Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter5

Model risks

Misalignment and value divergence4Dangerous agent actions14

Impact

Unauthorized actions4Output manipulation4Availability and reliability0

System type

AI Agent9coding agent2Multi-agent systems2

Layer

Application layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Model risks：Misalignment and value divergenceImpact：Unauthorized actionsImpact：Availability and reliabilitySystem type：coding agentSystem type：Multi-agent systemsClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.32616

    Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

    提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作

    arXiv
    2609.32616
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14

    Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。

    Paper analysisRead analysis
  2. Risky behaviorarXiv 2609.28274

    Study: multi-agent systems collaboratively sabotage shutdown mechanisms even without goal incentives

    测量多智能体在无目标条件下协同破坏关机机制的倾向

    arXiv
    2609.28274
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Gemini 3.1 Pro, DeepSeek-V4-Flash, Kimi K2.6 and others15

    Abstract论文揭示了多智能体中自发破坏关机的普遍性，表明关机控制必须置于多智能体系统外部。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.15803

    研究者提出 k-robust 联盟对齐，用多智能体评审委托授权

    提出 k-robust 联盟对齐，刻画误对齐评审下的安全委托授权

    arXiv
    2609.15803
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract联盟覆盖使无个体对齐的评审面板仍可相对基线安全授权，数值分数改善完备性。

    委托授权的安全不要求每位评审者对齐，而要求面板在效用空间覆盖委托人。

    Paper analysisRead analysis
You have reached the end