Skip to content

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

Oct 13 · Tuesday

All papers

Found 6 papers
Filter5

System type

Models and APIs48LLM applications12AI Agent27coding agent5Multi-agent systems6Embodied systems and robotics1

Layer

Prompt layer0Model layer1Application layer5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
System type：coding agentSystem type：Embodied systems and roboticsLayer：Prompt layerLayer：Model layerLayer：Application layerClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  2. Analysis and theoryarXiv 2610.09517

    审计发现 CLIP 安全分数主要反映画面与提示词场景的相似度

    开环审计冻结视觉语言安全分，发现其反映场景模板而非危险感知

    arXiv
    2610.09517
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    CLIP ViT-B/32, CLIP ViT-L/14, Qwen2-VL-7B
    Abstract论文审计了冻结 VLM 安全评分机制，指出其反映场景模板而非危险感知，为安全强化学习评估提供了严谨基准。

    本文是一项针对安全强化学习中冻结视觉语言模型（VLM）安全评分机制的实证审计研究。

    Paper analysisRead analysis
  3. Analysis and theoryarXiv 2610.06001

    AgentSpy: Observing AI agent behavior at the system call layer and detecting skill injection attacks

    提出 AgentSpy，在系统调用层观测 Agent 行为并检测技能注入

    arXiv
    2610.06001
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    gpt-5.6-terra, deepseek-v4-flash, glm-5.3-flash and others4
    Abstract提出了系统级智能体监控框架 AgentSpy，揭示出通过测试背后的非预期行为与注入风险。

    本研究提出了面向 AI 智能体的系统级外部监控与行为分析框架 AgentSpy。

    Paper analysisRead analysis
  4. Analysis and theoryarXiv 2610.06163

    SAGE：定位 LLM Agent 修复中最早偏离安全意图的环节

    提出 SAGE，定位代码修复 Agent 最早偏离安全意图的轮次

    arXiv
    2610.06163
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.5, Claude Opus 4.8, Gemini 3.1 Pro and others6
    AbstractSAGE 在已通过检查的修复轨迹上定位静默失败的最早偏离，类型比轮次更稳定。

    SAGE 在已通过语法和功能检查、但仍含确认安全缺陷的智能体修复轨迹上，定位最早可归因的安全意图偏离。。

    Paper analysisRead analysis
  5. Analysis and theoryarXiv 2610.04375

    Paper reveals that LLM agent tool calls are rewritten during execution paths, and proposes IntAct as a fix

    提出 IEC 与 IntAct，测量并修复 Agent 工具调用的路径篡改

    arXiv
    2610.04375
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    qwen3-coder-plus, Qwen2.5-Coder-32B, Qwen2.5-72B and others4

    Abstract论文界定工具调用在执行路径中的意图偏离问题，提出无执行归因协议与跳级修复，为智能体工程提供评测与设计准则。

    Paper analysisRead analysis
  6. Analysis and theoryarXiv 2609.27263

    GitHub Agentic Workflows 的智能体工作流规范与维护实证研究

    实证调查 gh-aw 工作流规范的结构、维护演化与指令防护

    arXiv
    2609.27263
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Gemini 3.1 Pro, GLM-5.2, gpt-oss
    Abstractgh-aw 指令又长又常改，任务和约束很常见，显式注入防护很少，LLM 标注与人工标签大体一致。

    这是一项对 GitHub Agentic Workflows Markdown 的仓库挖掘，目标是描述开发者如何规定并维护会反复执行的智能体工作。

    Paper analysisRead analysis
You have reached the end