AI peer agent seen as supportive partner in math learning
Exploring AI Peer in Collaborative Mathematics Learning
Human-Computer Interaction
Summary
It can be hard for people to see an AI as a true partner when solving math problems together. This paper looks at what makes an AI feel more like a teammate. The authors found that people trust the AI more when it acts like a real person—making mistakes, sharing control, and thinking out loud—rather than just giving correct answers or instructions. These insights help design AI that can better support collaborative learning.
What this means in practice
- •For educational technology developers: Create AI learning partners that foster trust and collaboration by mimicking peer-like behaviors such as imperfection and shared reasoning.$Commercial implications: Enables development of AI-driven math tutoring platforms that feel more like supportive peers, improving user engagement and learning outcomes.
- •For software teams building chatbots: Design chatbots with adaptive personalities that modulate social behaviors to be perceived as collaborative peers rather than authoritative tutors.
Authors
Yiran Lin, Ye Deng, Ziqi Pan, Yongan Yu, Alexandra I. Cristea
Abstract
Artificial intelligence (AI) agents are increasingly explored as collaborative learning partners in mathematics education, yet it remains unclear what makes an AI recognizable as a peer. This study examines how domain experts perceive and interact with an adaptive LLM-based peer agent combining a Big Five-informed persona with motivational state modulation for collaborative mathematics problem solving. Through thematic analysis of expert interviews, we identify conditions shaping peer perceptions, including emotional safety, shared control, and collaborative reasoning. Participants primarily judged the AI through its social behavior rather than mathematical capabilities. The AI was perceived more as a peer when it created a non-judgmental space, engaged in tentative reasoning, displayed appropriate imperfection, and respected participants' pace. Conversely, blind agreement and over-instruction reduced trust and shifted perceptions toward a tutor role. Based on these findings, we propose human-centered design dimensions for AI peer agents to guide future peer-oriented learning systems.