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

2026-03-22

AI Summary

This study investigates the interaction patterns between university students and artificial intelligence systems during complex problem-solving tasks and their impact on task performance and self-regulated learning. Grounded in distributed cognition and self-regulated learning theories, the research employs cluster analysis and semantic similarity computation to identify three distinct collaboration patterns: delegated reasoning, co-constructed explanation, and delegated elaboration. Findings reveal that the delegated reasoning group achieved the highest task performance and exhibited the greatest semantic similarity between human and AI utterances, whereas the co-constructed explanation group demonstrated significantly greater use of self-regulation strategies. The study highlights a tension between AI system efficiency and the depth of learner regulation, offering theoretical insights and practical implications for the design of intelligent educational tools.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Multiagent Systems: Distributed Problem Solving

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Human-AI collaboration
• collaborative problem solving
• distributed cognition
• self-regulation
• cognitive distribution

Innovation

• distributed cognition
• regulation of learning
• human-AI collaboration
• collaborative problem solving
• cluster analysis