A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-Reliance
This work addresses the problem of LLM pedagogical agents potentially causing cognitive offloading and over-reliance in students, offering a theory-guided alternative for high school STEM+C education.
The paper introduces Copa, a multi-agent, multimodal LLM pedagogical agent designed for STEM+C learning, built on the Evidence-Decision-Feedback (EDF) framework. In a study with 33 high school dyads, Copa supported students' confidence and conceptual understanding without fostering dependence, and provided adaptive, personalized, and interpretable feedback.
LLM pedagogical agents are proliferating, yet recent findings have raised questions about their adherence to established theories of learning and, by extension, their educational value. Concerns regarding cognitive offloading, over-reliance, and "gaming" behaviors persist and remain largely unaddressed. In response, we developed Copa, an agentic, multi-agent, multimodal Collaborative Peer Agent for STEM+C learning. Copa is built on top of the Evidence-Decision-Feedback (EDF) framework, grounding its interactions in Social Cognitive Theory and Social Constructivism and promoting sense-making through adaptive, dialogic support rather than answer-seeking. In an authentic high school computational-modeling study (n=33 dyads), we demonstrate that Copa (1) supports students' confidence building and ability to verbalize conceptual understanding without causing dependence; and (2) provides adaptive feedback personalized to learners that is interpretable with respect to students' multimodal input data. These findings position theory-guided, multimodal LLM agents as a promising path toward classroom AI integration that amplifies students' reasoning rather than replacing it.