Designing Memory-Augmented AR Agents for Spatiotemporal Reasoning in Personalized Task Assistance

TL;DR

This paper proposes a memory-augmented framework for AR agents that enhances their ability to perform complex, personalized, multi-step tasks by integrating long-term user experience and spatiotemporal reasoning.

Contribution

It introduces a novel conceptual framework with four modules for memory-augmented AR agents, enabling personalized, context-aware assistance over time.

Findings

Framework design with four interconnected modules

Practical implementation roadmap and use cases

Potential for improved long-term personalized AR assistance

Abstract

Augmented Reality (AR) systems are increasingly integrating foundation models, such as Multimodal Large Language Models (MLLMs), to provide more context-aware and adaptive user experiences. This integration has led to the development of AR agents to support intelligent, goal-directed interactions in real-world environments. While current AR agents effectively support immediate tasks, they struggle with complex multi-step scenarios that require understanding and leveraging user's long-term experiences and preferences. This limitation stems from their inability to capture, retain, and reason over historical user interactions in spatiotemporal contexts. To address these challenges, we propose a conceptual framework for memory-augmented AR agents that can provide personalized task assistance by learning from and adapting to user-specific experiences over time. Our framework consists of four interconnected modules: (1) Perception Module for multimodal sensor processing, (2) Memory Module for persistent spatiotemporal experience storage, (3) Spatiotemporal Reasoning Module for synthesizing past and present contexts, and (4) Actuator Module for effective AR communication. We further present an implementation roadmap, a future evaluation strategy, a potential target application and use cases to demonstrate the practical applicability of our framework across diverse domains. We aim for this work to motivate future research toward developing more intelligent AR systems that can effectively bridge user's interaction history with adaptive, context-aware task assistance.