Affective Agent: On-Device Personalized Intervention Reasoning for Wearable Systems

2026-09-10

AI Summary

本文提出Affective Agent，一种三层架构，结合语言模型与生理等数据，在穿戴设备上实现个性化干预决策，无需依赖云端或重新训练。

Abstract

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.

Problem

• Affective Computing
• Wearable Systems
• Personalized Intervention
• On-Device Reasoning
• Uncertainty

Innovation

• on-device reasoning
• personalized intervention
• wearable systems
• compact language model
• structured memory evolution