCP) 和 Agent-to-Agent (A2A) 通信协议的深度实现指南，能直接移植到独立开发者AI系统间的多代理协调中，改变你对agentic架构设计的判断。
原文
Computer Science > Artificial Intelligence
[Submitted on 22 Jun 2026]
Title:The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
Authors:Haggai Roitman
View a PDF of the paper titled The Hitchhiker's Guide to Agentic AI: From Foundations to Systems, by Haggai Roitman
Abstract:The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems. The book covers the full stack from first principles to production deployment, organized around a central thesis: building great agentic systems requires understanding every layer of the pipeline, not just one. The book opens with the LLM substrate -- transformer architecture, GPU systems, training and fine-tuning (SFT,LoRA, MoE), model compression, and inference optimization -- treated as essential foundations rather than the primary focus. It then develops the alignment and reasoning layer: reinforcement learning from human feedback (RLHF), PPO, DPO and its variants, GRPO, reward modeling, and RL for large reasoning models including chain-of-thought and test-time scaling. The second half is devoted to agentic AI proper. Topics include agentic training and trajectory-based RL, retrieval-augmented generation (RAG and Agentic RAG), memory systems (in-context, external, episodic, and semantic), agent harness design and context management, and a taxonomy of agent design patterns. Inter-agent coordination is covered in depth: the Model Context Protocol (MCP), agent skills and tool use, the Agent-to-Agent (A2A) communication protocol, and multi-agent architectures spanning centralized, decentralized, and hierarchical topologies. The book concludes with agent development frameworks, agentic UI design, evaluation methodology for agentic tasks, and production deployment. Each chapter pairs rigorous theoretical foundations with implementation guidance, code examples, and references to the primary literature.
https://doi.org/10.48550/arXiv.2606.24937
arXiv-issued DOI via DataCite
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR); Machine Learning (cs.LG) |
|---|---|
| Cite as: | arXiv:2606.24937 [cs.AI] |
| (or arXiv:2606.24937v1 [cs.AI] for this version) | |
Submission history
From: Haggai Roitman [view email] [v1] Mon, 22 Jun 2026 17:48:54 UTC (5,525 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled The Hitchhiker's Guide to Agentic AI: From Foundations to Systems, by Haggai Roitman
view licenseCurrent browse context:
cs.AI
Change to browse by:
References & Citations
Loading...
BibTeX formatted citation
Data provided by:
Bookmark
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
ScienceCast (What is ScienceCast?)
Demos
Replicate (What is Replicate?)
Hugging Face Spaces (What is Spaces?)
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
这条对你有帮助吗？