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

arXiv 2605.13850 ↗First posted 16 Mar 2026cs.AI cs.MA cs.SEcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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 (Perception, 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 28 named patterns, 15 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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 15 of its 28 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

15 of 28 references.

Closest ancestors · 5

Same direction, newest first

Other references · 10

2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

Similar, not cited

Close in wording, no citation either way