Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment
This work addresses the need for scalable and pedagogically sound virtual educators in AI4Education, though it appears incremental by building on existing multi-agent and LLM frameworks.
The authors tackled the problem of scalable conversational education by proposing WikiHowAgent, a multi-LLM agent workflow for procedural learning and pedagogic quality assessment, resulting in a dataset of 114,296 conversations across 17 domains and demonstrating effectiveness in diverse setups.
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.