AI前沿：从模型大小到“啊哈”时刻的突破
本期“TAI快报”探讨了五篇AI前沿论文的核心发现：
“Do Larger Language Models Imply Better Reasoning? A Pretraining Scaling Law for Reasoning”揭示语言模型推理能力存在U型曲线，过大模型可能损害效果，提出图搜索熵预测最佳模型大小，强调数据质量决定上限。
“Understanding Aha Moments: from External Observations to Internal Mechanisms”研究AI的“啊哈”时刻，揭示其通过拟人化反思提升推理能力，提出分离指标避免推理崩溃，但可能导致过度思考。
“DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments”创新性地在真实网络环境中训练AI研究智能体，显著提升开放域任务性能，涌现规划等认知行为。
“Agentic Knowledgeable Self-awareness”提出智能体自我觉知新范式，KnowSelf方法让AI根据情境灵活决策，打破规划过拟合，提升泛化能力。
“Align to Structure: Aligning Large Language Models with Structural…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.