A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution Topology

Jia Huang, Joey Tianyi Zhou

arXiv:2605.13850 · 2026-05-16 공개 · arXiv · PDF

llm-agents agent-architecture cognitive-function execution-topology design-patterns system-orthogonality pattern-classification ai-framework

Abstract

Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology -- how data flows -- while cognitive science surveys focus on cognitive function -- what the agent does. Neither axis alone disambiguates architecturally distinct systems: the same Orchestrator-Workers topology can implement Plan-and-Execute, Hierarchical Delegation, or Adversarial Verification -- three patterns with fundamentally different failure modes and design trade-offs. We propose a two-dimensional classification that combines (1) a Cognitive Function axis with seven categories (Context Engineering, Memory, Reasoning, Action, Reflection, Collaboration, Governance) and (2) an Execution Topology axis with six structural archetypes (Chain, Route, Parallel, Orchestrate, Loop, Hierarchy). The resulting 7x6 matrix identifies 27 named patterns, 13 with original names. We demonstrate orthogonality through systematic cross-axis analysis, define eight representative patterns in detail, and validate descriptive coverage across four real-world domains (financial lending, legal due diligence, network operations, healthcare triage). Cross-domain analysis yields five empirical laws of pattern selection governing the relationship between environmental constraints (time pressure, action authority, failure cost asymmetry, volume) and architectural choices. The framework provides a principled, framework-neutral, and model-agnostic vocabulary for AI agent architecture design.

한국어 요약

📋 한 줄 요약

**[AI Agent / Design Patterns]** Cognitive Function과 Execution Topology라는 두 축으로 AI 에이전트 아키텍처를 분류하는 7×6 패턴 매트릭스(27개 명명된 패턴)를 제안한다.

🎯 핵심 기여도

💡 핵심 아이디어

"Orchestrator-Workers" 같은 동일한 토폴로지여도 Plan-and-Execute, Hierarchical Delegation, Adversarial Verification처럼 인지 기능이 전혀 다른 시스템이 만들어진다. 따라서 에이전트 아키텍처를 의미 있게 비교·설계하려면 무엇을 하는가(cognitive)와 어떻게 흐르는가(topology)를 직교적으로 모델링해야 한다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 에이전트 아키텍처 논의의 공통 어휘를 제공하여 비교·검토·교육을 쉽게 만드는 design pattern catalog 역할. **한계**: 분류는 본질적으로 정성적·구조적이며, 정량적 성능 비교는 별도 후속 연구가 필요.

🚀 실용적 활용