mlsanityData to 7 Oct 2026

Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego

arXiv 2603.15799 ↗First posted 16 Mar 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Prose2Policy (P2P) is a LLM-based practical tool that translates natural-language access control policies (NLACPs) into executable Rego code (the policy language of Open Policy Agent, OPA). It provides a modular, end-to-end pipeline that performs policy detection, component extraction, schema validation, linting, compilation, automatic test generation and execution. Prose2Policy is designed to bridge the gap between human-readable access requirements and machine-enforceable policy-as-code (PaC) while emphasizing deployment reliability and auditability. We evaluated Prose2Policy on the ACRE dataset and demonstrated a 95.3% compile rate for accepted policies, with automated testing achieving a 82.2% positive-test pass rate and a 98.9% negative-test pass rate. These results indicate that Prose2Policy produces syntactically robust and behaviorally consistent Rego policies suitable for Zero Trust and compliance-driven environments.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 32 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

11 of 32 references.

References · 11

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  4. 2025Authenticated Delegation and Authorized AI Agentscited by 63
  5. 2024Cedar: A New Language for Expressive, Fast, Safe, and Analyzable Authorization (Extended Version)cited by 31
  6. 2025Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcementcited by 15
  7. 2023SoK: Access Control Policy Generation from High-level Natural Language Requirementscited by 5
  8. 2024RAGent: Retrieval-based Access Control Policy Generationcited by 5
  9. 2025Multi-Agent Code-Orchestrated Generation for Reliable Infrastructure-as-Codecited by 5
  10. 2025ARPaCCino: An Agentic-RAG for Policy as Code Compliancecited by 4
  11. 2025ArGen: Auto-Regulation of Generative AI via GRPO and Policy-as-Codecited by 2

Built on by

Not cited yet.