Conversational Learning Diagnosis via Reasoning Multi-Turn Interactive Learning

TL;DR

This paper introduces ParLD, a multi-agent framework for conversational learning diagnosis that improves reliability and insightfulness by modeling student behavior, analyzing dialogue, and reasoning about future responses in multi-turn educational interactions.

Contribution

The study proposes ParLD, a novel preview-analyze-reason framework utilizing multi-agent collaboration for more reliable and psychologically grounded conversational learning diagnosis.

Findings

ParLD outperforms baseline methods in learning diagnosis accuracy.

It provides more reliable and psychologically grounded cognitive state assessments.

The framework enhances tutoring support through effective future response prediction.

Abstract

Learning diagnosis is a critical task that monitors students' cognitive state during educational activities, with the goal of enhancing learning outcomes. With advancements in language models (LMs), many AI-driven educational studies have shifted towards conversational learning scenarios, where students engage in multi-turn interactive dialogues with tutors. However, conversational learning diagnosis remains underdeveloped, and most existing techniques acquire students' cognitive state through intuitive instructional prompts on LMs to analyze the dialogue text. This direct prompting approach lacks a solid psychological foundation and fails to ensure the reliability of the generated analytical text. In this study, we introduce ParLD, a preview-analyze-reason framework for conversational learning diagnosis, which leverages multi-agent collaboration to diagnose students' cognitive state over multiple dialogue turns. Specifically, ParLD comprises three main components: (1) Behavior Previewer, which generates a student behavior schema based on previous states and learning content; (2) State Analyzer, which diagnoses the tutor-student dialogue and behavior schema to update the cognitive state; and (3) Performance Reasoner, which predicts the student's future responses and provides verifiable feedback to support ParLD's self-reflection with the Chain Reflector. They operate sequentially and iteratively during each interaction turn to diagnose the student's cognitive state. We conduct experiments to evaluate both performance prediction and tutoring support, emphasizing the effectiveness of ParLD in providing reliable and insightful learning diagnosis.