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

arXiv: https://arxiv.org/abs/2507.05528 · HTML: https://mlsanity.com/paper/2507.05528/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 14 of 14)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery](https://mlsanity.com/paper/2405.09783/) (2024)
- [SciAgent: Tool-augmented Language Models for Scientific Reasoning](https://mlsanity.com/paper/2402.11451/) (2024)
- [NEWTON: Are Large Language Models Capable of Physical Reasoning?](https://mlsanity.com/paper/2310.07018/) (2023)
- [CGMI: Configurable General Multi-Agent Interaction Framework](https://mlsanity.com/paper/2308.12503/) (2023)
- [Empowering Personalized Learning through a Conversation-based Tutoring System with Student Modeling](https://mlsanity.com/paper/2403.14071/) (2024)
- [ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback](https://mlsanity.com/paper/2402.10980/) (2024)
- [Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation](https://mlsanity.com/paper/2502.02780/) (2025)
- [Learning-by-teaching with ChatGPT: The effect of teachable ChatGPT agent on programming education](https://mlsanity.com/paper/2412.15226/) (2024)
- [Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality](https://mlsanity.com/paper/2405.13034/) (2024)

## Built on by (most cited first, 5 of 5)

- [Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis](https://mlsanity.com/paper/2508.11398/) (2025)
- [Opportunities and Challenges of LLMs in Education: An NLP Perspective](https://mlsanity.com/paper/2507.22753/) (2025)
- [ClinTutor-R1: Advancing Scalable and Robust One-to-Many Alignment in Clinical Socratic Education](https://mlsanity.com/paper/2512.05671/) (2025)
- [SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice](https://mlsanity.com/paper/2606.04155/) (2026)
- [Lect=uraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching](https://mlsanity.com/paper/2606.16428/) (2026)

## Abstract (arXiv)

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.