Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style

2025-05-25

AI Summary

Existing LLM-based educational simulations suffer from static student modeling and non-adaptive teaching strategies. Method: This paper proposes an education-oriented heterogeneous multi-agent simulation framework comprising: (1) cognitively diverse heterogeneous student agents; (2) a self-optimizing teacher agent featuring a novel genetic algorithm–driven mechanism for pedagogical strategy evolution; and (3) a Persona-RAG module that jointly models learning styles and integrates retrieval-augmented generation (RAG) for personalized knowledge retrieval and response generation. Contribution/Results: Experiments demonstrate that the framework spontaneously generates interpretable, differentiated instructional patterns. It significantly outperforms baseline methods in simulating authentic teacher-student interactions and in supporting teacher training and educational strategy research.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Search and Optimization: Sampling/Simulation-based Search
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• 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: User modeling and simulation for interactive and conversational systems

Abstract

Effective teaching requires adapting instructional strategies to accommodate the diverse cognitive and behavioral profiles of students, a persistent challenge in education and teacher training. While Large Language Models (LLMs) offer promise as tools to simulate such complex pedagogical environments, current simulation frameworks are limited in two key respects: (1) they often reduce students to static knowledge profiles, and (2) they lack adaptive mechanisms for modeling teachers who evolve their strategies in response to student feedback. To address these gaps, extbf{we introduce a novel simulation framework that integrates LLM-based heterogeneous student agents with a self-optimizing teacher agent}. The teacher agent's pedagogical policy is dynamically evolved using a genetic algorithm, allowing it to discover and refine effective teaching strategies based on the aggregate performance of diverse learners. In addition, extbf{we propose Persona-RAG}, a Retrieval Augmented Generation module that enables student agents to retrieve knowledge tailored to their individual learning styles. Persona-RAG preserves the retrieval accuracy of standard RAG baselines while enhancing personalization, an essential factor in modeling realistic educational scenarios. Through extensive experiments, we demonstrate how our framework supports the emergence of distinct and interpretable teaching patterns when interacting with varied student populations. Our results highlight the potential of LLM-driven simulations to inform adaptive teaching practices and provide a testbed for training human educators in controlled, data-driven environments.

Problem

• Adapting teaching strategies to diverse student cognitive profiles
• Enhancing LLM-based teacher agents with genetic algorithm optimization
• Personalizing student learning styles via Retrieval Augmented Generation

Innovation

• LLM-based heterogeneous student agents
• Genetic algorithm for teacher adaptation
• Persona-RAG for personalized learning