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

• URL: http://arxiv.org/abs/2603.21288v1
• Date: Sun, 22 Mar 2026 15:21:55 GMT
• Title: Unpacking Interaction Profiles and Strategies in Human-AI Collaborative Problem Solving: A Cognitive Distribution and Regulation Perspective
• Abstract summary: This study adopts an integrated distributed cognition and regulation of learning perspective to examine the collaboration patterns and dynamics of human-AI collaboration.<n>Three distinct collaborative problem-solving modes were identified: Delegated Reasoning (DR), Concerted Interpretation (CI), and Delegated Elaboration (DE)
• Score: 17.879329691577684
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts [57.79777631004424]
  We present a conceptual framework for analyzing dialogue in collaborative problem-solving contexts.<n>Our framework integrates cognitive and non-cognitive problem solving with metacognitive regulatory mechanisms.
  arXiv  Detail & Related papers  (2026-06-25T16:20:49Z)
• From Affect to Complex Behavior: Advancing Multimodal Human-Centered AI at the 10th ABAW Workshop & Competition [60.17193786245766]
  The ABAW Competition introduces a diverse set of challenges targeting key aspects of affective and behavioral understanding.<n>The paper track presents a wide range of contributions spanning pose, motion & behavior estimation, affect modelling & multimodal learning, benchmarks, datasets & evaluation protocols, fairness, robustness & deployment.
  arXiv  Detail & Related papers  (2026-05-24T17:44:37Z)
• Agentic Reasoning for Large Language Models [122.81018455095999]
  Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making.<n>Large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, but struggle in open-ended and dynamic environments.<n>Agentic reasoning marks a paradigm shift by reframing LLMs as autonomous agents that plan, act, and learn through continual interaction.
  arXiv  Detail & Related papers  (2026-01-18T18:58:23Z)
• Agentic AI as Undercover Teammates: Argumentative Knowledge Construction in Hybrid Human-AI Collaborative Learning [6.109253207492508]
  Generative artificial intelligence (AI) agents are increasingly embedded in collaborative learning environments.<n>This study investigates how agentic AI, designed as undercover teammates with either supportive or contrarian personas, shapes the dynamics of collaborative reasoning.
  arXiv  Detail & Related papers  (2025-10-19T14:26:15Z)
• MEJO: MLLM-Engaged Surgical Triplet Recognition via Inter- and Intra-Task Joint Optimization [52.149337961205624]
  We propose a framework that empowers both inter- and intra-task optimization for surgical triplet recognition.<n>For inter-task optimization, we introduce the Shared-Specific-Disentangled (S$2$D) learning scheme that decomposes representations into task-shared and task-specific components.<n>For intra-task optimization conflicts, we develop a Coordinated Gradient Learning (CGL) strategy, which dissects and rebalances the positive-negative ambiguities.
  arXiv  Detail & Related papers  (2025-09-16T09:48:52Z)
• Human-AI collaboration or obedient and often clueless AI in instruct, serve, repeat dynamics? [0.0]
  This study examines human-AI interactions while solving a complex problem.<n>Findings reveal a dominant Instructive pattern with interactions characterized by iterative ordering rather than collaborative negotiation.
  arXiv  Detail & Related papers  (2025-08-03T11:43:01Z)
• When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration [79.69935257008467]
  We introduce Knowledge Integration and Transfer Evaluation (KITE), a conceptual and experimental framework for Human-AI knowledge transfer capabilities.<n>We conduct the first large-scale human study (N=118) explicitly designed to measure it.<n>In our two-phase setup, humans first ideate with an AI on problem-solving strategies, then independently implement solutions, isolating model explanations' influence on human understanding.
  arXiv  Detail & Related papers  (2025-06-05T20:48:16Z)
• Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems [12.471774408499817]
  Agentic AI aims to create systems that set their own goals, adapt proactively to change, and refine behavior through continuous experience.<n>Recent advances suggest that, when facing multiple and unforeseen tasks, agents could benefit from sharing machine-learned knowledge and reuse policies that have already been fully or partially learned by other agents.<n>This study explores how an agent decides what knowledge to select, from whom, and when and how to integrate it in its own policy in order to accelerate its own learning.
  arXiv  Detail & Related papers  (2025-06-05T20:38:11Z)
• Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems [29.924868489451327]
  This study systematically investigates four dimensions of collaboration strategies.<n>We quantify the impact of these strategies on both task accuracy and computational efficiency.<n>This work establishes a foundation for designing adaptive, scalable multi-agent systems.
  arXiv  Detail & Related papers  (2025-05-18T15:46:14Z)
• Augmenting the Author: Exploring the Potential of AI Collaboration in Academic Writing [25.572926673827165]
  This case study highlights the importance of prompt design, output analysis, and recognizing the AI's limitations to ensure responsible and effective AI integration in scholarly work. The paper contributes to the field of Human-Computer Interaction by exploring effective prompt strategies and providing a comparative analysis of Gen AI models.
  arXiv  Detail & Related papers  (2024-04-23T19:06:39Z)
• A Survey on Human-AI Collaboration with Large Foundation Models [11.837685062760132]
  Human-AI (HAI) Collaboration has become pivotal for advancing problem-solving and decision-making processes.<n>The advent of Large Foundation Models (LFMs) has greatly expanded its potential, offering unprecedented capabilities.<n>This paper reviews the crucial integration of LFMs with HAI, highlighting both opportunities and risks.
  arXiv  Detail & Related papers  (2024-03-07T22:37:49Z)
• Large Language Model-based Human-Agent Collaboration for Complex Task Solving [94.3914058341565]
  We introduce the problem of Large Language Models (LLMs)-based human-agent collaboration for complex task-solving. We propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process.
  arXiv  Detail & Related papers  (2024-02-20T11:03:36Z)
• Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection [57.13665112065285]
  Human-Object Interaction (HOI) detection is a challenging computer vision task. We present a framework that enhances HOI detection by incorporating structured text knowledge.
  arXiv  Detail & Related papers  (2023-07-25T14:20:52Z)
• An Artificial Intelligence driven Learning Analytics Method to Examine the Collaborative Problem solving Process from a Complex Adaptive Systems Perspective [0.7450115015150832]
  Collaborative problem solving (CPS) enables student groups to complete learning tasks, construct knowledge, and solve problems. Previous research has argued the importance to examine the complexity of CPS, including its multimodality, dynamics, and synergy. This research collected multimodal process and performance data to understand the nature of CPS in online interaction settings.
  arXiv  Detail & Related papers  (2022-10-28T11:13:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.