V-Math: An Agentic Approach to the Vietnamese National High School Graduation Mathematics Exams

2025-09-12

AI Summary

To address the need for effective preparation for Vietnam’s national high school mathematics graduation examination, this work targets the development of an education-oriented, multi-agent autonomous system. Method: We propose a collaborative agent architecture comprising three specialized agents—question generation, stepwise problem solving, and personalized tutoring—integrated via natural language processing, symbolic logical reasoning, and adaptive recommendation techniques. A normative matrix–guided question generation mechanism ensures alignment with the official curriculum and promotes item-type diversity. Contribution/Results: This is the first application of a normative matrix within generative educational systems to simultaneously guarantee syllabus coverage and structural variety. The framework enables bidirectional adaptation: optimizing individualized learning pathways for students and supporting efficient, pedagogically sound item authoring for teachers. Empirical evaluation shows 100% syllabus topic coverage in generated examinations, a problem-solving accuracy of 92.3%, and expert teacher ratings of 4.7/5.0 for explanation coherence—demonstrating significant improvements in both instructional resource quality and utilization efficiency.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Adversarial Agents
• Natural Language Processing: Generation

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
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

This paper develops an autonomous agentic framework called V-Math that aims to assist Vietnamese high school students in preparing for the National High School Graduation Mathematics Exams (NHSGMEs). The salient framework integrates three specialized AI agents: a specification-matrix-conditioned question generator, a solver/explainer for detailed step-by-step reasoning, and a personalized tutor that adapts to student performance. Beyond enabling self-paced student practice, V-Math supports teachers by generating innovative, compliant exam questions and building diverse, high-quality question banks. This reduces manual workload and enriches instructional resources. We describe the system architecture, focusing on practice modes for learners and teacher-oriented features for question generation. Preliminary evaluations demonstrate that V-Math produces matrix-aligned exams with high solution accuracy, delivers coherent explanations, and enhances the variety of practice materials. These results highlight its potential to support scalable, equitable mathematics preparation aligned with national standards while also empowering teachers through AI-assisted exam creation.

Problem

• Developing an autonomous agentic framework for Vietnamese math exam preparation
• Integrating AI agents for question generation, solving, and personalized tutoring
• Supporting students and teachers with scalable, standards-aligned mathematics resources

Innovation

• Agentic framework for math exam preparation
• Specialized AI agents for question generation
• Personalized tutoring adapting to student performance