{"slug": "policy-as-skill-governed-llm-decision-support-with-evidence-deterministic-and", "title": "Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit", "summary": "A new arXiv paper (2609.27087v1) introduces Policy-as-Skill (PaS), a modular runtime that packages evidence validation, review routing, version control, and auditability as executable, versioned policy capabilities for LLM-based policy, compliance, risk, and operational decision support. Evaluating thirteen methods with a fixed Gemma4 backend on 600 development tasks, the authors report PaS+Audit reaches 53.8% exact accuracy, 0.346 macro-F1, 0.854 review F1, 1.000 citation precision, 0.984 policy-reference recall, and 1.000 audit completeness, outperforming LLM+RAG on most governance and review metrics. Deterministic control raises aggregate accuracy to 61.2% but is strongly task dependent, which the authors say supports selective rather than universal rule-based intervention.", "body_md": "arXiv:2609.27087v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/policy-as-skill-governed-llm-decision-support-with-evidence-deterministic-and", "canonical_source": "https://arxiv.org/abs/2609.27087", "published_at": "2026-09-24 04:00:00+00:00", "updated_at": "2026-09-24 04:30:13.234910+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-safety", "ai-research", "ai-policy"], "entities": ["Policy-as-Skill", "PaS", "Gemma4", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/policy-as-skill-governed-llm-decision-support-with-evidence-deterministic-and", "markdown": "https://wpnews.pro/news/policy-as-skill-governed-llm-decision-support-with-evidence-deterministic-and.md", "text": "https://wpnews.pro/news/policy-as-skill-governed-llm-decision-support-with-evidence-deterministic-and.txt", "jsonld": "https://wpnews.pro/news/policy-as-skill-governed-llm-decision-support-with-evidence-deterministic-and.jsonld"}}