EduAgentQG: Multi-Agent Personalized Mathematics Question Generation with Explicit Diversity and Objective-Aware Evaluation
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
机构 * East China Normal University(东华大学) ; Shanghai Institute of Al for Education(上海人工智能教育研究院) ; The Chinese University of Hong Kong, Shenzhen School of Data Science(香港中文大学(深圳)数据科学学院)
专题命中 推理评测 :CoT(summary_cn,abstract);planning(abstract);分类 cs.CL、cs.AI
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。
Comments Accepted to IPM 2026