Home // CLOUD COMPUTING 2026, The Seventeenth International Conference on Cloud Computing, GRIDs, and Virtualization // View article
Authors:
Rana Nameer Hussain Khan
Dawood Wasif
Jin-Hee Cho
Ali R Butt
Keywords: Infrastructure as Code; multi-agent systems; Large Language Models; program synthesis; policy as code
Abstract:
The increasing complexity of cloud-native infrastructure has made Infrastructure-as-Code (IaC) essential for reproducible and scalable deployments. While Large Language Models (LLMs) have shown promise in generating IaC snippets from natural language prompts, their monolithic, single-pass generation approach often results in syntactic errors, policy violations, and unscalable designs. In this paper, we propose MACOG (Multi-Agent Code-Orchestrated Generation), a novel multi-agent LLM-based architecture for IaC generation that decomposes the task into modular subtasks handled by specialized agents: Architect, Provider Harmonizer, Engineer, Reviewer, Security Prover, Cost and Capacity Planner, DevOps, and Memory Curator. The agents interact via a shared-blackboard, finite-state orchestrator layer, and collectively produce Terraform configurations that are not only syntactically valid but also policy-compliant, semantically coherent. To ensure infrastructure correctness and governance, we incorporate Terraform Plan for execution validation and Open Policy Agent (OPA) for customizable policy enforcement. We evaluate MACOG using the IaC-Eval benchmark, where MACOG is the top enhancement across models, e.g., GPT-5 improves from 54.90 (RAG) to 74.02 and Gemini-2.5 Pro from 43.56 to 60.13, with concurrent gains on BLEU, CodeBERTScore, and an LLM-judge metric. Ablations show constrained decoding and deploy feedback are critical. Removing them drops IaC-Eval to 64.89 and 56.93, respectively.
Pages: 71 to 76
Copyright: Copyright (c) IARIA, 2026
Publication date: April 19, 2026
Published in: conference
ISSN: 2308-4294
ISBN: 978-1-68558-373-6
Location: Lisbon, Portugal
Dates: from April 19, 2026 to April 23, 2026