Back to library

Foundations

Technology foundations of AI agents: architectures, protocols (MCP, A2A), reasoning patterns, and foundational papers.

15 resources

Type:
15 resources found
reportOECD • 2026

The agentic AI landscape and its conceptual foundations

OECD landscape paper mapping agentic AI architectures, capability tiers, and governance touchpoints for policymakers. Synthesises definitions across vendors and academic work into a shared vocabulary, flagging where existing AI policy instruments need adjustment for agents.

Introductions and landscapeInternational
reportStanford HAI • 2026

AI Index Report 2026 (Technical Performance chapter)

Stanford HAI's annual index chapter on technical performance, tracking benchmark progress for reasoning, coding, and tool-using agents. Covers capability jumps on SWE-bench, GAIA, and WebArena plus compute and cost trends across frontier model families.

Introductions and landscapeInternational
guidelineIBM • 2026

The 2026 Guide to AI Agents

IBM explainer introducing AI agent architectures, planning loops, memory, and tool use for enterprise teams. Walks through single-agent, multi-agent, and hierarchical patterns with use cases across IT operations, customer service, and supply chain automation.

Introductions and landscapeGlobal
guidelineOpenAI • 2025

A practical guide to building agents

OpenAI handbook on deciding when an agent is appropriate, selecting models, writing clear instructions, defining tools, and adding safety guardrails. Covers single-agent and manager patterns with examples using the OpenAI Agents SDK.

Agent architecturesGlobal
guidelineAnthropic • 2024

Building Effective AI Agents

Anthropic engineering write-up distinguishing deterministic workflows from agents and documenting composable patterns like prompt chaining, routing, parallelisation, orchestrator-workers, and evaluator-optimiser. Recommends starting with the simplest pattern and adding autonomy only where it pays off.

Agent architecturesGlobal
researchChip Huyen • 2025

Agents

Chip Huyen's long-form essay breaking down agent components (planning, tool use, memory, reflection), common failure modes, and evaluation challenges. Covers ReAct-style loops, function calling, and practical trade-offs when moving from prototypes to production agents.

Agent architecturesGlobal
reportAda Lovelace Institute • 2025

Delegation Nation: Advanced AI Assistants and why they matter

Ada Lovelace Institute policy briefing on advanced AI assistants as systems that act on a user's behalf. Examines concentration of power, delegation risks, and policy levers, calling for UK-specific rules on consent and accountability.

Introductions and landscapeUnited Kingdom
researchYiming Lei et al. • 2025

Large Language Model Agents: A Comprehensive Survey on Architectures, Capabilities, and Applications

Academic survey cataloguing LLM agent architectures, planning and reasoning methods, memory mechanisms, tool-use strategies, and multi-agent coordination. Also maps application domains from coding and science to robotics, with open challenges for each layer.

Foundational papersInternational
researchShunyu Yao et al. • 2023

ReAct: Synergizing Reasoning and Acting in Language Models

Yao et al. introduce the ReAct prompting framework that interleaves chain-of-thought reasoning traces with tool actions, letting models plan, act, and observe in a loop. Evaluated on HotpotQA, FEVER, ALFWorld, and WebShop.

Reasoning and planningInternational
researchTimo Schick et al. • 2023

Toolformer: Language Models Can Teach Themselves to Use Tools

Meta AI paper showing how a language model can teach itself to call external APIs (calculator, search, translator, calendar, Q&A) through self-supervised fine-tuning on API-augmented data, improving zero-shot performance without losing core skills.

Foundational papersInternational
researchJason Wei et al. • 2022

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Google Research paper showing that prompting large models with worked-example reasoning chains elicits multi-step arithmetic, commonsense, and symbolic reasoning. Establishes the chain-of-thought technique that underpins most modern agent planning loops.

Reasoning and planningInternational
standardAnthropic and Model Context Protocol project • 2025

Model Context Protocol specification

Model Context Protocol 2025-11-25 specification defining the JSON-RPC interface that lets AI applications connect to tools, resources, and prompts through standard servers. Covers transport, authentication, capability negotiation, and progress notifications for agent integrations.

Protocols and interoperabilityGlobal
repositoryModel Context Protocol project • 2025

Model Context Protocol reference repository

GitHub monorepo for the Model Context Protocol project containing the specification, schemas, reference SDKs, and example servers. Entry point for developers building MCP-compatible tools, clients, or servers across Python, TypeScript, and other languages.

Protocols and interoperabilityGlobal
guidelineGoogle Cloud • 2025

What is the Model Context Protocol (MCP) and how does it work?

Google Cloud explainer introducing the Model Context Protocol, its client-server architecture, and how MCP servers expose tools and data to agents. Walks through Vertex AI integration patterns and compares MCP with bespoke tool plumbing.

Protocols and interoperabilityGlobal
standardGoogle • 2025

Announcing the Agent2Agent Protocol (A2A): A new era of Agent Interoperability

Google's launch post for Agent2Agent, an open protocol that lets agents built on different stacks discover each other, exchange capabilities, and coordinate long-running tasks. Supported at launch by 50+ partners including Atlassian, Salesforce, and SAP.

Protocols and interoperabilityGlobal
Foundations | VerifyWise AI Governance Library