Use the solver as a hint engine for intelligent tutoring of spatial reasoning in puzzle games¶

Strategy · All strategies
Evidence · 1 claim (1 for) · 1 study (1 design), q1 · 0 of 1 report an effect size · 1 claim rests on one study

Description¶

The authors propose deploying the human-centric solver as the core of an educational tool: 'the system can serve as a core engine for an intelligent tutoring system, providing meaningful, human-like hints tailored to a player's current solution attempt'. Because the agent reasons symbolically about stability and path affordances, its intermediate decisions can be translated into interpretable feedback for players. They envisage that 'Experiments with students in STEM fields, engaging with such interactive teaching tools, can be an effective educational aid'.

Design Implications¶

Context¶

Requirements¶

• The game must be representable in the qualitative grid model with stability and path criteria
• Hints must be derived from the agent's symbolic decision process for a player's current attempt

Constraints¶

• The tutoring use case is envisaged but not yet empirically tested in this article

Target Learners¶

• children developing spatial skills
• students in STEM fields

Target Learning Goals¶

• structural stability understanding
• spatial path visualization and planning

Affordances¶

• Hybrid Qualitative Com Model Camelot Jr

Claims¶

• The hybrid qualitative-COM solver solves arbitrary Camelot Jr. configuration challenges within the game's problem space [+W]

Related Strategies¶

• Apply GAP data in educational game design through difficulty tuning, hints, and feedback

Examples¶

-

Key Sources¶

• Abhishek Jaiswal, Zoe Falomir. (2026). A Qualitative Model for Reasoning about Path and Support. arXiv preprint. https://arxiv.org/abs/2609.20349