Learning in Blocks: A Multi Agent Debate Assisted Personalized Adaptive Learning Framework for Language Learning

TL;DR

This paper presents Learning in Blocks, a multi-agent debate framework for personalized language learning that evaluates conversational skills using CEFR rubrics and improves outcomes through targeted review.

Contribution

It introduces a novel multi-agent debate system for scoring and recommending language skills, validated on CEFR-aligned conversations and shown to enhance learning outcomes.

Findings

HeteroMAD achieves high agreement with expert scoring (0.23 variation).

Recommendation acceptability reaches 90.91%.

Learners using the framework outperform those with feedback alone.

Abstract

Most digital language learning curricula rely on discrete-item quizzes that test recall rather than applied conversational proficiency. When progression is driven by quiz performance, learners can advance despite persistent gaps in using grammar and vocabulary during interaction. Recent work on LLM-based judging suggests a path toward scoring open-ended conversations, but using interaction evidence to drive progression and review requires scoring protocols that are reliable and validated. We introduce Learning in Blocks, a framework that grounds progression in demonstrated conversational competence evaluated using CEFR-aligned rubrics. The framework employs heterogeneous multi-agent debate (HeteroMAD) in two stages: a scoring stage where role-specialized agents independently evaluate Grammar, Vocabulary, and Interactive Communication, engage in debate to address conflicting judgments, and a judge synthesizes consensus scores; and a recommendation stage that identifies specific grammar skills and vocabulary topics for targeted review. Progression requires demonstrating 70% mastery, and spaced review targets identified weaknesses to counter skill decay. We benchmark four scoring and recommendation methods on CEFR A2 conversations annotated by ESL experts. HeteroMAD achieves a superior score agreement with a 0.23 degree of variation and recommendation acceptability of 90.91%. An 8-week study with 180 CEFR A2 learners demonstrates that combining rubric-aligned scoring and recommendation with spaced review and mastery-based progression produces better learning outcomes than feedback alone.