@inproceedings{pei-etal-2025-conversational,
    title = "Conversational Education at Scale: A Multi-{LLM} Agent Workflow for Procedural Learning and Pedagogic Quality Assessment",
    author = "Pei, Jiahuan  and
      Ye, Fanghua  and
      Sun, Xin  and
      Deng, Wentao  and
      Hindriks, Koen  and
      Wang, Junxiao",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.161/",
    doi = "10.18653/v1/2025.findings-emnlp.161",
    pages = "2984--2997",
    ISBN = "979-8-89176-335-7",
    abstract = "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."
}