Architecture Guide

A systematic guide to the architectural dimensions that define multi-agent LLM systems. Understand how design choices impact performance, scalability, and coordination.

What Are Agents and Frameworks?

An Agent

An autonomous system that can observe its environment, make decisions, and take actions. In multi-agent LLM systems, each agent uses a large language model to reason about what to do. Agents have roles (what they specialize in), objectives (what they're trying to achieve), tools they can use, and memory to store information.

A Framework

The system that orchestrates multiple agents, manages how they communicate, and controls how they execute tasks. The framework defines the rules: how agents are scheduled, how they share information, and how they coordinate. Different frameworks make different architectural choices, which dramatically affect performance.

Architectural Paradigms

Multi-agent LLM frameworks fall into three main paradigms based on how they structure execution and agent interactions. Each paradigm makes different trade-offs between control, flexibility, and performance.

Graph-Based

Model your system as a workflow graph. Nodes represent agents or steps, edges define flow. Execution follows the predefined structure step by step.

Best for: Deterministic workflows, predictable execution, transparent debugging.

Examples:

Enforces You Control
Workflow structure Node definitions
Edge execution Memory, data flow

Role-Based

Organize agents around job descriptions. Each agent has a role that defines what they do. Coordination emerges from agents following their roles and delegating tasks.

Best for: Flexible tasks, adaptive coordination, role specialization.

Examples:

Enforces You Control
Role abstraction Role definitions
Role interactions Execution order

GABM

Treat multi-agent systems like simulations. Agents exist in a shared environment and interact with it over time. Coordination happens indirectly through environment state.

Best for: Complex simulations, emergent behavior, environment-mediated interactions.

Examples:

Enforces You Control
Time-step model Agent behaviors
Environment-mediated Environment rules
Paradigm Execution model Coordination style
Graph-based Follows predefined workflow graph Determined at design time
Role-based Role-conditioned reasoning and delegation Emerges from role interactions
GABM Time-step simulation with environment Mediated through shared environment state

Design Dimensions

These dimensions define multi-agent system architecture. Each dimension represents a fundamental design choice that can be fixed by the framework paradigm or configured by the system designer. We organize them into three categories: how individual agents work, how agents interact, and how the system environment is structured.

Single-Agent Characteristics

These dimensions control how individual agents are designed and how they behave. They determine what agents know, how they think, and what actions they can take.

  • Behavioral Specification: How agent behavior is specified (roles, goals, planning)
  • Storage Architecture: How agents remember (LTM, STM, EM, WM, EK)
  • Tool Execution: Where tool execution authority resides
Learn More →

Multi-Agent Characteristics

These dimensions control how agents interact with each other. They determine who can talk to whom, how information flows, and whether agents can collaborate on decisions.

  • Network Topology: How agents are connected and structured
  • Communication Pattern: How information moves between agents
  • Collaboration: Mechanisms for joint coordination
Learn More →

Environment

This dimension determines whether system execution is mediated through an explicit shared world state or through agent-local and developer-managed state.

  • World State: Explicit shared environment state
  • Grounded Variables: Variables representing system state
Learn More →