EduAgentQG: A Multi-Agent Workflow Framework for Personalized Question Generation
🤖 AI Summary
To address low efficiency, limited semantic diversity, and weak alignment with pedagogical objectives in personalized educational question generation, this paper proposes a multi-agent collaborative framework. It comprises five specialized agents—planning, generation, solving, pedagogical evaluation, and verification—organized into a closed-loop iterative system. The framework integrates structured task planning, a multi-dimensional binary-scoring evaluation model, and a dynamic feedback mechanism. Compared to conventional single-agent or rule-based approaches, it significantly enhances question quality stability, semantic diversity, and pedagogical alignment. Experiments on two benchmark mathematics question datasets demonstrate substantial improvements over state-of-the-art methods: +32.7% in diversity, +28.4% in pedagogical objective alignment, and +25.1% in overall quality. This work establishes a novel paradigm for automated, scalable, and adaptive generation of high-quality educational resources.
Application Category
📝 Abstract
High-quality personalized question banks are crucial for supporting adaptive learning and individualized assessment. Manually designing questions is time-consuming and often fails to meet diverse learning needs, making automated question generation a crucial approach to reduce teachers' workload and improve the scalability of educational resources. However, most existing question generation methods rely on single-agent or rule-based pipelines, which still produce questions with unstable quality, limited diversity, and insufficient alignment with educational goals. To address these challenges, we propose EduAgentQG, a multi-agent collaborative framework for generating high-quality and diverse personalized questions. The framework consists of five specialized agents and operates through an iterative feedback loop: the Planner generates structured design plans and multiple question directions to enhance diversity; the Writer produces candidate questions based on the plan and optimizes their quality and diversity using feedback from the Solver and Educator; the Solver and Educator perform binary scoring across multiple evaluation dimensions and feed the evaluation results back to the Writer; the Checker conducts final verification, including answer correctness and clarity, ensuring alignment with educational goals. Through this multi-agent collaboration and iterative feedback loop, EduAgentQG generates questions that are both high-quality and diverse, while maintaining consistency with educational objectives. Experiments on two mathematics question datasets demonstrate that EduAgentQG outperforms existing single-agent and multi-agent methods in terms of question diversity, goal consistency, and overall quality.
Problem
Research questions and friction points this paper is trying to address.
Automating personalized question generation to reduce teacher workload
Overcoming unstable quality and limited diversity in existing methods
Ensuring educational goal alignment through multi-agent collaboration
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-agent collaboration for personalized question generation
Iterative feedback loop among five specialized agents
Binary scoring across multiple evaluation dimensions
🔎 Similar Papers
No similar papers found.
