# ARPaCCino: An Agentic-RAG for Policy as Code Compliance

arXiv: https://arxiv.org/abs/2507.10584 · HTML: https://mlsanity.com/paper/2507.10584/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 11 Jul 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 7 of 7)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [A Survey of using Large Language Models for Generating Infrastructure as Code](https://mlsanity.com/paper/2404.00227/) (2024)
- [Using a Feedback Loop for LLM-based Infrastructure as Code Generation](https://mlsanity.com/paper/2411.19043/) (2024)
- [Challenges and solutions when adopting DevSecOps: A systematic review](https://mlsanity.com/paper/2103.08266/) (2021)
- [ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges](https://mlsanity.com/paper/2504.12143/) (2025)
- [Large Language Models for IT Automation Tasks: Are We There Yet?](https://mlsanity.com/paper/2505.20505/) (2025)

## Built on by (most cited first, 4 of 4)

- [CodeScout: Contextual Problem Statement Enhancement for Software Agents](https://mlsanity.com/paper/2603.05744/) (2026)
- [Near-Miss: Latent Policy Failure Detection in Agentic Workflows](https://mlsanity.com/paper/2603.29665/) (2026)
- [Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego](https://mlsanity.com/paper/2603.15799/) (2026)
- [Towards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Harness](https://mlsanity.com/paper/2609.00050/) (2026)

## Abstract (arXiv)

Policy as Code (PaC) is a paradigm that encodes security and compliance policies into machine-readable formats, enabling automated enforcement in Infrastructure as Code (IaC) environments. However, its adoption is hindered by the complexity of policy languages and the risk of misconfigurations. In this work, we present ARPaCCino, an agentic system that combines Large Language Models (LLMs), Retrieval-Augmented-Generation (RAG), and tool-based validation to automate the generation and verification of PaC rules. Given natural language descriptions of the desired policies, ARPaCCino generates formal Rego rules, assesses IaC compliance, and iteratively refines the IaC configurations to ensure conformance. Thanks to its modular agentic architecture and integration with external tools and knowledge bases, ARPaCCino supports policy validation across a wide range of technologies, including niche or emerging IaC frameworks. Experimental evaluation involving a Terraform-based case study demonstrates ARPaCCino's effectiveness in generating syntactically and semantically correct policies, identifying non-compliant infrastructures, and applying corrective modifications, even when using smaller, open-weight LLMs. Our results highlight the potential of agentic RAG architectures to enhance the automation, reliability, and accessibility of PaC workflows.