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

arXiv: https://arxiv.org/abs/2411.19043 · HTML: https://mlsanity.com/paper/2411.19043/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 28 Nov 2024.

## Builds on (most cited first, 8 of 8)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models](https://mlsanity.com/paper/2311.16543/) (2023)
- [SynCode: LLM Generation with Grammar Augmentation](https://mlsanity.com/paper/2403.01632/) (2024)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [A Survey of using Large Language Models for Generating Infrastructure as Code](https://mlsanity.com/paper/2404.00227/) (2024)
- [Statically Inferring Usage Bounds for Infrastructure as Code](https://mlsanity.com/paper/2402.15632/) (2024)

## Built on by (most cited first, 5 of 5)

- [Reliable Proof Generation with LLMs via Analogical Retrieval and Symbolic Verification: A Case Study in Euclidean Geometry](https://mlsanity.com/paper/2505.14479/) (2025)
- [TerraFormer: Automated Infrastructure-as-Code with LLMs Fine-Tuned via Policy-Guided Verifier Feedback](https://mlsanity.com/paper/2601.08734/) (2026)
- [ARPaCCino: An Agentic-RAG for Policy as Code Compliance](https://mlsanity.com/paper/2507.10584/) (2025)
- [Deployability-Centric Infrastructure-as-Code Generation: Fail, Learn, Refine, and Succeed through LLM-Empowered DevOps Simulation](https://mlsanity.com/paper/2506.05623/) (2025)
- [Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency](https://mlsanity.com/paper/2608.14065/) (2026)

## Abstract (arXiv)

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.