Structuring scaffolding via LLM agents led to more accurate and interactive student participation in diagnostic tasks, while problematizing scaffolding elicited more constructive engagement, though overall performance depended primarily on scenario complexity rather than scaffolding type or prior知识.
Graber, Susanna Kissam, Valerie L
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Structuring versus Problematizing: How LLM-based Agents Scaffold Learning in Diagnostic Reasoning
Structuring scaffolding via LLM agents led to more accurate and interactive student participation in diagnostic tasks, while problematizing scaffolding elicited more constructive engagement, though overall performance depended primarily on scenario complexity rather than scaffolding type or prior知识.