Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.05271 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918155463426048 |
|---|---|
| author | Arun, Prashanth Vader, Vinita Xu, Erya McCready-Branch, Brent Seabrook, Sarah Scholz, Kyle Crisan, Ana Grossmann, Igor Poupart, Pascal |
| author_facet | Arun, Prashanth Vader, Vinita Xu, Erya McCready-Branch, Brent Seabrook, Sarah Scholz, Kyle Crisan, Ana Grossmann, Igor Poupart, Pascal |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_05271 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chrysalis: A Unified System for Comparing Active Teaching and Passive Learning with AI Agents in Education Arun, Prashanth Vader, Vinita Xu, Erya McCready-Branch, Brent Seabrook, Sarah Scholz, Kyle Crisan, Ana Grossmann, Igor Poupart, Pascal Human-Computer Interaction 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. |
| title | Chrysalis: A Unified System for Comparing Active Teaching and Passive Learning with AI Agents in Education |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2510.05271 |