A classroom study of 102 students finds that requesting AI-generated planning hints is associated with better solving outcomes, while debugging hints are over-used and optimization hints under-used.
You’re (Not) My Type-Can LLMs Generate Feed- back of Specific Types for Introductory Programming Tasks?Journal Of Computer Assisted Learning, 41, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Plan More, Debug Less: Applying Metacognitive Theory to AI-Assisted Programming Education
A classroom study of 102 students finds that requesting AI-generated planning hints is associated with better solving outcomes, while debugging hints are over-used and optimization hints under-used.