EduAgentQG：具有显式多样性和目标感知评估的多智能体个性化数学问题生成
EduAgentQG: Multi-Agent Personalized Mathematics Question Generation with Explicit Diversity and Objective-Aware Evaluation
AI总结：
本文针对现有数学问题生成方法难以兼顾目标对齐与可控多样性的问题，提出多智能体框架EduAgentQG，构建专属基准并验证其在多项指标上优于COT等基线方法。
摘要：
在智能教育领域，个性化数学问题生成旨在产出既满足教育要求又支持自适应评估与学习的数学问题。现有的基于大语言模型（LLM）的单智能体及多智能体方法虽提升了生成灵活性，但仍倾向于依赖聚合反馈或模型随机性，难以同时确保维度层面的目标对齐与可控多样性。为应对这些挑战，本文提出EduAgentQG——一种具备显式多样性和目标感知评估的多智能体协同个性化数学问题生成框架。该框架将问题生成组织为规划、撰写、评估、优化与检查的闭环流程：结构化生成计划与多个生成方向引导候选问题生成，细粒度评估则验证逻辑正确性、可解答性及知识概念、难度、年级水平、核心能力方面的目标对齐。本文构建了涵盖1-9年级、包含10273道数学问题的生成基准，涉及634个知识概念、16项核心能力及3个难度等级；该基准被划分为两个评估子集：含489个教育目标的MathChoice（用于选择题生成）与含500个教育目标的MathBlank（用于填空题生成）。实验结果显示，EduAgentQG在多样性、目标一致性及胜率指标上均显著优于COT、COT_N、ReAct和EQPR方法。
英文摘要：
In intelligent education, personalized mathematics question generation aims to produce mathematics questions that satisfy educational requirements while supporting adaptive assessment and learning. Existing LLM-based single-agent and multi-agent methods improve generation flexibility, but they still tend to rely on aggregated feedback or model randomness, making it difficult to jointly ensure dimension-wise objective alignment and controllable diversity. To address these challenges, we propose EduAgentQG, a multi-agent collaborative framework for personalized mathematics question generation with explicit diversity and objective-aware evaluation. EduAgentQG organizes question generation as a closed-loop process of planning, writing, evaluation, refinement, and checking: structured generation plans and multiple generation directions guide candidate generation, while fine-grained evaluation verifies logical correctness, solvability, and objective alignment in knowledge concepts, difficulty, grade level, and core competencies. We first construct a mathematics question generation benchmark containing 10,273 questions across Grades 1-9, covering 634 knowledge concepts, 16 core competencies, and three difficulty levels; for evaluation, it is organized into two subsets: MathChoice, with 489 educational objectives for multiple-choice question generation, and MathBlank, with 500 educational objectives for fill-in-the-blank question generation. Experiments show that EduAgentQG consistently outperforms COT, COT$_N$, ReAct, and EQPR in diversity, Objective Consistency, and Win Rate.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
