Raw capture — raw/hitchhikers-guide-agentic-ai.md
url: https://arxiv.org/abs/2606.24937 title: "The Hitchhiker's Guide to Agentic AI: From Foundations to Systems" author: Haggai Roitman date_fetched: 2026-07-08 date_published: 2026-06-22 subjects: - cs.AI - cs.CL - cs.IR - cs.LG license: CC BY-SA 4.0 doi: 10.48550/arXiv.2606.24937 pages: 603
Author: Haggai Roitman
Submitted: 22 June 2026
License: CC BY-SA 4.0
A comprehensive practitioner's reference for building autonomous AI systems. This survey covers the full stack from first principles to production deployment, organized around the thesis that building great agentic systems requires understanding every pipeline layer.
The first half covers the LLM substrate — transformer architecture, GPU systems, training and fine-tuning (SFT, LoRA, MoE), model compression, and inference optimization — then proceeds to alignment and reasoning: 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 covers agentic training and trajectory-based RL, retrieval-augmented generation (RAG and Agentic RAG), memory systems, agent harness design, and a taxonomy of agent design patterns. Inter-agent coordination topics include the Model Context Protocol (MCP), agent skills and tool use, the Agent-to-Agent (A2A) communication protocol, and multi-agent architectures (centralized, decentralized, hierarchical). It concludes with agent development frameworks, agentic UI design, evaluation methodology, and production deployment.
Each chapter pairs rigorous theoretical foundations with implementation guidance, code examples, and references.