Two controlled experiments show multi-agent LLM configurations with both tutors and peers deliver higher learning gains and less homogeneous outputs than single-LLM tutoring in math problem-solving and essay writing.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The authors achieve third place in EmotiW 2019 engagement intensity regression by extending an LSTM framework with facial landmarks, rank loss, and bootstrap aggregation to reach MSE 0.0626 on the test set.
citing papers explorer
-
Beyond the AI Tutor: Social Learning with LLM Agents
Two controlled experiments show multi-agent LLM configurations with both tutors and peers deliver higher learning gains and less homogeneous outputs than single-LLM tutoring in math problem-solving and essay writing.
-
Bootstrap Model Ensemble and Rank Loss for Engagement Intensity Regression
The authors achieve third place in EmotiW 2019 engagement intensity regression by extending an LSTM framework with facial landmarks, rank loss, and bootstrap aggregation to reach MSE 0.0626 on the test set.