Skip to content

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

Oct 13 · Tuesday

Agent safety · Papers

Found 1 paper
Filter2

Model risks

Dangerous agent actions20Inappropriate refusal1

System type

coding agent1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Model risks：Inappropriate refusalSystem type：coding agentTopic: Agent safetyClear all
  1. 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