外观
论文arXiv 2610.0702724 天前
教育未来工程师了解 LLMs：一个可扩展工作坊
提出可扩展游戏化工作坊，让工程硕士生通过网页提示 LLM 完成网格导航，并以问卷和 Spot 演示验证。
Boston Dynamics Spot原文链接：Educating future engineers about LLMs: A scalable workshop（arXiv 2610.07027 · 发布日期：2026-10-04）
Educating future engineers about LLMs: A scalable workshop
提出可扩展游戏化工作坊，让工程硕士生通过网页提示 LLM 完成网格导航，并以问卷和 Spot 演示验证。
核心要点
- 动机是 LLMs 融入工程流程后，学生需要实践批判性人机协作。
- 方法是用移动网页界面，让学生为非推理和推理 LLM 编写提示以求解导航任务。
- 系统返回机器人可执行计划、轨迹可视化和自动评分，并最终进行 Spot 现场演示。
- 问卷显示学习和参与度较高，提示分析显示学生策略随任务复杂度变化；代码已开源。
验证范围与局限：验证范围为10场面向工程硕士生的工作坊、网格导航任务和一次 Boston Dynamics Spot 真机演示。
英文摘要 (Abstract)
As large language models (LLMs) are increasingly integrated into engineering workflows, students require hands-on experience to learn how to collaborate with them critically. This paper presents a scalable gamified workshop designed for engineering Master's students to practice human-AI collaboration in navigation planning. Using a mobile web interface across 10 workshop sessions, a total of 226 students wrote prompts for a non-reasoning and a reasoning LLM to solve grid-based navigation tasks of increasing complexity. The system returned robot-executable plans, trajectory visualizations, and automated scoring, culminating in a live demonstration on a Boston Dynamics Spot robot. In a post-workshop questionnaire, 81.5% reported substantial learning and 91.0% reported high engagement. Analysis of the submitted prompts revealed that students changed their strategies from step-by-step instructions for the non-reasoning LLM toward providing higher-level guidance for complex problem-solving tasks. We conclude that such interactive simulation-to-reality environments are viable for teaching the verification and collaboration skills necessary for responsible LLM use in engineering. Code is available at: https://github.com/renchizhhhh/LLM-robotics-workshop
作者：Renchi Zhang, Joost de Winter, T. Dicke, Dimitra Dodou, Yke Bauke Eisma
来源
本页事实对应的公开页面，以原文为准。