Date
AI Overview
Why it matters
Manually creating quality mathematics questions for diverse learning needs is time-consuming. Existing AI question generators struggle to strictly follow specific curriculum requirements and often lack variation when generating multiple problems for the same objective.
Study at a glance
- Question: Can a multi-agent framework generate diverse, logically sound math questions that precisely match specified grade-level learning objectives?
- Setting and data: 10,273 teacher-provided mathematics questions across Grades 1–9 from primary and junior secondary schools in China, covering 634 concepts and 16 competencies.
- Method: Multi-agent framework development, benchmark evaluation across multiple models, and human expert evaluation of 100 sample instances.
- AI tools: EduAgentQG, Gemini-2.5-Flash, GPT-4o-mini, Qwen2.5-72B-Instruct, DeepSeek-V3, GPT-4o
Key findings
- EduAgentQG outperformed baseline approaches across diversity, objective consistency, and win rates, raising win rates by up to 4.75 percentage points with Gemini-2.5-Flash.
- Human experts preferred EduAgentQG-generated questions over gold-standard human questions 53.34% of the time, scoring them 8.42 out of 10 on objective consistency.
- Ablation tests showed that removing the evaluation agents or the planning module caused the steepest declines in question quality and diversity.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
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.
Research Categories
What is the application?
Who age?
Why use AI?
Methods
Publication Source
Publisher
arXiv
