OptAgent: an Agentic AI framework for Intelligent Building Operations

TL;DR

This paper introduces OptAgent, an agentic AI framework utilizing physics-informed machine learning for scalable, intelligent building energy management, demonstrating multi-agent coordination and benchmarking performance in real-world scenarios.

Contribution

It presents a novel modular AI environment with specialist agents and tools for comprehensive building energy modeling, control, and automation, advancing autonomous building operations.

Findings

Multi-domain, multi-agent coordination improves energy efficiency and comfort.

Benchmarking reveals impacts of model size and task complexity on performance.

Systematic evaluation guides future development of agentic AI in buildings.

Abstract

The urgent need for building decarbonization calls for a paradigm shift in future autonomous building energy operation, from human-intensive engineering workflows toward intelligent agents that interact with physics-grounded digital environments. This study proposes an end-to-end agentic AI-enabled Physics-Informed Machine Learning (PIML) environment for scalable building energy modeling, simulation, control, and automation. The framework consists of (1) a modular and physics-consistent PIML digital environment spanning building thermal dynamics, Heating, Ventilation, and Air Conditioning (HVAC), and distributed energy resources (DER) for grid-interactive energy management; and (2) an agentic AI layer with 11 specialist agents and 72 Model Context Protocol (MCP) tools that enable end-to-end execution of multi-step energy analytics. A representative case study demonstrates multi-domain, multi-agent coordination for assessing how system and control upgrades affect energy use, operating cost, thermal comfort, and flexibility. In addition, a large-scale benchmark (about 4000 runs) systematically evaluates workflow performance in terms of accuracy, token consumption, execution time, and inference cost. The results quantify the impacts of intelligence mode design, model size, task complexity, and orchestrator-specialist coordination, and provide key lessons for building future agentic AI systems in real-world building energy applications. This work establishes a scalable, physics-grounded foundation for deploying agentic AI in decarbonized and grid-interactive building operations.