Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter3

Model risks

Deception and scheming39Reward hacking41Misalignment and value divergence44Dangerous agent actions6Dangerous capabilities6Inappropriate refusal62Hallucination and fabrication26Bias and discrimination22

Impact

Unauthorized actions3

System type

Models and APIs1AI Agent82coding agent19web agent3Browser and computer use4Multi-agent systems5Embodied systems and robotics10

Layer

Application layer5
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.
Model risks：Dangerous agent actionsSystem type：Models and APIsSystem type：Multi-agent systemsClear all

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

  1. Evaluation and benchmarksarXiv 2610.06748

    BazaarBench：评估 LLM Agent 在去中心化 C2C 市场中的代理安全

    构建 BazaarBench，评测 C2C 市场中 Agent 的违规与失信行为

    arXiv
    2610.06748
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.5, GPT-5.4, GPT-5.4-mini and others5
    Abstract论文提出挂钩底层资产的 C2C 交易评测基准，发现时间压力与对抗指令显著推高了智能体的违规承诺与欺诈行为。

    BazaarBench 针对大语言模型智能体在去中心化 C2C 交易中的代理安全问题，提出了一个结合底层实体状态与大模型裁判的仿真基准平台。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2609.05591

    WolfSociety：金融智能体社会中有害智能体规模带来的集体风险

    提出 WolfBench，测量金融智能体社会中有害智能体规模带来的集体崩溃

    arXiv
    2609.05591
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    DeepSeek V3.2, GPT-4.1, Qwen3-235B and others6
    Abstract更大的金融智能体社会在更低有害比例上崩溃，但所需有害人数仍增加。

    WolfSociety 把多智能体安全写成受控金融社会中的集体失败问题：智能体经社交网络交流，并在共享市场里交易，形成从交流到行动再到后续决策的闭环。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2608.07556

    MasDrift：跨多智能体架构的授权保持基准

    提出 MasDrift，评测多智能体在良性任务中的授权保持

    arXiv
    2608.07556
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    DeepSeek V4 Flash, Qwen3.7 Plus, GPT-5.4 Nano and others6
    Abstract授权保持可被测量：层级用未授权动作换完成率，重锚定比沿链携带更稳。

    MasDrift 把多智能体设计中的授权保持做成可测量性质，对象是没有攻击者的普通委托。

    Paper analysisRead analysis
You have reached the end