Chrysalis: A Unified System for Comparing Active Teaching and Passive Learning with AI Agents in Education

2025-10-06

AI Summary

This study investigates how two AI-mediated pedagogical paradigms—learning-by-teaching (active instruction) and tutored learning (passive tutoring)—differentially impact students’ learning experience and higher-order cognitive traits, particularly intellectual humility. Method: Leveraging the unified Chrysalis framework, we conducted a within-subjects experiment with 36 participants, comparing large language models deployed either as AI tutors or as teachable AI agents across multidisciplinary tasks. Contribution/Results: We find that active instruction significantly enhances metacognitive reflection and cognitive openness, fostering deeper knowledge construction and greater intellectual humility; in contrast, passive tutoring excels at facilitating immediate knowledge acquisition and task engagement. Our contributions are threefold: (1) a scalable, dual-mode AI education architecture; (2) empirical evidence revealing distinct mechanisms by which role-switching in human–AI interaction shapes advanced psychological traits; and (3) theoretically grounded, empirically validated design principles for AI agent roles in educational contexts.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

AI-assisted learning has seen a remarkable uptick over the last few years, mainly due to the rise in popularity of Large Language Models (LLMs). Their ability to hold long-form, natural language interactions with users makes them excellent resources for exploring school- and university-level topics in a dynamic, active manner. We compare students' experiences when interacting with an LLM companion in two capacities: tutored learning and learning-by-teaching. We do this using Chrysalis, an LLM-based system that we have designed to support both AI tutors and AI teachable agents for any topic. Through a within-subject exploratory study with 36 participants, we present insights into student preferences between the two strategies and how constructs such as intellectual humility vary between these two interaction modes. To our knowledge, we are the first to conduct a direct comparison study on the effects of using an LLM as a tutor versus as a teachable agent on multiple topics. We hope that our work opens up new avenues for future research in this area.

Problem

• Compares AI tutoring versus AI teaching for student learning experiences
• Examines student preferences between active teaching and passive learning
• Analyzes how intellectual humility varies across different AI interaction modes

Innovation

• LLM-based system supports both tutoring and teaching
• Direct comparison of AI tutor versus teachable agent
• Unified platform enables active teaching and passive learning