{"version":1,"type":"story","url":"https://digestai.news/story/researchers-propose-policy-as-skill-for-governed-llm-decision-making","json":"https://digestai.news/story/researchers-propose-policy-as-skill-for-governed-llm-decision-making.json","markdown":"https://digestai.news/story/researchers-propose-policy-as-skill-for-governed-llm-decision-making.md","slug":"researchers-propose-policy-as-skill-for-governed-llm-decision-making","headline":"Researchers propose Policy-as-Skill for governed LLM decision-making","summary":"Researchers introduced **Policy-as-Skill (PaS)**, a modular runtime framework designed to integrate governance, evidence validation, and auditability into large language model (LLM) decision-making. The system packages policy functions as executable, versioned capabilities to handle tasks like compliance checks, risk assessments, and operational decisions.\n\nEvaluated on 600 development tasks using a fixed **Gemma4** backend, PaS+Audit achieved **53.8% exact accuracy** and **macro-F1 of 0.346**. With deterministic control, accuracy rose to **61.2%**, though performance varied by task. The framework outperformed traditional LLM+RAG approaches on governance and review metrics, including **citation precision of 1.000** and **policy-reference recall of 0.984**. The authors emphasize its potential for selective rule-based intervention rather than universal deterministic control.","keyPoints":["Policy-as-Skill (PaS) adds governance, evidence checks, and audit trails to LLM decision-making via modular, versioned policy modules","Tested on 600 tasks with **Gemma4**, achieving **53.8% exact accuracy** and **0.346 macro-F1** without deterministic control","Deterministic control boosts accuracy to **61.2%** but works best for specific tasks, not universally"],"whyItMatters":"PaS could reduce risks in high-stakes LLM applications like finance or healthcare by embedding compliance checks and audit trails directly into decision workflows. If adopted, it may shift industry focus toward governed AI systems over unconstrained models.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["Gemma4"],"people":[]},"firstPublishedAt":"2026-09-24T04:00:00Z","updatedAt":"2026-09-24T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit","url":"https://arxiv.org/abs/2609.27087","publishedAt":"2026-09-24T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers propose Policy-as-Skill for governed LLM decision-making\", 24 September 2026, https://digestai.news/story/researchers-propose-policy-as-skill-for-governed-llm-decision-making","publisher":"Digest AI","title":"Researchers propose Policy-as-Skill for governed LLM decision-making","datePublished":"2026-09-24T04:00:00Z","url":"https://digestai.news/story/researchers-propose-policy-as-skill-for-governed-llm-decision-making"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}