Reconciling Different Theories of Learning with an Agent-based Model of Procedural Learning

2024-08-23

arXiv.org

AI Summary

This paper addresses theoretical conflicts among ICAP, KLI, and Cognitive Load Theory (CLT) in procedural learning by proposing ABICAP—the first computable agent-based model integrating all three frameworks. Grounded in agent-based modeling and cognitive architecture simulation, ABICAP embeds multi-theoretic behavioral constraints to dynamically simulate learning processes in educational settings. The study identifies the boundary conditions and prerequisite assumptions under which each theory holds, successfully reproducing and explaining previously contradictory empirical findings. It demonstrates that ICAP’s applicability in procedural learning requires additional operational constraints to be valid. Key contributions include: (1) a refined theoretical framework for procedural knowledge acquisition; and (2) the establishment of an “executable learning theory” paradigm—enabling computational instantiation, empirical verification, and systematic extension of learning theories. This advances both theoretical coherence and methodological rigor in educational cognitive science.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Machine Learning: Learning Theory

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: Practical large-scale studies of user experience
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Computational models of human learning can play a significant role in enhancing our knowledge about nuances in theoretical and qualitative learning theories and frameworks. There are many existing frameworks in educational settings that have shown to be verified using empirical studies, but at times we find these theories make conflicting claims or recommendations for instruction. In this study, we propose a new computational model of human learning, Procedural ABICAP, that reconciles the ICAP, Knowledge-Learning-Instruction (KLI), and cognitive load theory (CLT) frameworks for learning procedural knowledge. ICAP assumes that constructive learning generally yields better learning outcomes, while theories such as KLI and CLT claim that this is not always true. We suppose that one reason for this may be that ICAP is primarily used for conceptual learning and is underspecified as a framework for thinking about procedural learning. We show how our computational model, both by design and through simulations, can be used to reconcile different results in the literature. More generally, we position our computational model as an executable theory of learning that can be used to simulate various educational settings.

Problem

• Reconciling conflicting learning theories ICAP, KLI, and CLT
• Modeling procedural learning to address ICAP's conceptual focus gap
• Providing executable simulations for diverse educational settings

Innovation

• Agent-based model reconciles ICAP, KLI, CLT
• Computational model simulates procedural learning
• Executable theory for diverse educational settings