arXiv AI
Which Rules Matter Now? Policy-Centroid Routing Before an Intelligent System Acts
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 30
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing
arXiv:2606. 29887v1 Announce Type: new Abstract: In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on predefined risk taxonomies.
arXiv AI
Jul 1
PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines
arXiv:2606. 32004v1 Announce Type: new Abstract: Policy-grounded document review requires determining whether a target document complies with organization-specific policies, guidelines, or playbooks.
arXiv AI
Aug 11
PolicyKG: An Agentic LLM Pipeline for Translating Institutional Policies into SHACL Knowledge Graphs
arXiv:2608. 09028v1 Announce Type: new Abstract: Institutional policies stay in natural language while the systems that check compliance demand machine-readable constraints.
arXiv AI
Jul 7
AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis
arXiv:2607. 03656v1 Announce Type: cross Abstract: Large Language Models are increasingly used to turn natural-language requirements into code.
arXiv AI
Sep 18
Governance-as-Code: Translating EU AI Act Technical Requirements into Executable Compliance Pipelines for Generative AI Systems
The paper introduces Governance-as-Code (GaC), a framework that translates the EU AI Act’s technical requirements into 43 machine‑checkable acceptance criteria across six compliance modules. GaC runs within a CI/CD pipeline, producing Article‑indexed audit evidence and providing actual Rego policy code. The authors validate GaC on two enterprise deployments, showing it reproduces manual audit findings—including three penalty‑triggering violations—while reducing audit labor by about 75%.
arXiv AI
Sep 17
Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows
The paper introduces the concept of Compositional Policy Violations (CPVs), where each step in an agentic AI workflow passes its individual compliance check, yet the overall execution violates higher‑level policies such as referral thresholds or authority limits. It categorizes CPVs into four types—Authority Creep, Threshold Laundering, Cumulative Sum Violation, and Context Collapse—and argues that the appropriate remedy depends on where the guarded quantity changes. To address this, the authors propose a provenance‑aware runtime architecture that evaluates policies over complete execution traces, recomputing guarded quantities from raw provenance rather than relying on step‑level outputs.