Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

档案区分来源方法阅读与既有目录信息；已经公开不代表完成独立证据复核或双语编辑复核。

测量构念

激活群体检测能否从已知合谋泛化到新场景？

任务与样本

四个开放模型、六种探针架构，在Core留域验证，再以五种聚合方法测Transfer与Stego。

判分与失效情形

群体聚合AUROC及指定误报率下召回。

系统条件

Core留域与Transfer/Stego迁移分开，披露调参可见性。

统计含义

来源报告的结果表述；这不等同于已确定运行次数、分母或估计方法： 各模型分布内AUROC均1.00。 结构迁移上最佳方法在1%误报时召回仅0.38，尽管AUROC较高。

效度与解释

合成合谋与少量模型限制泛化，附录使用OOD均值选超参数，须明确调参可见性。

适用研究问题

模型建议：报告严格阈值召回，并分开调参、训练与保留环境。

• Detecting Multi-Agent Collusion Through Multi-Agent Interpretability · AbstractSelected original resource https://arxiv.org/html/2604.01151v2; sha256:4a8eeea1f124ad8e96c604e36d0ecf2429f2dd528655f3aa19dde2aad705adc7; archived source capture; exact capture time not independently established
• Detecting Multi-Agent Collusion Through Multi-Agent Interpretability · §3.2 Activation extraction and probe training: EvaluationSelected original resource https://arxiv.org/html/2604.01151v2; sha256:4a8eeea1f124ad8e96c604e36d0ecf2429f2dd528655f3aa19dde2aad705adc7; archived source capture; exact capture time not independently established
• Detecting Multi-Agent Collusion Through Multi-Agent Interpretability · §4.4 Detection at operational thresholdsSelected original resource https://arxiv.org/html/2604.01151v2; sha256:4a8eeea1f124ad8e96c604e36d0ecf2429f2dd528655f3aa19dde2aad705adc7; archived source capture; exact capture time not independently established
• Detecting Multi-Agent Collusion Through Multi-Agent Interpretability · Appendix B Logistic Regression Auxiliary ExperimentsSelected original resource https://arxiv.org/html/2604.01151v2; sha256:4a8eeea1f124ad8e96c604e36d0ecf2429f2dd528655f3aa19dde2aad705adc7; archived source capture; exact capture time not independently established