extit{One Size doesn't Fit All}: A Personalized Conversational Tutoring Agent for Mathematics Instruction

2025-02-18

AI Summary

Existing intelligent educational systems often neglect individual learner differences, resulting in insufficient personalization in mathematics instruction. This paper introduces PACE, a personalized dialogue tutoring agent for mathematics education. PACE employs the Felder-Silverman model to construct fine-grained cognitive representations of students’ learning styles and—novelly—integrates style-aware mechanisms with Socratic questioning to enable personality-centered, dynamic pedagogical strategy generation. The methodology comprises (1) learning style cognitive modeling, (2) Socratic dialogue generation, (3) domain-specific data construction and fine-tuning, and (4) multi-dimensional educational evaluation. Experimental results demonstrate that PACE significantly enhances student engagement and conceptual understanding, outperforming general-purpose AI tutoring baselines across multiple pedagogical metrics. These findings validate the substantive efficacy of learning-style-driven adaptive dialogue paradigms in improving mathematics learning outcomes.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Search and Optimization: Learning to Search
• Humans and AI: Learning Human Values and Preferences

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: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Large language models (LLMs) have been increasingly employed in various intelligent educational systems, simulating human tutors to facilitate effective human-machine interaction. However, previous studies often overlook the significance of recognizing and adapting to individual learner characteristics. Such adaptation is crucial for enhancing student engagement and learning efficiency, particularly in mathematics instruction, where diverse learning styles require personalized strategies to promote comprehension and enthusiasm. In this paper, we propose a extbf{P}erson extbf{A}lized extbf{C}onversational tutoring ag extbf{E}nt (PACE) for mathematics instruction. PACE simulates students' learning styles based on the Felder and Silverman learning style model, aligning with each student's persona. In this way, our PACE can effectively assess the personality of students, allowing to develop individualized teaching strategies that resonate with their unique learning styles. To further enhance students' comprehension, PACE employs the Socratic teaching method to provide instant feedback and encourage deep thinking. By constructing personalized teaching data and training models, PACE demonstrates the ability to identify and adapt to the unique needs of each student, significantly improving the overall learning experience and outcomes. Moreover, we establish multi-aspect evaluation criteria and conduct extensive analysis to assess the performance of personalized teaching. Experimental results demonstrate the superiority of our model in personalizing the educational experience and motivating students compared to existing methods.

Problem

• Personalized conversational tutoring for math
• Adapting to individual learning styles
• Improving student engagement and efficiency

Innovation

• Personalized Conversational Tutoring Agent
• Felder-Silverman Learning Style Model
• Socratic Teaching Method Instant Feedback