Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.30539 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910270815731712 |
|---|---|
| author | Cohn, Clayton Rayala, Surya Guo, Siyuan Wang, Hanchen David Mohammed, Naveeduddin Timalsina, Umesh Jain, Shruti Li, Ryan Eeds, Angela Deweese, Menton Popp, Pamela J. Osborn Stanton, Rebekah Walker, Shakeera S, Ashwin T Ma, Meiyi Biswas, Gautam |
| author_facet | Cohn, Clayton Rayala, Surya Guo, Siyuan Wang, Hanchen David Mohammed, Naveeduddin Timalsina, Umesh Jain, Shruti Li, Ryan Eeds, Angela Deweese, Menton Popp, Pamela J. Osborn Stanton, Rebekah Walker, Shakeera S, Ashwin T Ma, Meiyi Biswas, Gautam |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30539 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-Reliance Cohn, Clayton Rayala, Surya Guo, Siyuan Wang, Hanchen David Mohammed, Naveeduddin Timalsina, Umesh Jain, Shruti Li, Ryan Eeds, Angela Deweese, Menton Popp, Pamela J. Osborn Stanton, Rebekah Walker, Shakeera S, Ashwin T Ma, Meiyi Biswas, Gautam Multiagent Systems 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. |
| title | A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-Reliance |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2605.30539 |