情感智能体：可穿戴系统的设备端个性化干预推理
Affective Agent: On-Device Personalized Intervention Reasoning for Wearable Systems
- Harvard University（哈佛大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对可穿戴设备干预推理难题，提出三层架构的情感智能体，结合亚十亿参数语言模型与记忆演化实现设备端个性化干预，实验验证其有效性。
AI中文摘要：
情感计算推动了可穿戴状态推断的进步，但在设备端推理是否、何时以及如何进行干预仍然具有挑战性。我们提出了情感智能体（Affective Agent），一种用于在可穿戴级硬件上、在不确定性下进行个性化干预推理的三层参考架构。它将一个紧凑的亚十亿参数语言模型与生理证据、上下文和用户历史相结合，以决定是否、何时以及如何进行干预，无需云依赖或逐用户重训练。该架构由三个交互层（感知、个性化和推理）组成，通过主机管理的结构化记忆演化而非逐用户权重更新来适应个体用户。我们在室内环境质量控制中实例化了情感智能体，并在包含生理变化、上下文、信号质量和干预历史的、由模拟器生成的纵向场景上对其进行了评估。结果表明，记忆驱动的个性化和两遍结构化推理在此合成评估中改善了干预决策。通过将决策层移至设备端，这项工作展示了从可穿戴状态推断走向可穿戴级硬件上闭环、个性化干预的路径。
英文摘要：
Affective computing has advanced wearable state inference, but on-device reasoning about whether, when, and how to intervene remains challenging. We present Affective Agent, a three-layer reference architecture for personalized intervention reasoning under uncertainty on wearable-class hardware. It combines a compact sub-billion-parameter language model with physiological evidence, context, and user history to decide whether, when, and how to intervene, without cloud dependency or per-user retraining. The architecture is organized into three interacting layers (perception, personalization, and reasoning), adapting to individual users through host-managed structured memory evolution rather than per-user weight updates. We instantiate Affective Agent in indoor environmental quality control and evaluate it on held-out, simulator-generated longitudinal scenarios spanning physiological variation, context, signal quality, and intervention history. Results show that memory-driven personalization and two-pass structured reasoning improve intervention decisions within this synthetic evaluation. By moving the decision layer on-device, this work demonstrates a path from wearable state inference toward closed-loop, personalized intervention on wearable-class hardware.
