Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications

• URL: http://arxiv.org/abs/2608.23870v1
• Date: Mon, 24 Aug 2026 22:20:57 GMT
• Title: Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications
• Abstract summary: Actionable Policy schema is a YAML-based format for specifying what model responses can and cannot contain.<n>Synthetic data generation pipeline produces policy-aligned training data for model alignment and testing.<n>Tools to help define the schema and enforce policy are available as open source.
• Score: 10.941104277511934
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When it comes to safety policies for generative AI, one size does not fit all. Each organization and use case needs to mitigate different risks depending on the application context, regulatory environment, organizational values, and user personas. Yet, existing policy specification approaches are designed for traditional access control and fail to capture the nuances of GenAI application: the enforcement of content-based constraints. We present two contributions to address this gap: (1) the Actionable Policy schema, a YAML-based format for specifying what model responses can and cannot contain. The schema enables exception-based policy governance, proposing exceptions to track policy violations; (2) synthetic data generation pipeline that produces policy-aligned training data for model alignment and testing, and a set of tools to help define the schema and enforce policy. Together, these enable organizations to specify policies once and enforce them throughout the GenAI application lifecycle: from model alignment to runtime monitoring. The Actionable Policy schema, example policies, and tools are available as open source: https://github.com/ibm-granite/granite.trust.policy-tools We welcome new ideas, contributions and feedback.

Related papers

• PolicyMem: Geometric Policy Memory for LLM Governance [72.04962480384322]
  We introduce PolicyMem, a geometric policy memory that externalizes natural-language policies as reusable geometric memory objects.<n>A memory writer compiles natural-language policies into policy memory slots, and query-response pairs read the policy memory through projection energy.<n>The resulting policy-evidence profile directly mediates the safety verdict and is reused for policy attribution and post-intervention verification.
  arXiv  Detail & Related papers  (2026-09-12T06:07:43Z)
• XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment [110.47421789797546]
  XPolicyLab is a unified standard and open ecosystem for robot policy evaluation and deployment.<n>XPolicyLab integrates 42 robot policies and standardizes their installation, debug, serving, adapters and evaluation.<n>In a controlled study, conforming to the standard reduces the integration effort of a representative policy from over five hours to two hours.
  arXiv  Detail & Related papers  (2026-08-10T17:41:04Z)
• Deontic Policies for Runtime Governance of Agentic AI Systems [2.1095754823099657]
  We propose AgenticRei, which realizes key governance requirements such as obligations, dispensations, policy conflict resolutions, and reasoning over policies.<n>Our approach composes naturally with industry-standard frameworks like A2AS.
  arXiv  Detail & Related papers  (2026-06-17T18:02:07Z)
• PolicyBank: Evolving Policy Understanding for LLM Agents [51.86716874651299]
  PolicyBank maintains structured, tool-level policy insights and iteratively refines them.<n>PolicyBank closes up to 82% of the gap toward a human oracle.
  arXiv  Detail & Related papers  (2026-04-16T20:29:30Z)
• Runtime Governance for AI Agents: Policies on Paths [4.111929395230638]
  We argue that the execution path is the central object for effective runtime governance.<n>In our view, runtime evaluation is the general case, and it is necessary for any path-dependent policy.
  arXiv  Detail & Related papers  (2026-03-17T14:35:52Z)
• Customize Multi-modal RAI Guardrails with Precedent-based predictions [55.63757336900865]
  A multi-modal guardrail must effectively filter image content based on user-defined policies.<n>Existing fine-tuning methods typically condition predictions on pre-defined policies.<n>We propose to condition model's judgment on "precedents", which are the reasoning processes of prior data points similar to the given input.
  arXiv  Detail & Related papers  (2025-07-28T03:45:34Z)
• Dense Policy: Bidirectional Autoregressive Learning of Actions [51.60428100831717]
  This paper introduces a bidirectionally expanded learning approach, termed Dense Policy, to establish a new paradigm for autoregressive policies in action prediction.<n>It employs a lightweight encoder-only architecture to iteratively unfold the action sequence from an initial single frame into the target sequence in a coarse-to-fine manner.<n>Experiments validate that our dense policy has superior autoregressive learning capabilities and can surpass existing holistic generative policies.
  arXiv  Detail & Related papers  (2025-03-17T14:28:08Z)
• Fat-to-Thin Policy Optimization: Offline RL with Sparse Policies [5.5938591697033555]
  Sparse continuous policies are distributions that choose some actions at random yet keep strictly zero probability for the other actions.<n>In this paper, we propose the first offline policy optimization algorithm that tackles this challenge: Fat-to-Thin Policy Optimization (FtTPO)<n>We instantiate FtTPO with the general $q$-Gaussian family that encompasses both heavy-tailed and sparse policies.
  arXiv  Detail & Related papers  (2025-01-24T10:11:48Z)
• PolicyLR: A Logic Representation For Privacy Policies [34.73520882451813]
  We propose PolicyLR, a new paradigm that offers a comprehensive machine-readable representation of privacy policies. PolicyLR converts privacy policies into a machine-readable format using valuations of atomic formulae. We demonstrate PolicyLR in three privacy tasks: Policy Compliance, Inconsistency Detection and Privacy Comparison Shopping.
  arXiv  Detail & Related papers  (2024-08-27T07:27:16Z)
• Towards Interpretable Foundation Models of Robot Behavior: A Task Specific Policy Generation Approach [1.7205106391379026]
  Foundation models are a promising path toward general-purpose and user-friendly robots. In particular, the lack of modularity between tasks means that when model weights are updated, the behavior in other, unrelated tasks may be affected. We present an alternative approach to the design of robot foundation models, which generates stand-alone, task-specific policies.
  arXiv  Detail & Related papers  (2024-07-10T21:55:44Z)
• Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints [82.43359506154117]
  We show that typical offline reinforcement learning methods fail to learn from data with non-uniform variability. Our method is simple, theoretically motivated, and improves performance across a wide range of offline RL problems in Atari games, navigation, and pixel-based manipulation.
  arXiv  Detail & Related papers  (2022-11-02T11:36:06Z)
• Mutual Information Regularized Offline Reinforcement Learning [76.05299071490913]
  We propose a novel MISA framework to approach offline RL from the perspective of Mutual Information between States and Actions in the dataset. We show that optimizing this lower bound is equivalent to maximizing the likelihood of a one-step improved policy on the offline dataset. We introduce 3 different variants of MISA, and empirically demonstrate that tighter mutual information lower bound gives better offline RL performance.
  arXiv  Detail & Related papers  (2022-10-14T03:22:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.