A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (3) · 1757-1765
DOI: 10.1609/aaai.v40i3.37154 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Clayton Cohn und 8 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref).
Abstract (Originalsprache)
Large language models (LLMs) present new opportunities for creating pedagogical agents that engage in meaningful dialogue to support student learning. However, current LLM systems used in classrooms often lack the solid theoretical foundations found in earlier intelligent tutoring systems. To bridge this gap, we propose a framework that combines Evidence-Centered Design with Social Cognitive Theory and Zone of Proximal Development for adaptive scaffolding in LLM-based agents focused on STEM+C learning. We instantiate this framework with Inquizzitor, an LLM-based formative assessment agent that integrates human-AI hybrid intelligence and provides feedback grounded in cognitive science principles. Our findings show that Inquizzitor delivers high-quality assessment and interaction aligned with core learning theories, offering effective guidance that students value. This research demonstrates the potential for theory-driven LLM integration in education, highlighting the ability of these systems to provide adaptive and principled instruction.
Zitieren
APA
Cohn, C., Rayala, S., Srivastava, N., Fonteles, J. H., Jain, S., Luo, X., Mereddy, D., Mohammed, N., & Biswas, G. (2026). A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents. Proceedings of the AAAI Conference on Artificial Intelligence, 40(3), 1757-1765. https://doi.org/10.1609/aaai.v40i3.37154
Vancouver
Cohn C, Rayala S, Srivastava N, Fonteles JH, Jain S, Luo X, et al. A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(3):1757-1765. doi:10.1609/aaai.v40i3.37154
BibTeX
@article{Cohn2026,
author = {Cohn, Clayton and Rayala, Surya and Srivastava, Namrata and Fonteles, Joyce Horn and Jain, Shruti and Luo, Xinying and Mereddy, Divya and Mohammed, Naveeduddin and Biswas, Gautam},
title = {A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {3},
pages = {1757--1765},
doi = {10.1609/aaai.v40i3.37154}
}
EUVIMED