Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts

2026-06-25

AI Summary

This study addresses the lack of effective frameworks for analyzing dialogic dynamics in human–AI or multi-agent collaborative problem solving, which hinders the evaluation and optimization of such partnerships. To bridge this gap, the authors propose a hierarchical dual-layer encoding framework that systematically integrates metacognitive regulation mechanisms into dialogue analysis for the first time. By unifying cognitive and non-cognitive behaviors with metacognitive processes, the framework elucidates the interaction mechanisms underlying collaborative problem solving. Combining discourse analysis with cognitive modeling, it is validated across nine cross-domain datasets, demonstrating strong effectiveness and generalizability. The findings reveal metacognitive regulation as a key discriminative factor in deep collaboration, significantly advancing understanding of how knowledge, skills, and effort are coordinated in human–agent teamwork.

Abstract

We present a conceptual framework for analyzing dialogue in collaborative problem-solving contexts, with an emphasis on the emerging dynamics of human-AI and multi-agent collaboration. As intelligent systems become active agents capable of autonomous reasoning and strategic cooperation, understanding the dialogic interaction during collaborative problem solving is increasingly important for optimizing and evaluating such partnerships. Our framework addresses key limitations in current analytical approaches through a hierarchical two-layer coding scheme that integrates cognitive and non-cognitive problem solving with metacognitive regulatory mechanisms. We demonstrate its effectiveness and generalizability across nine datasets spanning multiple domains, and provide insights into how humans and agents coordinate their knowledge, skills, and efforts to solve complex problems, showing in particular that metacognitive regulation can be an essential discriminator of deeper collaboration.

Problem

• dialogue dynamics
• collaborative problem-solving
• human-AI collaboration
• metacognitive regulation
• multi-agent systems

Innovation

• dialogue dynamics
• collaborative problem-solving
• metacognitive regulation
• human-AI collaboration
• hierarchical coding scheme