mlsanityData to 14 Oct 2026

Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit

arXiv 2609.27087 ↗First posted 22 Sep 2026cs.AI cs.SCcited by 0

Not on the map. Why?

Abstract (arXiv)

Organizations increasingly use LLMs for policy, compliance, risk, and operational decision support, requiring evidence validation, review routing, version control, and auditability. We introduce Policy-as-Skill (PaS), a modular runtime that packages these functions as executable, versioned policy capabilities. Thirteen methods are evaluated with a fixed Gemma4 backend on 600 development tasks. PaS+Audit achieves 53.8% exact accuracy, macro-F1 0.346, review F1 0.854, citation precision 1.000, policy-reference recall 0.984, and audit completeness 1.000, outperforming LLM+RAG on most governance and review metrics. Deterministic control raises aggregate accuracy to 61.2% but is strongly task dependent, supporting selective rather than universal rule-based intervention.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 22 Sep 2026.

Builds on

19 of 27 references.

References · 19

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 350
  5. 2023Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planningcited by 61
  6. 2024Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them incited by 46
  7. 2024MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimizationcited by 16
  8. 2024StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Modelscited by 14
  9. 2025Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agentscited by 14
  10. 2023Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Modelscited by 9
  11. 2023Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learningcited by 7
  12. 2024Privacy Policy Analysis through Prompt Engineering for LLMscited by 6
7 more
  1. 2024Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agentscited by 6
  2. 2025Using LLMs for Automated Privacy Policy Analysis: Prompt Engineering, Fine-Tuning and Explainabilitycited by 4
  3. 2025Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendationcited by 4
  4. 2024Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidancecited by 3
  5. 2026Prompt Governance? On Governing Technologies Governed by Natural Languagecited by 3
  6. 2024A Minimalist Prompt for Zero-Shot Policy Learningcited by 2
  7. 2025Prompt Commons: Collective Prompting as Governance for Urban AIcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Judgment Quality to Downstream Utility: Rethinking LLM-as-a-Judge for Open-Ended Tasks
  2. 2026Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies
  3. 2025Executable Governance for AI: Translating Policies into Rules Using LLMs
  4. 2026SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs
  5. 2026Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation
  6. 2026COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
  7. 2026Interactive Critique-Revision Training for Reliable Structured LLM Generation
  8. 2026Policy-Invisible Violations in LLM-Based Agents