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.

翻译：LLM教学代理正在迅速普及，然而近期的研究对其是否遵循既定学习理论及其教育价值提出了质疑。关于认知卸载、过度依赖和“投机取巧”行为的担忧持续存在，且在很大程度上未得到解决。为此，我们开发了Copa——一种面向STEM+C学习的代理型、多智能体、多模态协作同伴代理。Copa建立在“证据-决策-反馈”（EDF）框架之上，将其交互根植于社会认知理论和社会建构主义，通过自适应对话式支持促进意义建构，而非追求答案。在一项真实的高中计算建模研究（n=33对）中，我们证明了Copa：（1）能够支持学生建立信心并使其具备用语言表达概念性理解的能力，而不会导致依赖；（2）提供针对学习者的个性化自适应反馈，且该反馈可基于学生的多模态输入数据进行解释。这些发现表明，理论引导的多模态LLM代理是向课堂AI整合迈出的有前景的一步，它能增强而非取代学生的推理能力。