Multi-Agent-Based Smart-Home Energy Management with Adaptive Reasoning

This paper introduces SmartHouseOperator, a multi-agent intelligent control framework for adaptive and energy-efficient smart-home management. Modern smart homes integrate heterogeneous devices and sensors, yet most existing solutions rely on static rules or manual coordination, limiting their ability to adapt to dynamic environmental conditions and evolving user preferences. SmartHouseOperator addresses these limitations through an agentic architecture that coordinates device-specific agents for air conditioning, lighting, refrigeration, and shutters under a central orchestrator. The system combines contextual inputs (e.g., weather, occupancy, power load), persistent knowledge, reinforcement-learning-based preference modeling, and LLM-powered reasoning to enable coordinated and personalized control decisions. Experimental results show that the framework achieves consistent reasoning performance across multiple agent orchestration engines and reduces air-conditioning power consumption by up to 16% under critical load conditions. These findings demonstrate the potential of multi-agent, learning-enabled control systems to deliver intelligent, energy-aware, and user-centric smart-home operation.