paper-with-me

Papers

Deployability-Centric Infrastructure-as-Code Generation: An LLM-based Iterative Framework

2025-06-05 · Tianyi Zhang, Shidong Pan, Zejun Zhang, Zhenchang Xing, Xiaoyu Sun

Infrastructure-as-Code (IaC) generation holds significant promise for automating cloud infrastructure provisioning. Recent advances in Large Language Models (LLMs) present a promising opportunity to democratize IaC development by generating deployable infrastructure templates from natural language descriptions, but current evaluation focuses on syntactic correctness while ignoring deployability, the fatal measure of IaC template utility. We address this gap through two contributions: (1) IaCGen, an LLM-based deployability-centric framework that uses iterative feedback mechanism to generate IaC templates, and (2) DPIaC-Eval, a deployability-centric IaC template benchmark consists of 153 real-world scenarios that can evaluate syntax, deployment, user intent, and security. Our evaluation reveals that state-of-the-art LLMs initially performed poorly, with Claude-3.5 and Claude-3.7 achieving only 30.2% and 26.8% deployment success on the first attempt respectively. However, IaCGen transforms this performance dramatically: all evaluated models reach over 90% passItr@25, with Claude-3.5 and Claude-3.7 achieving 98% success rate. Despite these improvements, critical challenges remain in user intent alignment (25.2% accuracy) and security compliance (8.4% pass rate), highlighting areas requiring continued research. Our work provides the first comprehensive assessment of deployability-centric IaC template generation and establishes a foundation for future research.

📄 PDF Abstract BibTeX arXiv:2506.05623

Code (1)

Tianyi2/IaCGen 공식 구현

Tasks

Code Generation

Similar Papers 제목 키워드 기반

TerraFormer: Automated Infrastructure-as-Code with LLMs Fine-Tuned via Policy-Guided Verifier Feedback

2026-01-13 · Prithwish Jana, Sam Davidson, Bhavana Bhasker, Andrey Kan 외 arxiv

Automating Infrastructure-as-Code (IaC) is challenging, and large language models (LLMs) often produce incorrect configurations from natural language (NL). We present TerraFormer, a neuro-symbolic framework for IaC gener…

Reinforcement Learning

Architectural Constraints Alignment in AI-assisted, Platform-based Service Development

2026-05-06 · Julius Irion, Moritz Leugers, Paul Hartwig, Simon Kling 외 arxiv

AI-assisted development tools enable rapid prototyping of services but often lack awareness of architectural constraints, infrastructure dependencies, and organizational standards required in production environments. Con…

Code Generation

Compared to What? A Human-Anchored Security Benchmark for LLM-Generated Infrastructure-as-Code

2026-08-28 · Animesh Shaw arxiv

Large language models are increasingly used to author Infrastructure-as-Code (IaC), where a single insecure default can be deployed directly into production. Prior evaluations report raw vulnerability counts for model-ge…

The Principles of Data-Centric AI (DCAI)

2022-11-26 · Mohammad Hossein Jarrahi, Ali Memariani, Shion Guha

Data is a crucial infrastructure to how artificial intelligence (AI) systems learn. However, these systems to date have been largely model-centric, putting a premium on the model at the expense of the data quality. Data …

Rethinking the Role of Infrastructure in Collaborative Perception

2024-10-15 · Hyunchul Bae, Minhee Kang, Minwoo Song, Heejin Ahn

Collaborative Perception (CP) is a process in which an ego agent receives and fuses sensor information from surrounding vehicles and infrastructure to enhance its perception capability. To evaluate the need for infrastru…