Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 2 papers
Filter2

Impact

Unauthorized actions14Data and privacy leaks4Output manipulation2Oversight failure4

System type

AI Agent15coding agent2Multi-agent systems4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Impact：Output manipulationSystem type：coding agentTopic: Agent safetyClear all
  1. 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
  2. DefensesarXiv 2610.00850

    AuraForge：为训练安全编码 Agent 扩展安全监督

    提出 AuraForge，从漏洞修复合成安全测试并训练编码 Agent

    arXiv
    2610.00850
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    Qwen3.5-4B, GLM 4.7 Flash, Qwen3-Coder-Next and others7
    AbstractAuraForge 用攻击效果测试和防泄露环境做成 AuraGym，合成监督的误拒更低，训出的 4B 模型增益高于人工测试。

    AuraForge 把真实仓库的历史漏洞修复变成可执行训练任务，用来监督编程智能体同时满足功能请求和隐含的安全要求。

    Paper analysisRead analysis
You have reached the end