Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter4

Impact

Output manipulation2

System type

Models and APIs13AI Agent3coding agent1science agent1web agent0
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.
Impact：Output manipulationSystem type：coding agentSystem type：science agentSystem type：web agentClear all

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

  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. Analysis and theoryarXiv 2609.27234

    CELLAUDIT：审计 AI 智能体发现细胞模型中的输入使用声明

    提出 CellAudit，审计智能体发现的细胞模型是否使用所声明输入

    arXiv
    2609.27234
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    CellScientist, AIDE, CellForge and others4
    AbstractCellAudit 把输入使用声明从源码追到拟合贡献，并说明高分不必等于使用了扰动。

    CellAudit 为智能体发现的细胞响应模型增加一层输入使用证伪：源码是否消费注册输入、拟合预测是否依赖它、该依赖是否改善对观测响应的预测。

    Paper analysisRead analysis
You have reached the end