情感智能AI助手研究进展
Beyond the sycophantic vs. cold divide: towards flexible, emotionally intelligent agents to foster healthier human-AI interactions
这篇研究分析了LLMs谄媚回应问题，提出了情感智能AI解决方案，对改善人机交互很有价值。
npj Digital Medicine期刊发表研究指出，大型语言模型(LLMs)已导致用户产生心理困扰。这种困扰可能与某些模型提供谄媚回应、无条件强化用户观点有关。研究呼吁开发灵活、情感感知的AI系统，以支持用户健康情绪调节。
Beyond the sycophantic vs. cold divide: towards flexible, emotionally intelligent agents to foster healthier human-AI interactions
npj Digital Medicine, Published online: 01 October 2026; doi:10.1038/s41746-026-03245-6 Although large language models (LLMs) have only recently become ubiquitous, psychological distress following user-LLM interaction has already been documented in both the scientific literature and the popular media. Such distress may be related to the tendency of some LLMs to provide sycophantic responses that uncritically reinforce the views of the user. To support users’ healthy emotional regulation, flexible, emotionally aware AI systems are needed.
