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

Model risks

Deception and scheming4Reward hacking7Dangerous agent actions71Inappropriate refusal2

System type

AI Agent2Multi-agent systems0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Model risks：Inappropriate refusalSystem type：AI AgentSystem type：Multi-agent systemsTopic: Agent safetyClear all
  1. Evaluation and benchmarksarXiv 2609.33658

    AgentBound：面向工具型 LLM Agent 安全的四路反事实评测框架

    提出 AGENT BOUNDARY，用四向反事实任务评测工具智能体行动边界

    arXiv
    2609.33658
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.5, Claude Opus 4.8, Gemini 3.5 Flash and others15
    Abstract四向反事实基准把过度拒绝和未授权遵从拆开，Thought 校正在十个配置上提高已授权完成。

    AGENT BOUNDARY 是面向工具使用 LLM 智能体的四向可执行反事实评测，并附带一个决策时 Thought 校准模块。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2605.19722

    研究用 30 项漏洞分析任务评测自主安全智能体的安全对齐效果

    评测自主安全智能体在授权漏洞分析中的对齐拒答效应

    arXiv
    2605.19722
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Gemma 4 31B official instruction-tuned model, TrevorJS Gemma 4 31B uncensored GGUF, Gemma 4 26B A4B official instruction-tuned model and others8
    Abstract轨迹级评测把拒答、接地、工具接口分开。

    这项工作把安全对齐效应测成自主安全智能体的轨迹属性，而不是单轮拒答率。

    Paper analysisRead analysis
You have reached the end