Unveiling interaction patterns between students and generative AI teachable agent: Focusing on students' agency and AI agents' authority

Выявление закономерностей взаимодействия студентов с обучаемыми агентами на основе генеративного искусственного интеллекта: акцент на субъектности студентов и авторитетности агентов ИИ
Jinhee Kim, Yukyeong Song, Wanli Xing, Taehyun Kim, Hai Li, Chenglu Li
2026-02-09

AI authorityAI teachable agentsAI-assisted learning environmentssequential interaction analysisstudent agency
Abstract With the growing integration of artificial intelligence (AI) in education, conversational AI agents are increasingly used to support student learning. This study examines how interactions with AI teachable agents are temporally associated with students' agency and how these associations relate to students' learning outcomes. Analysing 7188 discussion threads containing over 117,000 text utterances, we explore the relationship between AI authority and student agency using classification and regression models. Findings reveal that AI authority is significantly associated with subsequent student agency levels; however, increased student agency does not lead to changes in AI authority. Sequential interaction analysis shows that students initially demonstrate higher agency in response to authoritative AI prompts, though this effect stabilizes over time. In addition, higher student agency is associated with more elaboration and clarification talk but also with increased off‐task discussions, which slightly hinder learning gains. These findings underscore the need for balancing structured AI guidance with opportunities for student autonomy. This research contributes critical insights into designing AI‐assisted learning environments that foster both engagement and effective learning outcomes.
1
AI authority was significantly associated with students’ subsequent agency levels, whereas increased student agency did not alter AI authority.
2
Higher student agency also increased off-task discussion, which slightly hindered learning gains.
3
Higher student agency corresponded to more elaboration and clarification talk, indicating richer learning-related interaction.
4
Students initially showed higher agency in response to authoritative AI prompts, but this effect stabilized over time.
5
The findings support balancing structured AI guidance with opportunities for student autonomy in AI-assisted learning environments.

student interactions with generative AI teachable agents in AI-assisted learning environments

temporal relationships between AI authority and student agency, and their associations with learning outcomes and discourse patterns

Publication Details
Publication Date
2026-02-09
Journal
Publisher
ISSN
Cited by
18
Access Type
Author Information
Authors
Jinhee Kim
Yukyeong Song
Wanli Xing
Taehyun Kim
Hai Li
Chenglu Li
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%