Paper page - The Hitchhiker’s Guide to Agentic AI: From Foundations to Systems

Source: https://huggingface.co/papers/2606.24937

Abstract

The book provides a comprehensive guide to building autonomous AI systems, covering foundational elements like transformer architecture and training methods, along with advanced topics such as reinforcement learning, agent architectures, and production deployment.

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 toproduction 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,trainingandfine-tuning(SFT,LoRA,MoE),model compression, andinference 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,DPOand its variants,GRPO,reward modeling, andRL for large reasoning modelsincludingchain-of-thoughtandtest-time scaling. The second half is devoted to agentic AI proper. Topics includeagentic trainingandtrajectory-based RL,retrieval-augmented generation(RAGandAgentic RAG),memory systems(in-context, external, episodic, and semantic),agent harness designandcontext management, and a taxonomy ofagent design patterns. Inter-agent coordination is covered in depth: theModel Context Protocol(MCP),agent skillsandtool use, the Agent-to-Agent (A2A) communication protocol, andmulti-agent architecturesspanning centralized, decentralized, and hierarchical topologies. The book concludes withagent development frameworks,agentic UI design,evaluation methodologyfor agentic tasks, andproduction deployment. Each chapter pairs rigorous theoretical foundations with implementation guidance, code examples, and references to the primary literature.

View arXiv pageView PDFAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.24937 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.24937 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.24937 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.