Enhancing the development of Cherenkov Telescope Array control software with Large Language Models
This work addresses software development and operational efficiency for the Cherenkov Telescope Array Observatory, representing an incremental application of existing methods to a new domain.
The authors tackled the challenge of developing control software for the Cherenkov Telescope Array by creating AI agents based on instruction-finetuned large language models to assist in engineering and operations, integrating these features into pipelines for operations and offline data analysis.
We develop AI agents based on instruction-finetuned large language models (LLMs) to assist in the engineering and operation of the Cherenkov Telescope Array Observatory (CTAO) Control and Data Acquisition Software (ACADA). These agents align with project-specific documentation and codebases, understand contextual information, interact with external APIs, and communicate with users in natural language. We present our progress in integrating these features into CTAO pipelines for operations and offline data analysis.