规模化对话式教育：面向程序性学习与教学质量评估的多LLM智能体工作流
Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment
AI总结：
针对现有对话式教育研究可扩展性不足、教学质量评估框架有限的问题，提出多LLM智能体工作流WikiHowAgent，整合多角色智能体支持程序性学习与质量评估，构建超11万组对话的大规模数据集并验证了方法有效性，相关资源已开源。
摘要：
大语言模型（LLM）推动了虚拟教育者与学习者的发展，搭建起自然语言处理（NLP）与人工智能教育（AI4Education）的桥梁。现有研究往往缺乏可扩展性，未能利用多样化的大规模课程内容，且用于评估教学质量的框架十分有限。为此，我们提出WikiHowAgent——一种利用LLM模拟互动式教学对话的多智能体工作流。它整合了教师智能体、学习者智能体、交互管理器与评估器，以支持程序性学习并评估教学质量。我们构建了一个包含114296组师生对话的数据集，这些对话基于17个领域、727个主题下的14287篇教程。我们的评估协议结合了计算指标、基于评分量规的指标与人类判断对齐结果。结果表明，该工作流在多种场景下均具备有效性，为探究LLM在不同领域的能力提供了洞见。我们的数据集与实现代码已完全开源。
英文摘要：
Large language models (LLMs) have advanced virtual educators and learners, bridging NLP with AI4Education. Existing work often lacks scalability and fails to leverage diverse, large-scale course content, with limited frameworks for assessing pedagogic quality. To this end, we propose WikiHowAgent, a multi-agent workflow leveraging LLMs to simulate interactive teaching-learning conversations. It integrates teacher and learner agents, an interaction manager, and an evaluator to facilitate procedural learning and assess pedagogic quality. We introduce a dataset of 114,296 teacher-learner conversations grounded in 14,287 tutorials across 17 domains and 727 topics. Our evaluation protocol combines computational and rubric-based metrics with human judgment alignment. Results demonstrate the workflow's effectiveness in diverse setups, offering insights into LLM capabilities across domains. Our datasets and implementations are fully open-sourced.
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。
