Modeling learners’ stepwise reasoning improves tutoring feedback accuracy
Making Reasoning Visible: Configuration-Aware Diagnostic Modeling for Adaptive Scaffolding in Structured Reasoning Tasks
Computation and LanguageArtificial IntelligenceMachine Learning
Summary
Many tutoring systems only check if students’ answers are right or wrong, missing important clues about how they solve problems. The authors created a method that tracks students’ step-by-step actions during grammar exercises to reveal how they think, including whether they guess or try to fix errors systematically. They found that students’ reasoning changes based on the task, and many get stuck repeating mistakes when the problems require juggling complex ideas. Their system can predict when students will succeed soon, helping tutors intervene earlier with better guidance.
What this means in practice
- •For edtech software developers: Integrate stepwise reasoning models to detect student errors early and deliver adaptive feedback in language learning apps.
- •For data analysts in online education: Use sequential strategy patterns to identify students stuck in unproductive reasoning for targeted interventions.
Authors
Trystan Geoffre, Zheng Yuan, Thierry Geoffre
Abstract
Modeling the latent, multi-step reasoning processes of learners is a core challenge for adaptive tutoring systems, which often rely on simple right/wrong answers rather than understanding how students think. Instantiated here for grammatical reasoning, this study introduces a diagnostic framework that makes students' step-by-step problem-solving visible by analyzing their action sequences in an interactive learning game. The framework computes five interpretable strategy dimensions (e.g., systematic error correction, random guessing), estimates coordination demand from task structure and behavioral patterns, and classifies reasoning into four distinct states. Analyzing 36,234 interactions from 234 students working on 42 morphosyntactic exercises, we found that reasoning strategies vary primarily by context rather than stable traits (intraclass correlation = 0.14), and students show high persistence in unproductive states; specifically, 74.6% of failures driven by high coordination demand (rather than simple knowledge gaps) are followed by another failure without intervention. Our early warning model predicts validation success with strong accuracy (AUC = 0.826 using strategy patterns alone; 0.902 with additional sequential context) while avoiding circular reliance on current error counts. These findings demonstrate that making latent reasoning processes visible enables earlier, more targeted scaffolding that responds to how students are thinking rather than simply whether they succeed. While demonstrated in language learning, the framework provides a generalizable, interpretable architecture for diagnosing complex, structured reasoning in any domain.