arXiv AI
PolicyMem: Geometric Policy Memory for LLM Governance
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
Aug 26
RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards
RePolicy is a reinforcement learning approach designed to invoke safety policies for language model agents by evaluating entire execution trajectories within context-dependent policy libraries. It generates policy-grounded rationales and safety judgments, and is initialized with the PolicyTraj-20K dataset before fine-tuning via GRPO with verifiable rewards and policy-context perturbation. Experiments on six safety benchmarks demonstrate strong safety-detection performance and robust policy invocation across varying contexts.
Hugging Face Trending Papers
Aug 25
RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards
Safeguarding language model agents requires assessing complete execution trajectories under context-dependent safety policies. Existing policy-aware safeguards mainly rely on prompting or supervised f...
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 Machine Learning
Sep 2
Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs
The paper introduces a training‑free approach to detect policy violations in large language models by treating the task as an out‑of‑distribution problem in the model’s activation space. It uses whitening‑inspired techniques to compute policy‑violation scores directly from normalized hidden activations, requiring only the policy text and a few illustrative examples. Experiments on several LLMs and policy benchmarks show the method achieves up to 86.0% F1, outperforming fine‑tuned and LLM‑as‑a‑judge baselines while being computationally lightweight.
Hugging Face Trending Papers
Jun 24
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, in real-world deployment, emerging safety requirements are often specified as natural-language policies, while corresponding supervision data may be costly, delayed, or unavailable.