发表机构
University of Southern Denmark（南丹麦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文综述自适应人机协作，提出多模态情境建模、不确定性感知干预和纵向协同适应的三分类体系，并整合为MCAL双时间尺度参考模型，通过实例验证其应用。
AI 中文摘要
人工智能正从静态的决策支持工具转变为自适应协作者，它必须感知情境，决定何时以及如何进行干预，并通过与个体和群体的反复互动来改进。然而，元分析证据表明，人机组合往往未能超越任一单独伙伴的最佳表现，且相关文献在多模态感知、不确定性量化、依赖与委派、促进以及团队协作等方面仍然分散。本文通过闭环视角对自适应人机协作文献进行了综述。遵循迭代识别、基于明确标准的分阶段筛选、结构化提取、分类驱动综合和滚雪球方法，我们分析了50篇被评述的工作。我们贡献了：i）多模态情境建模的分类体系，涵盖从个体状态到集体状态（如群体参与度和参与平等性）；ii）不确定性感知干预的分类体系，涵盖不确定性来源、估计与校准机制、从解释调节和延迟到群体促进的干预手段库，以及干预策略；iii）纵向协同适应和面向协同效应的评估分类体系。我们将这三个分类体系整合到MCAL中，这是一个双时间尺度的多模态协同适应循环参考模型，并在一个混合人机工作空间上对其进行实例化，通过一个具体设置遍历循环的每个阶段，以展示每个分类单元在实践中的含义。
英文摘要
Artificial intelligence is shifting from a static decision-support tool to an adaptive collaborator that must sense context, decide when and how to intervene, and improve through repeated interaction with humans individually and in groups. Yet meta-analytic evidence shows that human-AI combinations often fail to outperform the best of either partner alone, and the enabling literature remains fragmented across multimodal sensing, uncertainty quantification, reliance and delegation, facilitation, and teaming. This paper reports a review of adaptive human-AI collaboration literature through a closed-loop lens. Following iterative identification, staged selection against explicit criteria, structured extraction, taxonomy-driven synthesis, and snowballing, we analyze 50 reviewed works. We contribute i) a taxonomy of multimodal context modeling, from individual states to collective states such as group engagement and participation equality; ii) a taxonomy of uncertainty-aware intervention, covering uncertainty sources, estimation and calibration mechanisms, an intervention repertoire that ranges from explanation modulation and deferral to group facilitation, and intervention policies; and iii) a taxonomy of longitudinal co-adaptation and synergy-oriented evaluation. We integrate the three taxonomies into MCAL, a dual-timescale Multimodal Co-Adaptation Loop reference model, and instantiate it on a mixed human-robot workspace, walking every stage of the loop through one concrete setting to show what each taxonomy cell holds in practice.
CommentsAccepted to be published at the Companion of the INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION (ICMI Companion '26), October 05--09, 2026, Napoli, Italy
