An Illustrated Guide to AI Agents. Concepts and Code for Building Agents with LLMs, Tools, and Memory Maarten Grootendorst, Jay Alammar

An Illustrated Guide to AI Agents. Concepts and Code for Building Agents with LLMs, Tools, and Memory Maarten Grootendorst, Jay Alammar - okladka książki

Autorzy:: Maarten Grootendorst, Jay Alammar
Wydawnictwo:: O'Reilly Media (Z chęcią przeczytam książkę w języku polskim)
Ocena:: Bądź pierwszym, który oceni tę książkę
Stron:: 450
Dostępne formaty:: ePub

Mobi

Ebook

220,15 zł ~~259,00 zł~~ (-15%)

259,00 zł najniższa cena z 30 dni

Dodaj do koszyka Dostępny natychmiast po opłaceniu zakupu lub Kup na prezent Kup 1-kliknięciem

Przenieś na półkę

Do przechowalni

Artificial intelligence is entering a new phase. No longer limited to answering prompts or completing simple writing tasks, AI agents can now reason, plan, and act with increasing independence. From accelerating scientific breakthroughs to supporting creative work, these systems are quickly reshaping industries and everyday life. This book provides the conceptual foundation and practical insights you need to understand—and effectively work with—this emerging technology.

Through hundreds of clear graphic illustrations, Maarten Grootendorst and Jay Alammar explain how AI agents are built, how they think, and where they're heading. Designed for professionals, students, and curious learners alike, this guide goes beyond the buzz to reveal what's actually happening inside these systems, why it matters, and how to apply the knowledge in real-world contexts. With its visual storytelling and accessible explanations, An Illustrated Guide to AI Agents is your essential reference for navigating the next frontier of artificial intelligence.

Explore the core architecture of AI agents: tools, memory, and planning
Understand reasoning LLMs, multimodal models, and multi-agent collaboration
Learn advanced methods, including distillation, quantization, and reinforcement learning
Evaluate real-world applications, strengths, and limitations of AI agents

Wybrane bestsellery

Promocja

La IA ha adquirido nuevas y sorprendentes capacidades lingüísticas en los últimos ańos. Impulsados por los rápidos avances en Deep Learning, los sistemas de IA lingüística son capaces de escribir y comprender textos mejor que nunca. Esta tendencia está dando lugar a nuevas funciones, productos e industrias enteras. A través de la naturaleza visualm
- ebook
Grandes modelos de lenguaje: una guía práctica (Spanish Edition). Comprensión y generación del lenguaje

Jay Alammar, Maarten Grootendorst

(211,65 zł najniższa cena z 30 dni)

228.65 zł ~~269.00 zł (-15%)~~
Promocja

AI has acquired startling new language capabilities in just the past few years. Driven by the rapid advances in deep learning, language AI systems are able to write and understand text better than ever before. This trend enables the rise of new features, products, and entire industries. With this book, Python developers will learn the practical too
- ebook
Hands-On Large Language Models. Language Understanding and Generation

Jay Alammar, Maarten Grootendorst

(211,65 zł najniższa cena z 30 dni)

228.65 zł ~~269.00 zł (-15%)~~

Ebooka "An Illustrated Guide to AI Agents. Concepts and Code for Building Agents with LLMs, Tools, and Memory" przeczytasz na:

czytnikach Inkbook, Kindle, Pocketbook, Onyx Boox i innych
systemach Windows, MacOS i innych

systemach Windows, Android, iOS, HarmonyOS
na dowolnych urządzeniach i aplikacjach obsługujących formaty: PDF, EPub, Mobi

Masz pytania? Zajrzyj do zakładki Pomoc »

Oceny i opinie klientów: An Illustrated Guide to AI Agents. Concepts and Code for Building Agents with LLMs, Tools, and Memory Maarten Grootendorst, Jay Alammar

(0)

Szczegóły książki

ISBN Ebooka:: 979-83-416-6266-7, 9798341662667
Data wydania ebooka :: 2026-09-02 Data wydania ebooka często jest dniem wprowadzenia tytułu do sprzedaży i może nie być równoznaczna z datą wydania książki papierowej. Dodatkowe informacje możesz znaleźć w darmowym fragmencie. Jeśli masz wątpliwości skontaktuj się z nami sklep@ebookpoint.pl.
Język publikacji:: angielski
Rozmiar pliku ePub:: 25.6MB
Rozmiar pliku Mobi:: 25.6MB

Zgłoś erratę

Spis treści książki

Preface
- An Intuition-First Philosophy
- Building As You Read: The TinyAgent
- Audience
- Prerequisites
- Book Structure
- Hardware and Software Requirements
- API Keys
- Conventions Used in This Book
- Using Code Examples
- OReilly Online Learning
- How to Contact Us
- Acknowledgments
I. The Anatomy of an AI Agent
1. Introduction
- What Is an AI Agent?
  - Large Language Models
  - Reasoning Large Language Models
  - Augmenting the Large Language Model
    - Memory
    - Tools
    - Planning and reflection
  - An Agentic System
    - Autonomy
    - Agentic applications: What makes them so useful?
    - Responsible agent development and usage
    - Evaluating agents
- Specializations
  - Multi-Agent Collaboration
  - The Multi-Modal Agent
  - The Coding Agent
- The TinyAgent
- Summary
2. Large Language Models
- Part 1: What You Should Know About Large Language Models
  - Input and Output Tokens
  - From Language Modeling to Powering Agents
    - System prompt
    - Multi-turn conversations
    - Tool use
  - The TinyAgent
    - The large language model
    - A step and trajectory
    - Updating your TinyAgent
  - Training a Large Language Model
    - Pre-training: language modeling
    - Post-training: supervised fine-tuning
    - Post-training: reinforcement learning
    - The Group Relative Policy Optimization reinforcement learning algorithm
  - The Transformer Architecture
    - The tokenizer, Transformer blocks, and language modeling head
    - Processing through the Transformer blocks
    - Inside the Transformer block
    - The Transformer block: the feed-forward neural network
    - The Transformer block: an overview of self-attention
- Part 2: A Deeper Dive Into Large Language Models
  - How Self-Attention Works
  - KV-Caching Revisited
  - More Efficient Self-Attention
    - Multi-head Latent Attention
    - DeepSeek Sparse Attention
  - Mixture of Experts
- Summary
3. Reasoning Large Language Models
- The Paradigm Shift from Train-Time Compute to Test-Time Compute
  - Train-Time Compute Versus Test-Time Compute
  - Scaling Laws
- Categories of Test-Time Compute
  - Reward Models
  - Prompt Engineering
- Search Against Verifiers
  - Self-Consistency
  - Best-of-N Samples
- Modifying Proposal Distribution
  - Supervised Fine-Tuning
    - Flan-PaLM
    - s1: Simple test-time scaling
  - Reinforcement Learning
    - Reasoning with DeepSeek-R1 Zero
    - DeepSeek-R1
  - Native Reasoning
- Emerging Directions in Reasoning Research
  - Reasoning in Multi-Modal LLMs
  - Efficient Reasoning
  - Reasoning in Latent Space
- Summary
4. Memory
- Types of Memory
- Short-Term Memory
  - Conversation Memory
  - Trimming
  - Summarization
- Long-Term Memory
  - Retrieval-Augmented Generation
  - Agentic Retrieval-Augmented Generation
    - A-MEM
    - Search-o1
- Context Engineering
  - Context Engineering for Multi-Agent Systems
  - Optimizing the Context
    - Context tracking and storage
    - Context selection
    - Context compression
    - Context ordering
  - Context As the Specification
- Summary
5. Tool Usage, Learning, and Protocols
- Tool Usage
  - Tool Creation
  - Tool Definition
    - Using natural language
    - Using structured function calling
  - Tool Selection
  - Tool Calling
  - Tool Output Processing
  - TinyAgent with Tools
    - The system prompt
    - A single step
    - Executing an action
    - Running your TinyAgent with tool-calling capabilities
- Tool Learning
  - In-Context Learning
  - Supervised Fine-tuning
  - Reinforcement Learning
    - ToolRL
    - Search-R1
  - TinyAgent with Native Tool-Calling Capabilities
- Model Context Protocol
  - Core Components
  - The MCP Flow
- Skills
  - The SKILL.md
  - The Bundled Resources
- Summary
6. Planning and Reflection
- Planning
  - Task Decomposition
    - Chain-of-Thought
    - Explicit planning
  - Action Sequencing
    - Reason and act with prompting
    - Reason and Act with supervised fine-tuning
    - Reason and Act with reinforcement learning
- Agents That Continuously Improve
  - Reflection
    - Self-Refine
    - Reflexion
  - Self-Improvement
    - Test-time reinforcement learning
    - R-Zero
- Summary
7. Evaluating Agents
- Public Benchmarks and Leaderboards
  - Coding and Software Engineering
  - Tool Use
  - Software and Computer-Use Environments
  - Real-World Task Completion
  - Reasoning and Knowledge
  - Other Groups of Benchmarks
  - Reading Benchmark Scores Critically
- Outcome Evaluation: Did the Agent Get the Right Output?
  - Human Evaluation
  - Automated Evaluation
    - Building a simple agent evaluator
    - Exact match
    - Programmatic checks
    - LLM-as-a-judge
    - Rubric-based evaluation
- Trajectory Evaluation: Did It Get There the Right Way?
- Reliability: Does It Succeed Every Time?
  - Measuring Capability with pass@k
  - Measuring Reliability with pass^k
- Safety: Does It Avoid Harm?
- Building Your Own Evals
- Summary
II. Specialized Agents
8. Multi-Agent Systems
- The Multi-Agent System
- Orchestrating Agents
  - Patterns
  - General-Purpose Frameworks for Collaborative Task-Solving Patterns
    - CAMEL
    - MetaGPT
    - Production-grade frameworks
  - Communication Protocols
- Agent Society
  - Emotional Intelligence
    - Theory of Mind
    - Social identity
  - Simulations
  - Interactive Simulacra of Human Behavior
- Deep Research Agents
  - Toward an AI Co-Scientist
  - Agent Laboratory
- Summary
9. Multi-Modal Understanding
- What Are Multi-Modal LLMs?
- Encoding Modalities
  - Text
  - Images
    - Vision-Transformer
    - Contrastive Language-Image Pre-training
  - Audio
    - wav2vec 2.0
    - Whisper
    - CLAP
  - Video
    - ViViT
    - TimeSformer
    - Just CLIP
  - Many-Modality
- Connecting Modalities
  - Projection-Based Connector
  - Query-Based Connector
  - Fusion-Based Connector
  - Advantages and Disadvantages
- TinyAgent
- Summary
10. Code Agents and Code LLMs
- Users and Builders of Code Agents and Large Language Models
- Building Code Agents
  - Code Agents to Serve Non-Coders
  - Code Tools
    - File manipulation tools
    - Code interpreter sandbox environment
    - Command-line tools
    - Computer use tools
    - Code search
    - SQL tool
  - Context Management
    - Context optimization for the LLM cache
    - The repository map
    - Context compaction
  - Code Agents for Software Engineering
    - SWE-bench: code problems at the level of a GitHub issue
    - Planning for software engineering agents
  - Task-Specific Workflows
    - Agentless
    - TinyAgent with code tools
- Building Code LLMs
- Summary
Afterword
Index