Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents

2026-02-25

AI Summary

Current large language models exhibit limited capabilities when handling complex tasks, and the construction of modular multi-model agents lacks systematic design principles. This work proposes a structured agent template grounded in cognitive science theories—such as working memory and dual-process theory—and classical AI algorithms, including search and planning. The framework formally defines role allocation and coordination mechanisms among multiple LLMs, offering the first systematic translation of cognitive and AI architectural principles into a reusable blueprint for language-based intelligent agents. By mapping existing agent systems onto this template, the study demonstrates its potential to enhance interpretability, improve task effectiveness, and guide the efficient design of modular language agents.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

While contemporary large language models (LLMs) are increasingly capable in isolation, there are still many difficult problems that lie beyond the abilities of a single LLM. For such tasks, there is still uncertainty about how best to take many LLMs as parts and combine them into a greater whole. This position paper argues that potential blueprints for designing such modular language agents can be found in the existing literature on cognitive models and artificial intelligence (AI) algorithms. To make this point clear, we formalize the idea of an agent template that specifies roles for individual LLMs and how their functionalities should be composed. We then survey a variety of existing language agents in the literature and highlight their underlying templates derived directly from cognitive models or AI algorithms. By highlighting these designs, we aim to call attention to agent templates inspired by cognitive science and AI as a powerful tool for developing effective, interpretable language agents.

Problem

• large language models
• modular language agents
• cognitive models
• AI algorithms
• agent composition

Innovation

• agent templates
• cognitive models
• modular language agents
• large language models
• AI algorithms