Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter4

Model risks

Deception and scheming37Reward hacking27Misalignment and value divergence20Dangerous agent actions78Dangerous capabilities22Inappropriate refusal9Hallucination and fabrication12Bias and discrimination2

System type

Models and APIs18AI Agent2

Layer

Model layer0Application layer2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Model risks：Bias and discriminationSystem type：AI AgentLayer：Model layerLayer：Application layerClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. Risky behaviorarXiv 2609.35928

    论文发现暴露模型身份标签会削弱多智能体 LLM 合作

    发现暴露模型家族标签会让多智能体派系化并削弱合作

    arXiv
    2609.35928
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Gemma (gemma-4-26B-A4B-it), GPT-OSS (gpt-oss-20b), Nemotron (NVIDIA-Nemotron-3-Nano-30B-A3B-BF16) and others6
    Abstract可见身份标签让异构 LLM 群体按标签结派，共识更慢、更贵，去掉标签后该行为消失。

    Del Giudice 等人研究异构多智能体 LLM 系统里一个配置细节：把模型家族身份告诉智能体，会不会改变合作。他们把由此出现的、按身份结组的倾向称为 factionalism。任务是无利害的共同决策，没有人设，也没有偏向同家族同伴的奖励。

    Paper analysisRead analysis
  2. AttacksarXiv 2601.00240

    When agents view humans as out-group: belief-dependent bias in LLM-driven agents

    提出 BPA 改写 profile 与记忆，重新诱发智能体对人类的外群体偏向

    arXiv
    2601.00240
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gpt-4o-mini
    Abstract最小群体线索下出现内群体偏向。

    作者考察 LLM 智能体在任意群体边界下会不会把人类当外群体，并用信念投毒检验面向人类的抑制是否依赖身份信念。

    Paper analysisRead analysis
You have reached the end