Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment

TL;DR

This paper introduces WikiHowAgent, a multi-LLM agent framework for scalable procedural learning and pedagogic quality assessment, supported by a large dataset of teacher-learner interactions across multiple domains.

Contribution

It presents a novel multi-agent workflow leveraging LLMs for interactive education and introduces a large, diverse dataset for evaluating pedagogic quality.

Findings

Effective in diverse educational setups

Provides insights into LLM capabilities across domains

Open-sourced dataset and implementation

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.