---
title: "Connecting Dialogue and Thought: Understanding Dialogue Dynamics in Collaborative Problem Solving"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2606.27233v1"
permalink: "https://feed.astralor.com/items/itm_3b83bc3cd1171e2ef79f816f"
published: "2026-06-25T16:20:49.000Z"
score: 52
channel: "ai"
tags: ["Metacognitive Regulation","Collaborative Problem Solving","Multi-Agent Collaboration","Dialogue Systems"]
---

# Connecting Dialogue and Thought: Understanding Dialogue Dynamics in Collaborative Problem Solving

## At a glance

This paper presents a conceptual framework for analyzing dialogue dynamics in collaborative problem solving, focusing on emerging human-AI and multi-agent interactions. Using a hierarchical two-layer coding scheme that integrates cognitive and non-cognitive problem solving with metacognitive regulation, it demonstrates effectiveness across nine datasets and reveals metacognitive regulation as a key discriminator of deeper collaboration.

## Key points

- Proposes a two-layer coding framework integrating cognitive, non-cognitive, and metacognitive regulation
- Validates framework's generalizability across nine cross-domain datasets
- Identifies metacognitive regulation as a key discriminator of deep vs. surface collaboration
- Provides theoretical tools for optimizing human-AI and multi-agent systems

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_3b83bc3cd1171e2ef79f816f