00:00:30 AI的“错题本”：高手是如何炼成的？

00:03:50 AI的自我修养：如何像高手一样不断精进？ 

00:07:10 AI当学徒：如何让机器自己学会“青出于蓝”？ 

00:11:25 AI的“装傻”艺术：我们还能相信它吗？ 

本期介绍的四篇论文：

[CL] WarriorMath: Enhancing the Mathematical Ability of Large Language Models with a Defect-aware Framework  

[Microsoft & Peking University]  

https://arxiv.org/abs/2508.01245  

---

[LG] Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-Tuning  

[Meta Reality Labs]  

https://arxiv.org/abs/2508.01543  

---

[LG] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search  

[University of Washington & DeepReinforce Team]  

https://arxiv.org/abs/2508.02091  

---

[LG] LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring  

[University College London]  

https://arxiv.org/abs/2508.00943