paper-with-me

홈 › Papers

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

2026-03-29 · Nicy Scaria, Silvester John Joseph Kennedy, Deepak Subramani arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.22770

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate

2025-11-28 · Finn G. Vamosi, Nils D. Forkert arxiv

When people reason about cause and effect, they often consider many competing "what if" scenarios before deciding which explanation fits best. Analogously, advanced language models capable of causal inference can conside…

Causal Inference

LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

2026-06-15 · Jaward Sesay, Yue Yu, Siwei Dong, Börje F. Karlsson arxiv

Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. However, existing …

Semantic Segmentation

GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion

2024-09-21 · Tongxuan Liu, Xingyu Wang, Weizhe Huang, Wenjiang Xu 외

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, C…

Logical Reasoning

Assisted Debate Builder with Large Language Models

2024-05-14 · Elliot Faugier, Frédéric Armetta, Angela Bonifati, Bruno Yun

We introduce ADBL2, an assisted debate builder tool. It is based on the capability of large language models to generalise and perform relation-based argument mining in a wide-variety of domains. It is the first open-sour…

Argument MiningLanguage ModelingLanguage ModellingLarge Language Model+1

Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate

2024-08-08 · Yiqun Zhang, Xiaocui Yang, Shi Feng, Daling Wang 외

Competitive debate is a complex task of computational argumentation. Large Language Models (LLMs) suffer from hallucinations and lack competitiveness in this field. To address these challenges, we introduce Agent for Deb…