Date
Publisher
arXiv
Generative social robots (GSRs) powered by large language models offer new possibilities for personalized tutoring in higher education, but also introduce risks related to misinformation, missing transparency, or reinforcing incorrect student responses. Prior work identified knowledge-based design (KBD) requirements that define the informational prerequisites for GSRs to manifest responsible and effective tutoring behavior in higher education. In this paper, we operationalized selected KBD requirements in the Reachy Mini robot platform through system prompting, retrieval-augmented generation, and stateful prompt orchestration. As a result, we present Teachy Mini, a GSR tutoring system that was developed using KBD. To test the system, we conducted a preliminary evaluation study. Participants (N = 24) completed a robot-guided learning session about research methodologies. They learned either with Teachy Mini or with a control version that did not follow KBD principles. Teachy Mini was perceived as significantly more aligned with responsible tutoring behavior than the control robot. Moreover, a manipulation check illustrated that Teachy Mini used personalization, slide-grounded explanations, Socratic questioning, affective support, and learner-anchored feedback more consistently than the control robot. No significant between-condition differences were found in system acceptance, intrinsic motivation, or learning effectiveness, although exploratory analyses suggested a positive effect of KBD on objective learning gains when accounting for learner preferences. Overall, the study offered an initial implementation and preliminary evaluation of KBD for GSR tutoring, indicating that KBD can shape responsible robot behavior and potentially increase learning effectiveness in robot-supported learning.
Study at a glance
- Question: Does integrating structured knowledge into a generative tutoring robot improve students' learning, acceptance, and perceptions of responsible tutoring behavior?
- Setting and data: 24 university students and recent graduates in Germany or Switzerland, March to April 2026.
- Method: Randomized controlled trial (between-subjects laboratory experiment) with qualitative content analysis of interaction transcripts.
Why it matters
Generative social robots can provide personalized tutoring, but risk generating inaccurate responses and reinforcing errors. Practical system configurations are needed to ensure robots exhibit responsible tutoring behaviors in higher education.
Key findings
- Students rated the knowledge-based robot significantly higher on perceived alignment with responsible tutoring behavior than the control robot (d = 0.930).
- No significant differences appeared between conditions in system acceptance, intrinsic learning motivation, or objective and subjective learning effectiveness in the main analysis.
- The knowledge-based robot produced zero factual errors and cited slides consistently, whereas the control robot made factual errors in 6.1% of its messages and never provided sources.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
