The Year in AI Papers
The year/Independent research

Paper 2510.14359

AI for Service: Proactive Assistance with AI Glasses

Zichen Wen, Yiyu Wang, Chenfei Liao, Boxue Yang, Junxian Li, Weifeng Liu, Haocong He, Bolong Feng, Xuyang Liu, Yuanhuiyi Lyu, Xu Zheng, Xuming Hu, et al.

Published
Oct 2025
Research lab
Independent
Citations
16
GitHub
Not linked

01 In brief

Summary

The paper introduces AI for Service (AI4Service), a paradigm for proactive, real-time assistance via AI glasses, contrasting with reactive AI that only responds to explicit commands.

It proposes Alpha-Service, a framework inspired by the von Neumann architecture, comprising five components: Input Unit (perception via dual MLLMs), Central Processing Unit (task orchestration via LLM), Arithmetic Logic Unit (tool use, e.g., web search), Memory Unit (long-term personalization), and Output Unit (human-friendly synthesis).

The system addresses two challenges: 'Know When' (detecting service opportunities from egocentric video) and 'Know How' (providing generalized and personalized services).

Implemented as a multi-agent system on AI glasses, it is validated in three case studies: a Blackjack advisor that proactively suggests hitting/standing based on card analysis, a museum tour guide that identifies artifacts and provides historical context, and a shopping fit advisor that offers styling and purchase advice.

The paper also discusses challenges including computational constraints, generalization vs.

personalization trade-offs, scalability, privacy, and user trust.

Future work includes enhancing memory personalization, expanding tools, and conducting large-scale user studies.

02 From the paper

Abstract

In an era where AI is evolving from a passive tool into an active and adaptive companion, we introduce AI for Service (AI4Service), a new paradigm that enables proactive and real-time assistance in daily life. Existing AI services remain largely reactive, responding only to explicit user commands. We argue that a truly intelligent and helpful assistant should be capable of anticipating user needs and taking actions proactively when appropriate. To realize this vision, we propose Alpha-Service, a unified framework that addresses two fundamental challenges: Know When to intervene by detecting service opportunities from egocentric video streams, and Know How to provide both generalized and personalized services. Inspired by the von Neumann computer architecture and based on AI glasses, Alpha-Service consists of five key components: an Input Unit for perception, a Central Processing Unit for task scheduling, an Arithmetic Logic Unit for tool utilization, a Memory Unit for long-term personalization, and an Output Unit for natural human interaction. As an initial exploration, we implement Alpha-Service through a multi-agent system deployed on AI glasses. Case studies, including a real-time Blackjack advisor, a museum tour guide, and a shopping fit assistant, demonstrate its ability to seamlessly perceive the environment, infer user intent, and provide timely and useful assistance without explicit prompts.