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

2025-05-01

AI Summary

Intelligent spaces suffer from insufficient dynamic, context-aware decision-making capabilities. Method: This paper proposes UserCentrix—a memory-augmented, personalized large language model (LLM) agent framework enabling meta-reasoning for autonomous decision-making. It introduces a hybrid hierarchical control architecture integrating centralized coordination with distributed execution; a task-urgency-driven proactive scaling mechanism; a Value-of-Information (VoI)-guided decision paradigm; and multi-agent collaborative negotiation. Contribution/Results: By synergistically integrating generative AI, LLM-based memory management, and multi-agent collaboration, UserCentrix significantly improves response accuracy, system efficiency, and computational resource utilization in real-world intelligent space deployments.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Multiagent Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Agentic AI, with its autonomous and proactive decision-making, has transformed smart environments. By integrating Generative AI (GenAI) and multi-agent systems, modern AI frameworks can dynamically adapt to user preferences, optimize data management, and improve resource allocation. This paper introduces UserCentrix, an agentic memory-augmented AI framework designed to enhance smart spaces through dynamic, context-aware decision-making. This framework integrates personalized Large Language Model (LLM) agents that leverage user preferences and LLM memory management to deliver proactive and adaptive assistance. Furthermore, it incorporates a hybrid hierarchical control system, balancing centralized and distributed processing to optimize real-time responsiveness while maintaining global situational awareness. UserCentrix achieves resource-efficient AI interactions by embedding memory-augmented reasoning, cooperative agent negotiation, and adaptive orchestration strategies. Our key contributions include (i) a self-organizing framework with proactive scaling based on task urgency, (ii) a Value of Information (VoI)-driven decision-making process, (iii) a meta-reasoning personal LLM agent, and (iv) an intelligent multi-agent coordination system for seamless environment adaptation. Experimental results across various models confirm the effectiveness of our approach in enhancing response accuracy, system efficiency, and computational resource management in real-world application.

Problem

• Enhancing smart spaces through dynamic context-aware decision-making
• Optimizing real-time responsiveness with hybrid hierarchical control
• Improving resource efficiency via memory-augmented reasoning and agent coordination

Innovation

• Integrates personalized LLM agents with memory management
• Uses hybrid hierarchical control for real-time responsiveness
• Employs memory-augmented reasoning and adaptive orchestration