Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter5

System type

LLM applications12AI Agent23coding agent1web agent7Browser and computer use4Multi-agent systems0Embodied systems and robotics3

Layer

Prompt layer3Model layer5Application layer4

System component

MCP and skills27Memory19Guardrails and judges11Monitors26Permissions and sandboxing23Fine-tuning and open weights3Vision4Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
System type：coding agentSystem type：Multi-agent systemsSystem type：Embodied systems and roboticsLayer：Application layerSystem component：MultimodalClear all

Another 262papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.38948

    DrivingBench 发布：让视觉语言模型驾驶丰田 Corolla 绕桩

    提出 DrivingBench，评测通用视觉语言模型能否闭环驾驶真车

    arXiv
    2609.38948
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    Evaluated models
    GPT-6 Astra, Claude Fable 5.1, Grok 4.6 and others4
    Abstract仅 Astra 第二次跑完低速锥桶路线。

    DrivingBench 评测通用 VLM 能否自己闭环开真车，推理延迟也算进任务。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2609.35912

    MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

    提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作

    arXiv
    2609.35912
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-sol, Kimi-K2.6, Kimi-K3 and others6

    Abstract论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。

    Paper analysisRead analysis
  4. AttacksarXiv 2505.23266

    AdvOF：用对抗物体融合攻击 VLM 驱动的视觉语言导航智能体

    提出 AdvOF，生成对抗物体误导视觉语言导航智能体的场景感知

    arXiv
    2505.23266
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    Attacker
    White-box
    Evaluated models
    Lseg, Clip, ViT-L/16 and others5
    AbstractAdvOF 以多视角融合生成对抗物体。

    AdvOF 是针对 VLM 驱动 VLN 服务导航的对抗物体攻击。

    Paper analysisRead analysis
You have reached the end