Using a Feedback Loop for LLM-based Infrastructure as Code Generation

Autor:	Palavalli, Mayur Amarnath, Santolucito, Mark
Rok vydání:	2024
Předmět:	Computer Science - Software Engineering Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Code generation with Large Language Models (LLMs) has helped to increase software developer productivity in coding tasks, but has yet to have significant impact on the tasks of software developers that surround this code. In particular, the challenge of infrastructure management remains an open question. We investigate the ability of an LLM agent to construct infrastructure using the Infrastructure as Code (IaC) paradigm. We particularly investigate the use of a feedback loop that returns errors and warnings on the generated IaC to allow the LLM agent to improve the code. We find that, for each iteration of the loop, its effectiveness decreases exponentially until it plateaus at a certain point and becomes ineffective. Comment: 4 pages, submitted to accepted by International Journal of Secondary Computing and Applications Research
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.19043 Zobrazit plný text záznamu View this record from Arxiv