Sensible Agent：与主动式 AR 智能体进行不唐突交互的框架
Sensible Agent: A Framework for Unobtrusive Interaction with Proactive AR Agents
AI总结：
针对主动式AR智能体语音交互的破坏性问题，提出Sensible Agent框架，利用多模态情境感知动态调整辅助内容与交付方式，显著降低交互负担并保持高可用性。
摘要：
主动式 AR 智能体有望提供情境感知辅助，但其交互通常依赖显式语音提示或回应，这可能具有破坏性或导致社交尴尬。我们引入了 Sensible Agent，这是一个专为与这些主动式智能体进行不唐突交互而设计的框架。Sensible Agent 基于实时多模态情境感知，动态调整提供“什么”辅助，以及至关重要的“如何”交付辅助。在专家研讨会（n=12）和数据标注研究（n=40）的指导下，该框架利用自我中心相机、多模态传感和 Large Multimodal Models (LMMs) 来推断情境，并建议通过最低侵入性的交互模式来交付适当的行动。我们通过在 XR 头显上的用户研究（n=10），在 AR 和 VR 场景中展示了原型。结果表明，与语音提示基线相比，Sensible Agent 显著降低了感知交互努力，同时保持了高可用性并获得了更高的偏好。
英文摘要：
Proactive AR agents promise context-aware assistance, but their interactions often rely on explicit voice prompts or responses, which can be disruptive or socially awkward. We introduce Sensible Agent, a framework designed for unobtrusive interaction with these proactive agents. Sensible Agent dynamically adapts both "what" assistance to offer and, crucially, "how" to deliver it, based on real-time multimodal context sensing. Informed by an expert workshop (n=12) and a data annotation study (n=40), the framework leverages egocentric cameras, multimodal sensing, and Large Multimodal Models (LMMs) to infer context and suggest appropriate actions delivered via minimally intrusive interaction modes. We demonstrate our prototype on an XR headset through a user study (n=10) in both AR and VR scenarios. Results indicate that Sensible Agent significantly reduces perceived interaction effort compared to voice-prompted baseline, while maintaining high usability and achieving higher preference.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
