Student Project Tracks

Big Picture

This summer we are building a system to study how students learn when working with AI.

The central idea is simple: AI should not just give answers. It should guide how students think. At the same time, we should be able to observe and measure that thinking process.

Each project is designed to contribute to a research study and lead to a publishable paper.

Project 1: Epistemic Trace System

What you will build

You will build the data and analysis layer of the system. This includes a structured record of student activity during problem solving.

The system will capture:

  • Student answers
  • Revisions
  • AI feedback
  • Timing

These will be organized into an event log that records:

  • Who did what
  • When it happened
  • The surrounding context

You will also build tools to:

  • Export data
  • Replay sessions
  • Analyze patterns in student work

Why this matters

This project provides the foundation for all research.

Without high-quality data, we cannot make strong claims. With it, we can support multiple studies.

Research directions

  • Analyze how students improve over time when guided by AI
  • Study how different types of AI intervention affect learning
  • Examine how role-based guidance affects collaboration
  • Model learning trajectories across multiple attempts

Possible paper titles

  • Adaptive AI-Guided Collaborative Learning: Analyzing Student Reasoning Through Epistemic Traces
  • The Impact of Timing and Specificity in AI Guidance on Student Problem Solving
  • Role-Based AI Guidance in Collaborative Learning: Effects on Participation and Reasoning
  • From Attempt to Understanding: Modeling Student Learning Trajectories in AI-Guided Activities
  • Measuring Revision Depth and Learning Progress in AI-Supported Problem Solving
  • Identifying Patterns of Productive Struggle in Collaborative Learning Environments

Research questions

  • How do students improve their answers over time
  • What does it mean for a student to be stuck
  • What patterns indicate meaningful learning

Best fit

This project fits students who enjoy building systems, working with structured data, and conducting detailed analysis.

Project 2: Adaptive AI Guidance System

What you will build

You will build the system that determines how AI provides guidance to students.

The system will generate feedback based on:

  • Time spent
  • Student behavior
  • Previous attempts

Guidance will evolve over time:

  • Early: open-ended prompts
  • Middle: hints
  • Late: more direct help

You will also design a configurable framework that supports:

  • Different guidance strategies
  • Role-based prompts within a group

Why this matters

This project focuses on how AI affects learning and how guidance should be designed.

Research directions

  • Study when AI should intervene
  • Analyze how timing affects learning outcomes
  • Explore how feedback detail influences performance
  • Examine role-based guidance in group settings
  • Model dynamic guidance strategies

Possible paper titles

  • Adaptive AI Guidance in Collaborative Learning: Effects of Timing and Feedback Specificity
  • When Should AI Help? Evaluating the Timing of Interventions in AI-Supported Learning
  • Designing Time-Based AI Interventions to Support Student Problem Solving
  • From Hints to Guidance: The Impact of Progressive AI Scaffolding on Student Performance
  • Role-Based AI Guidance in Collaborative Learning Environments
  • Supporting Group Roles with AI: Effects on Participation and Learning Outcomes
  • Adaptive Scaffolding with AI: Evaluating Dynamic Guidance Strategies in Collaborative Learning
  • Balancing Autonomy and Support: An Experimental Study of AI Intervention Strategies

Research questions

  • When should AI intervene
  • How does timing affect learning
  • Does more detailed guidance help or hurt

Best fit

This project fits students who are interested in AI behavior, experimentation, and understanding how people learn.

Important Notes

  • These projects are closely connected
  • All student activity must be recorded for research
  • Each project should contribute to a research paper

What Success Looks Like

By the end of the summer:

  • A working system used in real activities
  • Data collected from student interactions
  • Initial analysis results
  • A draft of a research paper

How to Choose

Choose based on how you prefer to think about problems.

  • If you are most interested in understanding what students are doing → Project 1
  • If you are most interested in designing how AI should guide students → Project 2

Scroll to Top