English(EN) AdaGuard: An Adaptive Guard Model with User-defined Policies

新的AdaGuard模型可适应用户定义的策略，以实现更安全的AI代理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了AdaGuard，这是一种新颖的自适应守护模型，旨在通过允许用户定义策略来增强语言模型代理的安全性。与固定的守护模型不同，AdaGuard可以解释和执行因不同应用程序和任务而异的策略。为了促进这一点，创建了一个名为AdaptiveSafety的新数据集，其中包含近12,000个用于训练和测试的示例。该团队还引入了SafePO，这是一种强化学习算法，通过平衡解释性推理和最终判决来完善违规识别，从而使AdaGuard模型在安全基准测试中达到高精度。 AI

影响通过允许灵活的用户定义策略来增强AI代理的安全性，有可能改善跨不同应用程序的部署。

排序理由该集群描述了一篇关于AI安全的新模型、数据集和算法的详细研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇关于AI安全的新模型、数据集和算法的详细研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yunhao Feng, Yifan Ding, Yuxiang Xie, Zheng Li, Mingrui Lao, Zeyuan Wang, Yanming Guo · 2026-10-23 04:00

AdaGuard: An Adaptive Guard Model with User-defined Policies

arXiv:2609.34241v2 Announce Type: replace Abstract: Guard models support the safe deployment of language model agents, but fixed risk taxonomies limit their ability to accommodate requirements that vary across applications and tasks. Under user-defined policies, detecting violati…

本文如何被排名

报道来源 [1]

AdaGuard: An Adaptive Guard Model with User-defined Policies

相关实体

相关话题