arXiv cs.MA· Clayton Cohn, Surya Rayala, Siyuan Guo, Hanchen David Wang, Naveeduddin Mohammed, Umesh Timalsina, Shruti Jain, Ryan Li, Angela Eeds, Menton Deweese, Pamela J. Osborn Popp, Rebekah Stanton, Shakeera Walker, Ashwin T S, Meiyi Ma, Gautam Biswas·· 12 小时前AI 评分27
CoSMoAgent：基于 GPT-5 的理论引导 LLM 教学智能体，支持开放式 STEM+C 学习
A Theory-Guided LLM Pedagogical Agent Supporting Open-Ended STEM+C Learning
AI 导读
研究团队提出 CoSMoAgent（Computational Science Modeling Agent），一个基于 GPT-5 的多智能体“知识型同伴”，以 Evidence-Decision-Feedback（EDF）框架为理论基础，面向高中运动学建模。
正文
Authors:Clayton Cohn, Surya Rayala, Siyuan Guo, Hanchen David Wang, Naveeduddin Mohammed, Umesh Timalsina, Shruti Jain, Ryan Li, Angela Eeds, Menton Deweese, Pamela J. Osborn Popp, Rebekah Stanton, Shakeera Walker, Ashwin T S, Meiyi Ma, Gautam Biswas
Abstract:Open-ended learning environments (OELEs) can support STEM+C (science, technology, engineering, mathematics, and computing) inquiry through activities such as computational modeling, which requires students to translate disciplinary knowledge across domains and coordinate scientific concepts with computational representations. However, this is often challenging for students, many of whom require support during problem solving. In this exploratory study, we present CoSMoAgent (Computational Science Modeling Agent), a GPT-5-based multi-agent knowledgeable peer for high-school kinematics modeling grounded in the Evidence-Decision-Feedback (EDF) framework. CoSMoAgent goes beyond dialogue: it infers students' strategies, learner states, and knowledge gaps from environment logs and evolving model states. These inferences guide dialogue policies that prioritize probing and hints over direct answers. We deployed CoSMoAgent with 11 dyads across three modeling tasks (33 dyad-sessions), using a mixed-methods design to examine learning outcomes, processes, and adaptive scaffolding. As task mastery increased, students verbalized their understanding more successfully and sought help less often, and the agent's policies shifted from probing toward suggesting actions and extending reasoning. Two contrasting case-study dyads followed markedly different problem-solving paths, yet achieved similar learning gains despite substantial differences in task mastery and CoSMoAgent interaction. Students valued the agent's questions but were often frustrated by its withholding of answers. The study contributes a design pattern and classroom evidence for LLM scaffolding grounded in environmental activity rather than chat alone within an open-ended modeling environment.
| Comments: | Submitted to Educational Technology Research and Development (ETR&D). Currently under review |
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2605.30539 [cs.MA] |
| (or arXiv:2605.30539v2 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2605.30539 arXiv-issued DOI via DataCite |
Submission history
From: Clayton Cohn [view email]
[v1]
Thu, 28 May 2026 20:13:18 UTC (2,687 KB)
[v2]
Sat, 24 Oct 2026 21:04:55 UTC (2,274 KB)
来源：arXiv cs.MA · arxiv.org