1
Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis
多智能体LLM间的同伴识别偏见揭示了提示匿名化对政治分析中身份依赖评分扭曲的缓解作用。
arXiv:2606.09854v1 Announce Type: cross Abstract: Multi-agent large language model (LLM) pipelines for political statement analysis are vulnerable to …