English(EN) Specification-based Security Evaluation of Real-World Agents Tool-Calling under Long-Horizon Context Tasks

新的RAS-Eval框架增强了LLM智能体安全评估能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

研究人员开发了RAS-Eval，一个用于评估大型语言模型（LLM）智能体安全性的新框架，特别适用于长时程、无人值守场景。与依赖LLM作为法官或智能体作为法官的现有方法不同，RAS-Eval使用线性时序逻辑（LTL）表示的形式化规范来验证工具调用轨迹和环境观察。这种方法提供了确定的判断，并能检测到基于日志的评估可能遗漏的瞬时安全违规行为。该框架已在包含1000个任务的基准数据集上进行了测试，涵盖了四种攻击面：间接提示注入、工具投毒、技能代码注入和工具代码注入。 AI

影响增强了在关键长时程任务中部署的LLM智能体的可靠性和安全性。

排序理由该集群描述了一篇详细介绍LLM智能体新评估框架的研究论文。[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: 33 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇详细介绍LLM智能体新评估框架的研究论文。[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; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yuchuan Fu, Minghe Wang, Xiaohan Yuan, Chenlin Zou, Kaitong Jia, Jinfeng Li, Dongxia Wang · 2026-11-11 05:00

面向长时域任务的真实世界Agent工具调用基于规格的安全评估

arXiv:2506.15253v2 Announce Type: replace-cross Abstract: As large language model (LLM) agents are increasingly deployed in long-horizon unattended scenarios, security evaluation of them before deployment becomes increasingly essential and challenging. Existing evaluation methods…

本文如何被排名

报道来源 [1]

面向长时域任务的真实世界Agent工具调用基于规格的安全评估

相关实体

相关话题