Model-Driven Synthesis for Programming Tutors

TL;DR

This paper explores using program synthesis to generate correct solutions that match student programs, enabling more effective automated feedback in programming tutors while balancing student experimentation and feedback needs.

Contribution

It introduces a novel approach employing program synthesis to generate solutions that facilitate constructive feedback in automated programming tutors.

Findings

Program synthesis can generate solutions closely matching student programs.

This approach improves the completeness of automated feedback.

It balances student experimentation with effective feedback provision.

Abstract

When giving automated feedback to a student working on a beginner's exercise, many programming tutors run into a completeness problem. On the one hand, we want a student to experiment freely. On the other hand, we want a student to write her program in such a way that we can provide constructive feedback. We propose to investigate how we can overcome this problem by using program synthesis, which we use to generate correct solutions that closely match a student program, and give feedback based on the results.