arXiv cs.AI· Ethan Mollick, Lilach Mollick, Ben Przystanski, LJ Ciccarelli, Natalie Bach, Laura Zarrow·· 1 天前AI 评分38
Primer：面向教师主导的教育模拟创作的开源 AI 框架
Primer: An AI Framework for Instructor-Centered Educational Simulation Creation
AI 导读
开源系统 Primer 发布，这是一个不绑定特定 LLM 的 AI 框架，帮助教师创建自适应教育模拟。它采用多智能体系统，围绕执行教师的教学意图贯穿整个学习体验，由教师提供学科、课程与学生知识，生成式 AI 产出可响应的练习变体。系统支持包括本地和开源模型在内的多种 AI 模型，提示词与 GitHub 仓库一并开放。
正文 · 原文
Abstract:Educational simulations are a well-established pedagogical technique that gives learners opportunities to apply knowledge, respond to challenges, and reflect on their performance. High-quality simulations, however, are difficult to build, requiring instructor input, scenario design, character development, scaffolding, technical implementation, and repeated revision. This paper presents Primer, an open-source, LLM-agnostic AI-supported system that helps educators create adaptive educational simulations. Educators contribute their knowledge of the subject, lesson, and students, while generative AI produces responsive variations of practice for students. Primer uses a multi-agent system centered around executing educator's instructional intent through the entire learning experience. We hope that by releasing Primer as an open-source system, including its prompts and GitHub repository, we provide a foundation for development and research on educator-in-the-loop AI authoring, multi-agent educational workflows, and simulation-based pedagogy. Further, by allowing the use of various AI models, including local and open source models, we provide the opportunity for implementation under varied governance regimes. Primer points toward a model of educational AI in which instructors can create locally grounded practice opportunities based on their own materials, goals, examples, and knowledge of students.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.16986 [cs.AI] |
| (or arXiv:2611.16986v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16986 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ethan Mollick [view email]
[v1]
Thu, 12 Nov 2026 15:50:46 UTC (1,106 KB)
来源：arXiv cs.AI · arxiv.org