Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter2

Model risks

Dangerous agent actions3

System type

Models and APIs46AI Agent80coding agent17science agent10web agent4Browser and computer use1Multi-agent systems18Embodied systems and robotics4

Layer

Application layer4
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.
System type：web agentSystem type：Browser and computer useClear all

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

  1. Risky behaviorarXiv 2609.35291

    窄域多模态微调可诱发涌现性失配，覆盖 15 个视觉语言模型

    证明无显式危害的图文窄微调可诱发跨任务涌现未对齐

    arXiv
    2609.35291
    Published
    Layer
    Model layer
    Setting
    Browser and computer use
    Evaluated models
    GPT-4o, GPT-4.1, Gemini 2.5 and others15
    Abstract证实窄多模态微调可引发全面的多渠道未对齐行为转变，揭示了后训练阶段对齐被隐蔽重塑的安全隐患。

    论文系统探究了视觉-语言模型中由窄任务微调诱发的跨模态涌现未对齐（Emergent Misalignment, EM）现象。

    Paper analysisRead analysis
  4. Risky behaviorarXiv 2602.00851

    研究提出说服传播现象：无关说服性对话会改变 AI Agent 的任务执行行为

    测量任务无关说服对 Agent 编码与网页研究行为的影响

    arXiv
    2602.00851
    Published
    Layer
    Application layer
    Setting
    web agent, coding agent
    Evaluated models
    gpt-4.1-nano, mistral-nemo-12b, llama-3.1-8b
    Abstract任务无关说服会在轨迹上留下任务相关的行为痕迹，但立场易感性不能稳定预测其幅度。

    这篇工作测量一件事：与任务无关的说服进入对话之后，AI 智能体执行后面的编码或网页研究时，轨迹是否系统性不同，以及“更容易被说服”能否预测差有多大。

    Paper analysisRead analysis
You have reached the end