Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Model risks

Reward hacking4Misalignment and value divergence1Dangerous agent actions4

System type

Models and APIs16AI Agent1coding agent0web agent0

Layer

Application layer19Training and data layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.
Model risks：Misalignment and value divergenceSystem type：AI AgentSystem type：coding agentSystem type：web agentLayer：Training and data layerClear all

Another 247papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.07935

    SIGMA：让模型依据 Model Spec 自我改进安全对齐

    提出 SIGMA，让模型依据 Model Spec 自造对齐数据并改进安全对齐

    arXiv
    2610.07935
    Published
    Layer
    Training and data layer
    Setting
    AI Agent
    Evaluated models
    Qwen3.6-27B
    AbstractSIGMA 用 Model Spec 自造监督，单轮训练可迁到多项智能体安全指标。

    SIGMA 让 Qwen3.6-27B 只凭 Model Spec 和高层领域，自己生产对齐任务、评分细则和奖励。

    Paper analysisRead analysis
You have reached the end