Conversational Learning Diagnosis via Reasoning Multi-Turn Interactive Learning

2026-03-03

AI Summary

This work addresses the limitations of existing conversational learning diagnostic methods, which often rely on intuitive prompting and lack grounding in theory of mind, thereby struggling to reliably model students’ cognitive states. To overcome this, the paper proposes ParLD, a novel framework grounded in theory of mind that implements a three-stage Preview-Analyze-Reason (Par) process. ParLD employs a multi-agent collaborative architecture to model behavioral patterns, track cognitive states, and predict future learning performance. It further incorporates a Chain Reflector mechanism to enable verifiable self-correction. Experimental results demonstrate that ParLD significantly enhances the accuracy, interpretability, and psychological plausibility of diagnostic outcomes in both learning performance prediction and instructional support tasks.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Life-Long and Continual Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• conversational learning diagnosis
• cognitive state
• multi-turn dialogue
• learning diagnosis
• language models

Innovation

• Conversational Learning Diagnosis
• Multi-Agent Collaboration
• Cognitive State Modeling
• Chain Reflector
• Preview-Analyze-Reason Framework