# A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-Reliance

arXiv: https://arxiv.org/abs/2605.30539 · HTML: https://mlsanity.com/paper/2605.30539/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 76 references that are in the map.
- First posted on arXiv 28 May 2026.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 5 of 5)

- [Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task](https://mlsanity.com/paper/2506.08872/) (2025)
- [Measuring Agents in Production](https://mlsanity.com/paper/2512.04123/) (2025)
- [A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization](https://mlsanity.com/paper/2410.02165/) (2024)
- [Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)](https://mlsanity.com/paper/2505.17238/) (2025)
- [Multimodal Methods for Analyzing Learning and Training Environments: A Systematic Literature Review](https://mlsanity.com/paper/2408.14491/) (2024)

## Abstract (arXiv)

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.