Scholarlink

In this work, we propose a hybrid AI system consisting of a multi-agent system simulating students during an exam and a teacher monitoring them, as well as an evolutionary algorithm that finds classroom arrangements which minimize cheating incentives. The students will answer the exam based on how much knowledge they have about the topic of the exam. In our simulation, then they enter a decision phase in which, for those questions they don’t know the answer to, they will either cheat or answer by guessing. If a student gets caught cheating, his/her exam will be cancelled. The purpose of this study is to examine the question of how different monitoring behaviors on the part of the teacher affect the cheating behaviors of students. The results of this study show that an unbiased teacher, that is, a teacher that monitors every student with the same probability, produces minimal cheating incentives for students.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Finding Optimal Classroom Arrangements to Minimize Cheating in Exams Using a Hybrid AI System

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Pablo León Alazraki Salas,
  • Andrés Gómez de Silva Garza

摘要

In this work, we propose a hybrid AI system consisting of a multi-agent system simulating students during an exam and a teacher monitoring them, as well as an evolutionary algorithm that finds classroom arrangements which minimize cheating incentives. The students will answer the exam based on how much knowledge they have about the topic of the exam. In our simulation, then they enter a decision phase in which, for those questions they don’t know the answer to, they will either cheat or answer by guessing. If a student gets caught cheating, his/her exam will be cancelled. The purpose of this study is to examine the question of how different monitoring behaviors on the part of the teacher affect the cheating behaviors of students. The results of this study show that an unbiased teacher, that is, a teacher that monitors every student with the same probability, produces minimal cheating incentives for students.