Tag
APRiL 提出了一个针对中文社交感知能力的开放式基准，包含 2,196 个评测实例，涵盖六类社交场景和两项互补任务。对来自六个模型家族的 12 个模型的实验揭示了一致的“理解-响应”差距：高质量的场景分析能提升响应质量，而薄弱的分析反而可能降低响应质量。
The article discusses the challenge of designing AI agents that are socially aware and know when to interrupt, emphasizing long-term memory and restraint over raw intelligence, as demonstrated by the author's Alfred system.