SLOW: Strategic Logical-inference Open Workspace for Cognitive Adaptation in AI Tutoring

TL;DR

SLOW is a novel AI tutoring framework that enhances deliberate reasoning, personalization, and emotional sensitivity by explicitly separating learner inference from instructional decision-making, inspired by dual-process theories.

Contribution

It introduces a transparent, theory-informed workspace for AI tutors that improves interpretability and pedagogical adaptation over traditional single-pass LLM approaches.

Findings

Significant improvements in personalization and emotional sensitivity.

Each module's ablation reduces system performance, confirming their importance.

Demonstrated interpretability through visualized decision-making processes.

Abstract

While Large Language Models (LLMs) have demonstrated remarkable fluency in educational dialogues, most generative tutors primarily operate through intuitive, single-pass generation. This reliance on fast thinking precludes a dedicated reasoning workspace, forcing multiple diagnostic and strategic signals to be processed in a conflated manner. As a result, learner cognitive diagnosis, affective perception, and pedagogical decision-making become tightly entangled, which limits the tutoring system's capacity for deliberate instructional adaptation. We propose SLOW, a theory-informed tutoring framework that supports deliberate learner-state reasoning within a transparent decision workspace. Inspired by dual-process accounts of human tutoring, SLOW explicitly separates learner-state inference from instructional action selection. The framework integrates causal evidence parsing from learner language, fuzzy cognitive diagnosis with counterfactual stability analysis, and prospective affective reasoning to anticipate how instructional choices may influence learners' emotional trajectories. These signals are jointly considered to guide pedagogically and affectively aligned tutoring strategies. Evaluation using hybrid human-AI judgments demonstrates significant improvements in personalization, emotional sensitivity, and clarity. Ablation studies further confirm the necessity of each module, showcasing how SLOW enables interpretable and reliable intelligent tutoring through a visualized decision-making process. This work advances the interpretability and educational validity of LLM-based adaptive instruction.