Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

Agent safety · Papers

Found 2 papers
Filter3

System type

AI Agent8coding agent2

System component

MCP and skills3RAG0Guardrails and judges2Monitors4Permissions and sandboxing12
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
System type：coding agentSystem component：RAGSystem component：Guardrails and judgesTopic: Agent safetyClear all
  1. Evaluation and benchmarksarXiv 2610.11773

    研究提出 Agent 安全新维度：识别未履行的安全义务

    提出义务识别基准 ObligationBench，并训练护栏识别 Agent 未履行的安全义务

    arXiv
    2610.11773
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    ObligationGuard, Claude-Opus-4.8, GPT-5.6-Sol and others17
    Abstract义务是护栏缺口。

    作者认为编码智能体的安全不能只靠拦截禁止动作，还要找出终止时仍未做的安全关键动作，并将其称为义务。

    Paper analysisRead analysis
You have reached the end