Large language model-based agent Schema and library for automated building energy analysis and modeling

Abstract

Large language models (LLMs) agents can function as autonomous, interactive, goal-oriented systems, but in the building energy sector, there is currently no structured paradigm that researchers and engineers can follow to create, access, and share effective LLM agents without starting from scratch. This paper introduces a JSON-based agent schema designed to structure the description of LLM agents. Additionally, the paper introduces an open-source library on GitHub that serves as a centralized repository for LLM agents designed for building energy analysis and modeling, all structured according to this schema. This library is publicly accessible, allowing users to utilize and upload agents, thereby enhancing the accessibility of LLM agents. The case studies demonstrate the schema's effectiveness with four example agents developed across different platform. These applications, developed on diverse platforms, successfully execute and seamlessly align with the proposed schema and can be reproduced without additional information beyond the schema.