Learning in Blocks uses heterogeneous multi-agent debate to score CEFR-aligned conversational competence, enforce 70% mastery progression, and deliver spaced review, yielding better outcomes than feedback alone in an 8-week study of 180 A2 learners.
instruction and curriculum
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Learner-level representations from aggregated student interactions show higher distinctiveness, better clustering, and stronger pairwise separation than single-interaction representations, enabling outcome-independent evaluation.
citing papers explorer
-
Learning in Blocks: A Multi Agent Debate Assisted Personalized Adaptive Learning Framework for Language Learning
Learning in Blocks uses heterogeneous multi-agent debate to score CEFR-aligned conversational competence, enforce 70% mastery progression, and deliver spaced review, yielding better outcomes than feedback alone in an 8-week study of 180 A2 learners.
-
Evaluating Learner Representations for Differentiation Prior to Instructional Outcomes
Learner-level representations from aggregated student interactions show higher distinctiveness, better clustering, and stronger pairwise separation than single-interaction representations, enabling outcome-independent evaluation.