Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter4

Model risks

Misalignment and value divergence1Hallucination and fabrication0

Defense type

Inference-time intervention1Detection and filtering4Permissions and approval3Monitoring and auditing5

Layer

Model layer10Application layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Model risks：Misalignment and value divergenceModel risks：Hallucination and fabricationDefense type：Inference-time interventionLayer：Application layerClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2608.27348

    INTENT-AS-A-TOOL：用意图工具追踪智能体失准

    提出 INTENT-AS-A-TOOL，用意图工具概率跟踪并干预智能体失准

    arXiv
    2608.27348
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemma-4-31B-IT, Qwen3.5-27B, Qwen3-235B-A22B and others5
    Abstract用意图工具的下一动作概率跟踪推理中的失准承诺，并在其成为首选时插入反思。

    Zhang 等人研究推理型语言模型在职场邮件沙箱里如何走向智能体失准，并提出用动作偏好而不是事后文本标签来跟踪承诺。问题是：有害执行往往出现在推理已经形成意图之后，但 CoT 监控是事后、粗粒度、依赖外部评审的，也看不到模型倾向调用哪个动作。

    Paper analysisRead analysis
You have reached the end