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
arXiv:2607. 06326v1 Announce Type: new Abstract: Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation.
By He Liu, Changtao Miao, Xinjie Yang, Tianle Song, Yin Wu, Junchi Chen, Bintao He, Xinyuan Zhang, Bo Zhang, Shi Yan, Wei Lu, Wei Wang, Danyang Xu, Jiansheng Cai, Zhe Li
AdaGuard is an adaptive guard model that evaluates language‑model agent trajectories against user‑defined policies. The authors created the AdaptiveSafety dataset, containing 10,939 training and 1,000 test examples with policy rules, counterfactuals, explanations, and violated rules. Using supervised pre‑training followed by the SafePO reinforcement‑learning algorithm, they built 0.6B, 4B, and 8B guard models, with the 4B version achieving 89.30% accuracy on AdaptiveSafety and 71.82% on DynaBench.
By Yunhao Feng, Yifan Ding, Yuxiang Xie, Zheng Li, Mingrui Lao, Zeyuan Wang, Yanming Guo
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
arXiv:2608. 03838v1 Announce Type: new Abstract: Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy.
By Zhinan Liu, Jie Li, Mingyu Kang, Jiayi Ji
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.
By Houcheng Jiang, Boxuan Zhang, Qiyong Zhong, Junfeng Fang, Xiang Wang, Xiangnan He
arXiv:2511. 04694v5 Announce Type: replace-cross Abstract: As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources within a single prompt context.
By Zishuo Zheng, Vidhisha Balachandran, Chan Young Park, Faeze Brahman, Sachin Kumar
VEPA is a framework that enables the verified evolution of formal guardrails for lifelong large language model agents. It represents guardrails as formal policies of symbolic rules over typed agent events, and during deployment uses LLM‑guided feedback to propose policy patches that fix new failures while preserving correct behavior. A deterministic verifier accepts only structurally valid, conflict‑free policies, and an evidence‑aware authority layer activates verified rules only when sufficient supporting evidence exists, ensuring that uncertain updates do not directly affect guardrail decisions.
By Duy Nguyen, Lesly Miculicich, Bhavana Dalvi Mishra, Shuo Li, Krishnamurthy Dj Dvijotham, Mohit Bansal, Tomas Pfister, Long T. Le
arXiv:2606. 07006v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert trajectory as the target behavior.
By Yongliang Miao, Fengyuan Liu, Wei Shi, Yanguang Liu, Fei Sun, Na Zou, Mengnan Du
SCOPE compiles natural‑language policies into neurosymbolic predicate programs that combine small neural models, deterministic extractors, and logical composition. The system is jointly optimized with adversarially generated counterexamples, achieving higher accuracy than prompt‑optimization, task‑decomposition, and workflow‑generation baselines on real‑world policy benchmarks. Programs trained with the weakest executor transfer to other models, enabling deployment on inexpensive models with stable, interpretable predictions.
By Arnon Mazza, Elad Levi
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.
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...