AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization
Not on the map. Why?
Abstract (arXiv)
Recent advances in artificial intelligence (AI) are reshaping smart glasses from egocentric capture and display devices into platforms for wearable intelligence. Smart glasses increasingly serve as wearable AI systems that connect first-person observation with real-time assistance under strict form-factor constraints. We frame this transition through the lens of AI smart glasses and define them as a system-level concept in which egocentric sensing, resource-aware computing, intelligent reasoning, multimodal interaction, and real-world application constraints are co-designed for personalized assistance in the physical world. To systematically study this perspective, we organize the survey around four connected dimensions. First, we examine the hardware foundation that bounds sensing, computation, feedback delivery, and sustained deployment. Second, we study wearable intelligence, where egocentric signals are transformed into perceptual, contextual, and agentic capabilities. Third, we discuss interaction design, through which users request, receive, correct, and regulate assistance during ongoing activity. Fourth, we analyze application scenarios across healthcare, accessibility, situated learning, daily life assistance, cultural tourism, and industrial support, showing how domain requirements reshape system design and evaluation. We further identify five cross-cutting research challenges for future AI smart glasses: next-generation hardware, trustworthy egocentric intelligence, lifelong personalized memory, proactive intelligence, and embodied foundation models. By centering smart glasses as wearable-intelligence platforms, this survey provides a unified framework for organizing technologies, applications, and open challenges in this emerging area.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 158 of its 213 references that are in the map. First posted on arXiv 17 Sep 2026.
Builds on
158 of 213 references.
References · 158
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023Visual Instruction Tuningcited by 7,792
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
- 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
- 2018SlowFast Networks for Video Recognitioncited by 1,862
- 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
- 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
38 more
- 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
- 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
- 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
- 2021Improving language models by retrieving from trillions of tokenscited by 1,278
- 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
- 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
- 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
- 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
- 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
- 2023VILA: On Pre-training for Visual Language Modelscited by 686
- 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
- 2020Rescaling Egocentric Visioncited by 529
- 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
- 2018TVQA: Localized, Compositional Video Question Answeringcited by 463
- 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
- 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 284
- 2022Egocentric Video-Language Pretrainingcited by 231
- 2021Keeping Your Eye on the Ball: Trajectory Attention in Video Transformerscited by 224
- 2024VoiceBench: Benchmarking LLM-Based Voice Assistantscited by 192
- 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
- 2023Augmenting Language Models with Long-Term Memorycited by 186
- 2023EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attentioncited by 172
- 2023Osprey: Pixel Understanding with Visual Instruction Tuningcited by 158
- 2025Time-R1: Post-Training Large Vision Language Model for Temporal Video Groundingcited by 138
- 2024Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Inputcited by 132
- 2023EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbonecited by 130
- 2024HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videoscited by 122
- 2020EGO-TOPO: Environment Affordances from Egocentric Videocited by 111
- 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 109
- 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
- 2023R2Former: Unified Retrieval and Reranking Transformer for Place Recognitioncited by 102
- 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 93
- 2025A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Modelscited by 87
- 2025EgoLife: Towards Egocentric Life Assistantcited by 86
- 2023AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?cited by 79
- 2023EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planningcited by 66
- 2024Yo'LLaVA: Your Personalized Language and Vision Assistantcited by 61
50 most cited of 158 All 158 (JSON)
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Affective Agent: On-Device Personalized Intervention Reasoning for Wearable Systems
- 2024GazeGPT: Augmenting Human Capabilities using Gaze-contingent Contextual AI for Smart Eyewear
- 2026GazeMind: A Gaze-Guided LLM Agent for Personalized Cognitive Load Assessment
- 2025Human-AI Co-Embodied Intelligence for Scientific Experimentation and Manufacturing
- 2025Sensible Agent: A Framework for Unobtrusive Interaction with Proactive AR Agents
- 2026Pro2Assist: Continuous Step-aware Proactive Assistance with Multi-modal Egocentric Perception for Long-horizon Procedural Tasks
- 2026Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision
- 2025From Screens to Scenes: A Survey of Embodied AI in Healthcare