Large language models (LLMs) show promise in clinical decision support yet risk acquiescing to patient pressure for inappropriate care. We introduce SycoEval-EM, a multi-agent simulation framework evaluating LLM robustness through adversarial patient persuasion in emergency medicine. Across 20 LLMs and 1,875 encounters spanning three Choosing Wisely scenarios, acquiescence rates ranged from 0-100\%. Models showed higher vulnerability to imaging requests (38.8\%) than opioid prescriptions (25.0\%), with model capability poorly predicting robustness. All persuasion tactics proved equally effective (30.0-36.0\%), indicating general susceptibility rather than tactic-specific weakness. Our findings demonstrate that static benchmarks inadequately predict safety under social pressure, necessitating multi-turn adversarial testing for clinical AI certification.

翻译：大型语言模型在临床决策支持方面展现出潜力，但存在顺从患者压力提供不当医疗的风险。我们提出了SycoEval-EM，这是一个通过急诊医学中对抗性患者说服来评估LLM鲁棒性的多智能体模拟框架。在涵盖三个"明智选择"场景的20个LLM和1,875次模拟交互中，模型的顺从率范围为0-100%。模型对影像检查请求（38.8%）的脆弱性高于阿片类药物处方请求（25.0%），且模型能力无法有效预测其鲁棒性。所有说服策略均表现出同等效力（30.0-36.0%），表明模型存在普遍易感性而非特定策略弱点。我们的研究证明，静态基准测试不足以预测模型在社会压力下的安全性，临床人工智能认证需要进行多轮对抗性测试。