arXiv Computation and Language

UniGuard: Multi-View Guardrail Learning for Cross-Interface Safety Generalization

UniGuard introduces a training framework that learns interface‑invariant safety representations by leveraging multiple semantically aligned views of the same safety case. The authors created the UniGuard‑FT dataset, transforming 1,000 public safety cases into prompt, response, multi‑turn conversation, agent‑trace, and multi‑agent‑trace formats, and trained a 0.6B model using classification, supervised contrastive learning, and asymmetric confidence calibration losses. On unseen‑interface benchmarks (ATBench, PolicyGuardBench, DynaBench), UniGuard‑0.6B outperforms its pretrained guardrail by an average of 45.12 F1 points and reduces expected calibration error by 35.41 points, while remaining competitive with much larger guardrails such as Claude‑Sonnet‑4.5 and GPT‑5.2.

arXiv AI

Oct 31

RePolicy: Learning to Select and Apply Safety Policies for Agent Safeguards

RePolicy is a safeguard that learns to both select the appropriate safety policy from a library and assess agent behavior against it. It processes an agent trajectory and a set of candidate policies, chooses the best-matching policy, applies its requirements, and predicts safety. The authors created PolicyTraj-20K, a dataset of over 20,000 annotated trajectories, and trained RePolicy with supervised and reinforcement learning, achieving top performance on six benchmarks and 19 baselines.

By Houcheng Jiang, Boxuan Zhang, Qiyong Zhong, Junfeng Fang, Xiang Wang, Xiangnan He

agents reinforcement-learning benchmarks safety

arXiv AI

Jun 6

From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

arXiv:2606. 05805v1 Announce Type: new Abstract: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk categories, and/or explanatory rationales about potential policy violations.

By Yuhao Sun, Jiacheng Zhang, Shaanan Cohney, Zhexin Zhang, Feng Liu, Xingliang Yuan

llms agents safety

arXiv AI

Jul 8

PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

arXiv:2607. 05910v1 Announce Type: cross Abstract: Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image.

By Mingyang Song, Luxin Xu, Haoyu Sun, Minzhou Pan, Yu Cheng, Bo Li

fine-tuning benchmarks safety

arXiv AI

Jul 3

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

arXiv:2607. 02072v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts.

By Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan

llms rag fine-tuning efficiency benchmarks safety

arXiv AI

Sep 7

Robust and Efficient Guardrails with Latent Reasoning

The paper introduces COLAGUARD, a guardrail model that embeds multi-step safety reasoning into a continuous latent space, allowing efficient hidden-state propagation during inference. Compared to existing methods, COLAGUARD achieves an 8.24‑point macro‑F1 improvement over Llama Guard 3 and matches the explicit reasoning baseline GuardReasoner, while delivering a 12.9× speedup and a 22.4× reduction in token usage across ten moderation settings and eight safety benchmarks.

By Siddharth Sai, Xiaofei Wen, Muhao Chen

llms diffusion benchmarks safety

arXiv Computer Vision

1d ago

Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model

The paper introduces NegWAM, a safety post‑training framework for unified world‑action models (WAMs) used in end‑to‑end autonomous driving. NegWAM generates negative trajectories that are close to expert paths but contain safety risks, using them as repulsive anchors to steer predictions away from dangerous behavior while encoding scene‑trajectory compatibility via rider tokens. The method achieves a 4.1% relative improvement on the NAVSIM v2 navhard benchmark and 93.3 EPDMS on navtest, demonstrating strong safety performance without sacrificing routine driving, and shows cross‑benchmark generalization in zero‑shot closed‑loop tests on HUGSIM.

By Zihao Zhang, Xinyu Zhang, Bing Zeng, Xingyu Chen, Zhenning Li, Bin Yu, Ziyuan Pu

agents robotics benchmarks safety

arXiv AI

Jul 21

A Dual-Hypothesis Reasoning Framework for LLM Guardrails

arXiv:2607. 17575v1 Announce Type: new Abstract: We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a prompt before making a safety decision, and (ii) multi-component supervised fine-tuning (MC-SFT), a structured training loss for reasoning-based guardrails that decomposes LLM outputs into logical components and weights them according to their importance.

By Md Asiful Islam, Mihai Surdeanu

llms fine-tuning benchmarks safety

arXiv AI

Jul 20

SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction

arXiv:2607. 15550v1 Announce Type: new Abstract: Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks where a single erroneous action can lead to irreversible consequences.

By Xue Yu, Bo Yuan, Pengshuai Yang, Kailin Zhao, Hong Hu, Junlan Feng

agents safety

arXiv AI

Aug 6

NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment

arXiv:2608. 04776v1 Announce Type: new Abstract: The ability to accurately assess and anticipate risks in safety-critical scenarios is crucial for autonomous driving systems.

By Yu Zhao, Jiangyu Pan, Tao Hu, Ming Yin, Fan Yang, Jiangfan Liu, Xiubo Liang

agents robotics benchmarks safety

arXiv Computer Vision

Sep 22

DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models

arXiv:2609.22762v1 Announce Type: new Abstract: Generative world-action models (WAMs) jointly generate future video and vehicle actions, while their action branches remain primarily optimized by expe...

By Fengcheng Yu, Dhruv Parikh, Junjie Ye, Maulik Bhatt, Thang Vu, Igor Vasiljevic, Vitor Guizilini, Yue Wang

safety

arXiv AI

Aug 12

Threat-guided Policy-aware Scene Perturbation for Safe Autonomous Driving with Online Reinforcement Learning

arXiv:2608. 10403v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient exposure to safety-critical driving scenes.

By Xincong Hu (Nanjing University), Lei Ou (Nanjing University), Maosen Li (Yinwang Intelligent Technology Co., Ltd), Jingtao Zhang (Yinwang Intelligent Technology Co., Ltd), Liguo Hou (Yinwang Intelligent Technology Co., Ltd), Zongzhang Zhang (Nanjing University)

agents reinforcement-learning robotics benchmarks safety

Hugging Face Trending Papers

Jun 22

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages.

llms nlp reinforcement-learning multimodal benchmarks safety

Related stories