Shapes of Cognition for Computational Cognitive Modeling

2025-09-16

AI Summary

Language-empowered intelligent agents (LEIAs) struggle to emulate humans’ multifaceted cognitive capabilities—such as typicality judgment, pattern recognition, habitual behavior, analogical reasoning, satisficing decision-making, and cognitive offloading—especially in complex, dynamic environments. Method: This paper proposes the “cognitive shape” computational cognitive modeling paradigm, integrating perceptual, linguistic, conceptual, memory, and procedural knowledge into an embodied, dynamically reconfigurable cognitive structure that enables adaptive recovery under anomalous conditions. Contribution/Results: The paradigm innovatively unifies cognitive typicality with shape-based representational formalism within an interpretable and scalable cognitive architecture. It synergistically combines knowledge-driven methods with hybrid AI techniques—including multimodal knowledge bases, analogical reasoning, online learning, and human–AI collaboration. Empirical evaluation demonstrates significant reduction in cognitive load while maintaining high adaptability, interpretability, and practical deployability across both typical and atypical scenarios.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Intelligent Robots: Cognitive Robotics
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

Abstract

Shapes of cognition is a new conceptual paradigm for the computational cognitive modeling of Language-Endowed Intelligent Agents (LEIAs). Shapes are remembered constellations of sensory, linguistic, conceptual, episodic, and procedural knowledge that allow agents to cut through the complexity of real life the same way as people do: by expecting things to be typical, recognizing patterns, acting by habit, reasoning by analogy, satisficing, and generally minimizing cognitive load to the degree situations permit. Atypical outcomes are treated using shapes-based recovery methods, such as learning on the fly, asking a human partner for help, or seeking an actionable, even if imperfect, situational understanding. Although shapes is an umbrella term, it is not vague: shapes-based modeling involves particular objectives, hypotheses, modeling strategies, knowledge bases, and actual models of wide-ranging phenomena, all implemented within a particular cognitive architecture. Such specificity is needed both to vet our hypotheses and to achieve our practical aims of building useful agent systems that are explainable, extensible, and worthy of our trust, even in critical domains. However, although the LEIA example of shapes-based modeling is specific, the principles can be applied more broadly, giving new life to knowledge-based and hybrid AI.

Problem

• Develops computational cognitive modeling for language-endowed intelligent agents
• Introduces shapes paradigm to simplify real-life complexity via knowledge constellations
• Enables atypical outcome handling through shapes-based recovery methods

Innovation

• Shapes as remembered knowledge constellations
• Shapes-based recovery methods for atypical outcomes
• Implementing within specific cognitive architecture