Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Mentigo: An Intelligent Agent for Mentoring Students in the Creative Problem Solving Process

Siyu Zha, Yujia Liu, Chengbo Zheng, Jiaqi XU, Fuze Yu, Jiangtao Gong, Yingqing XU

TL;DR

Mentigo, an AI-driven mentor agent designed to guide middle school students through the CPS process, is developed using a dataset of real classroom interactions to inform Mentigo’s dynamic mentoring framework powered by large language models (LLMs).

Abstract

With the increasing integration of large lauguage models (LLMs) in education, there is growing interest in using AI agents to support student learning in creative tasks. This study presents an interactive Mentor Agent system named Mentigo, which is designed to assist middle school students in the creative problem solving (CPS) process. We created a comprehensive dataset of real classroom interactions between students and mentors, which include the structured CPS task management, diverse guidance techniques, personalized feedback mechanisms. Based on this dataset, we create agentic workflow for the Mentigo system. The system's effectiveness was evaluated through a comparative experiment with 12 students and reviewed by five expert teachers. The Mentigo system demonstrated significant improvements in student engagement and creative outcomes. The findings provide design implications for leveraging LLMs to support CPS and offer insights into the application of AI mentor agents in educational contexts.

Mentigo: An Intelligent Agent for Mentoring Students in the Creative Problem Solving Process

TL;DR

Mentigo, an AI-driven mentor agent designed to guide middle school students through the CPS process, is developed using a dataset of real classroom interactions to inform Mentigo’s dynamic mentoring framework powered by large language models (LLMs).

Abstract

With the increasing integration of large lauguage models (LLMs) in education, there is growing interest in using AI agents to support student learning in creative tasks. This study presents an interactive Mentor Agent system named Mentigo, which is designed to assist middle school students in the creative problem solving (CPS) process. We created a comprehensive dataset of real classroom interactions between students and mentors, which include the structured CPS task management, diverse guidance techniques, personalized feedback mechanisms. Based on this dataset, we create agentic workflow for the Mentigo system. The system's effectiveness was evaluated through a comparative experiment with 12 students and reviewed by five expert teachers. The Mentigo system demonstrated significant improvements in student engagement and creative outcomes. The findings provide design implications for leveraging LLMs to support CPS and offer insights into the application of AI mentor agents in educational contexts.
Paper Structure (42 sections, 5 figures, 8 tables)

This paper contains 42 sections, 5 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Students‘ Creative Problem-Solving
  4. Generative AI for Student's Learning
  5. Formative Interview & Design Goals
  6. Participants and Procedure
  7. Findings
  8. Design Goals
  9. The Mentigo Agent System
  10. Mentigo Dataset Construction
  11. [DG1]Ensure Structured Task Management for Clarity and Compliance
  12. [DG2]Diversify Guided Strategies for Enhanced CPS Skills
  13. [DG3]Provide Personalize Feedback through Dynamic Student State
  14. Mentor Agent Workflow
  15. [DG4]Encourage Deep Cognitive Engagement and Conceptual Mastery
  16. ...and 27 more sections

Figures (5)

  • Figure 1: Framework of Mentigo Agent.The Controller Agent manages the flow of student interactions through three functions: Stage Decision, State Determine, and Strategy Selection. The Mentor Agent provides tailored feedback and guidance prompts based on students' progress. The Database stores information on different Stages, States, and Strategies to support adaptive decision-making, with all interactions facilitated by an LLM.
  • Figure 2: Prompts for Controller Agent
  • Figure 3: Prompts for Mentor Agent
  • Figure 4: Distribution of Student States and Guided Strategies Frequencies
  • Figure 5: Illustration of Student P1's Dialogues with Mentigo (Left) and the Baseline System (Right) at the Same Stage of Different Tasks