Lune

EMNLP Findings2025

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

Jiahuan Pei, Fanghua Ye, Xin Sun, Wentao Deng, Koen V. Hindriks, Junxiao Wang

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, largescale 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. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • LLM Agents for Education: Advances and Applications cites ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
  • LLM Agents for Education: Advances and Applications cites CHEMREASONER: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback
  • LLM Agents for Education: Advances and Applications cites Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on7

  1. ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem SolvingZhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen et al.ICLR 2024 · 289 citations
  2. LLM Agents for Education: Advances and ApplicationsZhendong Chu, Shen Wang, Jian Xie, Tinghui Zhu et al.EMNLP Findings 2025 · 89 citations
  3. MapCoder: Multi-Agent Code Generation for Competitive Problem SolvingMd. Ashraful Islam, Mohammed Eunus Ali, Md. Rizwan ParvezACL 2024 · 29 citations
  4. CHEMREASONER: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical FeedbackHenry W. Sprueill, Carl Edwards, Khushbu Agarwal, Mariefel V. Olarte et al.ICML 2024 · 19 citations
  5. Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral SimulationSonglin Xu, Hao-Ning Wen, Hongyi Pan, Dallas Dominguez et al.CHI 2025 · 13 citations

Related papers

  1. Simulated Students in Tutoring Dialogues: Substance or Illusion?Alexander Scarlatos, Jaewook Lee, Simon Woodhead, Andrew LanACL 2026 · 6 citations
  2. EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue FrameworkYao Shi, Rongkeng Liang, Yong XuACL 2025 · 18 citations
  3. From Solver to Tutor: Evaluating the Pedagogical Intelligence of LLMs with KMP-BenchWeikang Shi, Houxing Ren, Junting Pan, Aojun Zhou et al.AAAI 2026
  4. Inductive-Deductive Strategy Reuse for Multi-Turn Instructional DialoguesJiao Ou, Jiayu Wu, Che Liu, Fuzheng Zhang et al.EMNLP 2024 · 2 citations
  5. AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level EvaluationTiancheng Huang, Ruisheng Cao, Yuxin Zhang, Zhangyi Kang et al.ICLR 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines