Simulating Human-Like Learning Dynamics with LLM-Empowered Agents

2025-08-07

AI Summary

Modeling human-like learning dynamics and enabling interpretable cognitive development tracking remains a challenge in AI-driven education. Method: We propose LearnerAgent, a psychology-informed multi-agent framework built upon large language models (LLMs), integrating learner psychographic profiling, misconception-aware item diagnostics, periodic assessments, strategy selection, and peer interaction to simulate year-long individual cognitive evolution. Contribution/Results: We identify that base LLMs inherently exhibit “diligent yet fragile surface learning” behavior—revealing a fundamental dissociation between observable actions and underlying cognition. In contrast, augmenting LLMs with deep learning mechanisms yields sustained cognitive growth, psychologically plausible behavioral patterns, and coherent self-concept development. Empirical evaluation demonstrates LearnerAgent’s superiority in simulation fidelity, process interpretability, and psychological consistency, establishing a computationally grounded, empirically verifiable cognitive modeling paradigm for next-generation AI educational agents.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Multiagent Learning
• 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
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Capturing human learning behavior based on deep learning methods has become a major research focus in both psychology and intelligent systems. Recent approaches rely on controlled experiments or rule-based models to explore cognitive processes. However, they struggle to capture learning dynamics, track progress over time, or provide explainability. To address these challenges, we introduce LearnerAgent, a novel multi-agent framework based on Large Language Models (LLMs) to simulate a realistic teaching environment. To explore human-like learning dynamics, we construct learners with psychologically grounded profiles-such as Deep, Surface, and Lazy-as well as a persona-free General Learner to inspect the base LLM's default behavior. Through weekly knowledge acquisition, monthly strategic choices, periodic tests, and peer interaction, we can track the dynamic learning progress of individual learners over a full-year journey. Our findings are fourfold: 1) Longitudinal analysis reveals that only Deep Learner achieves sustained cognitive growth. Our specially designed "trap questions" effectively diagnose Surface Learner's shallow knowledge. 2) The behavioral and cognitive patterns of distinct learners align closely with their psychological profiles. 3) Learners' self-concept scores evolve realistically, with the General Learner developing surprisingly high self-efficacy despite its cognitive limitations. 4) Critically, the default profile of base LLM is a "diligent but brittle Surface Learner"-an agent that mimics the behaviors of a good student but lacks true, generalizable understanding. Extensive simulation experiments demonstrate that LearnerAgent aligns well with real scenarios, yielding more insightful findings about LLMs' behavior.

Problem

• Simulate human-like learning dynamics using LLM-based agents
• Track and analyze individual learning progress over time
• Evaluate cognitive growth and self-concept in diverse learner profiles

Innovation

• LLM-based multi-agent framework for learning simulation
• Psychologically grounded learner profiles for dynamics
• Longitudinal tracking with tests and peer interaction