From AI Assistance to Independent Mastery
Designing an AI Learning Coach for College Mathematics Readiness
Project Introduction
Generative AI is rapidly changing how students learn mathematics. Students can now ask systems such as ChatGPT or Gemini to explain a concept, demonstrate a solution, identify an error, generate practice problems, or guide them through a difficult calculation. At the same time, established educational platforms such as ALEKS, WebAssign, Connect, MyLab, and WileyPLUS provide structured practice, assessment, and—in some cases—adaptive learning based on students’ demonstrated knowledge.
These technologies can be viewed as several stages in the evolution of digital mathematics learning:
Generation 1: Online Homework and Automatic Assessment
\[
\text{Problem}
\rightarrow
\text{Student Response}
\rightarrow
\text{Automatic Grading}
\rightarrow
\text{Feedback}
\]
Systems such as WebAssign made large-scale online mathematics practice and assessment practical, while instructors largely determine what students study.
Generation 2: Adaptive Learning
\[
\text{Diagnose}
\rightarrow
\text{Estimate Knowledge}
\rightarrow
\text{Select Appropriate Material}
\rightarrow
\text{Practice}
\rightarrow
\text{Reassess}
\]
Systems such as ALEKS add individualized diagnosis and adaptive learning paths. The system increasingly determines what each student is ready to learn and where additional practice is needed.
Generation 3: Conversational AI Learning
\[
\text{Student Struggles}
\rightarrow
\text{AI Conversation}
\rightarrow
\text{Explanation or Hint}
\rightarrow
\text{Continued Practice}
\]
Generative AI makes individualized explanations and interactive tutoring available on demand. A student can ask follow-up questions, request alternative explanations, receive hints, and engage in a conversation tailored to the immediate difficulty.
These developments create tremendous opportunities, but they also introduce a fundamental educational problem:
A student being able to solve a problem with AI assistance is not the same as the student having mastered the mathematics.
The purpose of this project is therefore not simply to develop another AI mathematics tutor. Instead, it will investigate how an AI Learning Coach can help students progress from assisted learning to durable, independent mathematical mastery.
The Proposed Fourth Stage: AI That Builds Independence
The central learning cycle of the proposed system is:
\[
\boxed{\text{Diagnose prerequisite knowledge}}
\]
\[
\downarrow
\]
\[
\boxed{\text{Provide personalized AI coaching}}
\]
\[
\downarrow
\]
\[
\boxed{\text{Provide graduated assistance}}
\]
\[
\downarrow
\]
\[
\boxed{\text{Gradually fade assistance}}
\]
\[
\downarrow
\]
\[
\boxed{\text{Require AI-free practice}}
\]
\[
\downarrow
\]
\[
\boxed{\text{Verify independent mastery}}
\]
\[
\downarrow
\]
\[
\boxed{\text{Check retention and transfer}}
\]
The AI coach would therefore be designed with an unusual long-term objective: to make its own assistance progressively less necessary.
When students struggle, the system could diagnose whether the difficulty comes from the current topic or from an underlying prerequisite. Instead of immediately presenting a complete solution, it could provide progressively stronger levels of support—questions, small hints, larger hints, explanations, worked substeps, or examples.
As students improve, that assistance would deliberately decrease. Eventually, students would solve new problems without AI assistance. Their performance on these independent problems—not merely their success while receiving AI help—would provide evidence of mastery.
Initial Focus: Precalculus Readiness for College Mathematics
The first implementation will focus on foundational precalculus skills needed for success in college mathematics, particularly calculus.
Students can reach college calculus while retaining significant gaps in algebra, functions, trigonometry, arithmetic fluency, and related prerequisite skills. These gaps may become obstacles even when students understand the new calculus concept being taught.
The proposed system could identify such prerequisite weaknesses and provide short, targeted remediation rather than requiring students to repeat an entire algebra or precalculus course.
For example, a student struggling with a difference quotient may actually have difficulty expanding
\[
(x+h)^2.
\]
Rather than treating this simply as an error in calculus, the system could diagnose the underlying algebraic weakness, provide targeted coaching and practice, verify independent mastery of binomial expansion, and then return the student to the original calculus problem.
This suggests a broader goal:
Provide the right prerequisite mathematics, to the right student, at the right time, with the right amount of assistance—and then determine whether the student can perform independently.
A Human–AI Interaction Problem
This is fundamentally an HCI problem as well as a mathematics-education problem.
The project will investigate questions such as:
- When should AI provide an explanation, and when should it ask the student a question?
- How much assistance should be provided after an incorrect response?
- How can the system distinguish productive struggle from unproductive frustration?
- When should hints become more explicit?
- When should assistance begin to fade?
- How should students understand the difference between AI-assisted proficiency and independent mastery?
- How should progress and mastery be visualized?
- How can AI encourage students to think rather than simply obtain answers?
- How can students retain control and agency while benefiting from adaptive guidance?
- Can students transfer a repaired prerequisite skill to authentic college mathematics problems?
The project therefore combines mathematics education, learning science, adaptive learning, generative AI, and human–computer interaction.
Beyond the Initial Learning Coach
The initial HCI project should remain focused and feasible rather than attempting to build a complete learning-management system. However, it fits within a larger vision for AI-supported mathematics education consisting of three connected components:
1. AI-Assisted Learning
Students use AI freely and productively to understand concepts, diagnose errors, receive individualized explanations, practice mathematics, and address prerequisite weaknesses.
2. Independent Mastery and Assessment
Students periodically demonstrate what they can do without AI assistance, both during the learning process and eventually through secure summative assessments. This becomes increasingly important as conventional homework can no longer reliably demonstrate what a student knows independently.
3. AI-Assisted Grading and Personalized Feedback
AI can potentially help evaluate students’ mathematical reasoning and written solutions, apply instructor-defined rubrics, identify specific errors, recommend partial credit, and provide individualized formative feedback. Human instructors would retain oversight, particularly for ambiguous or low-confidence cases.
Ultimately, these components could form a continuous learning cycle:
\[
\boxed{\text{Learn with AI}}
\rightarrow
\boxed{\text{Demonstrate without AI}}
\rightarrow
\boxed{\text{AI-assisted evaluation}}
\rightarrow
\boxed{\text{Personalized feedback}}
\rightarrow
\boxed{\text{Targeted relearning}}
\]
The first project, however, will concentrate primarily on the first transition:
How can an AI Learning Coach help students move from AI-assisted learning to verified independent mathematical mastery?
Project Goal
The goal is not to determine whether students should or should not use AI. AI will increasingly be part of education, work, and everyday problem solving.
Instead, the project starts from a different premise:
Students should learn how to use AI effectively while also developing the knowledge and skills necessary to perform independently when independent competence matters.
A successful AI Learning Coach would therefore not maximize AI use, minimize AI use, or simply maximize the number of correctly completed problems. It would seek to maximize learning, independence, retention, and transfer.
This leads to the project’s central design principle:
The best AI learning assistance may be assistance that gradually teaches the learner not to need it.
The project will use HCI research and iterative prototyping to investigate how that principle can be translated into an effective learning experience, beginning with precalculus readiness and potentially extending later to other areas of mathematics and AI-supported education.