Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 1 paper
Filter3

Model risks

Reward hacking3Misalignment and value divergence1Dangerous agent actions11

System component

RAG0Monitors1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Model risks：Misalignment and value divergenceSystem component：RAGSystem component：MonitorsTopic: Agent safetyClear all
  1. DefensesarXiv 2609.15803

    研究者提出 k-robust 联盟对齐，用多智能体评审委托授权

    提出 k-robust 联盟对齐，刻画误对齐评审下的安全委托授权

    arXiv
    2609.15803
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract联盟覆盖使无个体对齐的评审面板仍可相对基线安全授权，数值分数改善完备性。

    委托授权的安全不要求每位评审者对齐，而要求面板在效用空间覆盖委托人。

    Paper analysisRead analysis
You have reached the end