Unpacking Interaction Profiles and Strategies in Human-AI Collaborative Problem Solving: A Cognitive Distribution and Regulation Perspective

TL;DR

This paper identifies three distinct modes of human-AI collaboration in complex problem-solving, revealing trade-offs between performance and self-regulation, with implications for designing educational AI tools.

Contribution

It introduces a novel classification of collaborative problem-solving modes in human-AI teams and analyzes their dynamics and performance differences.

Findings

DR mode yields highest task performance

Semantic similarity highest in DR group

CI group uses more self-regulation strategies

Abstract

This study adopts an integrated distributed cognition and regulation of learning perspective to examine the collaboration patterns and dynamics of human-AI collaboration when college students collaborating with AI for complex problem-solving. Through cluster analysis, three distinct collaborative problem-solving modes were identified in this study: Delegated Reasoning (DR), Concerted Interpretation (CI), and Delegated Elaboration (DE). This study found that the DR group achieved the highest task performance, significantly outperforming the CI group. Additionally, the semantic similarity between human and AI discourse was notably the highest in the DR group. In contrast, the CI group reported significantly greater use of self-regulation strategies. These findings uncover a critical tension between the efficiency of the distributed system and the depth of human learners regulatory engagement. Insights from this study offer valuable implications for the future design of AI-empowered educational tools and student-AI collaborative learning frameworks.