UserCentrix: An Agentic Memory-augmented AI Framework for Smart Spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Saleh, Alaa, Tarkoma, Sasu, Donta, Praveen Kumar, Lindgren, Anders, Motlagh, Naser Hossein, Dustdar, Schahram, Pirttikangas, Susanna, Lovén, Lauri
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911570565529600
author Saleh, Alaa
Tarkoma, Sasu
Donta, Praveen Kumar
Lindgren, Anders
Motlagh, Naser Hossein
Dustdar, Schahram
Pirttikangas, Susanna
Lovén, Lauri
author_facet Saleh, Alaa
Tarkoma, Sasu
Donta, Praveen Kumar
Lindgren, Anders
Motlagh, Naser Hossein
Dustdar, Schahram
Pirttikangas, Susanna
Lovén, Lauri
contents Agentic Artificial Intelligence (AI) constitutes a transformative paradigm in the evolution of intelligent agents and decision-support systems, redefining smart environments by enhancing operational efficiency, optimizing resource allocation, and strengthening systemic resilience. This paper presents UserCentrix, a hybrid agentic orchestration framework for smart spaces that optimizes resource management and enhances user experience through urgency-aware and intent-driven decision-making mechanisms. The framework integrates interactive modules equipped with agentic behavior and autonomous decision-making capabilities to dynamically balance latency, accuracy, and computational cost. User intent functions as a governing control signal that prioritizes decisions, regulates task execution and resource allocation, and guides the adaptation of decision-making strategies to balance trade-offs between speed and accuracy. Experimental results demonstrate that the framework autonomously enables efficient intent processing and real-time monitoring, while balancing reasoning quality and computational efficiency, particularly under resource-constrained edge conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00472
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UserCentrix: An Agentic Memory-augmented AI Framework for Smart Spaces
Saleh, Alaa
Tarkoma, Sasu
Donta, Praveen Kumar
Lindgren, Anders
Motlagh, Naser Hossein
Dustdar, Schahram
Pirttikangas, Susanna
Lovén, Lauri
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
Networking and Internet Architecture
Agentic Artificial Intelligence (AI) constitutes a transformative paradigm in the evolution of intelligent agents and decision-support systems, redefining smart environments by enhancing operational efficiency, optimizing resource allocation, and strengthening systemic resilience. This paper presents UserCentrix, a hybrid agentic orchestration framework for smart spaces that optimizes resource management and enhances user experience through urgency-aware and intent-driven decision-making mechanisms. The framework integrates interactive modules equipped with agentic behavior and autonomous decision-making capabilities to dynamically balance latency, accuracy, and computational cost. User intent functions as a governing control signal that prioritizes decisions, regulates task execution and resource allocation, and guides the adaptation of decision-making strategies to balance trade-offs between speed and accuracy. Experimental results demonstrate that the framework autonomously enables efficient intent processing and real-time monitoring, while balancing reasoning quality and computational efficiency, particularly under resource-constrained edge conditions.
title UserCentrix: An Agentic Memory-augmented AI Framework for Smart Spaces
topic Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
Networking and Internet Architecture
url https://arxiv.org/abs/2505.00472