【第182期】庆祝更新半年文中有彩蛋 || Long CoT Reasoning in LLMs

Seventy3 · Mar 31, 2025 · 15m

Seventy3: 用NotebookLM将论文生成播客，让大家跟着AI一起进步。

今天的主题是：

Demystifying Long Chain-of-Thought Reasoning in LLMs

Summary

This paper investigates how large language models (LLMs) achieve long chain-of-thought (CoT) reasoning, which involves extended, step-by-step thought processes for complex tasks. The authors explore the roles of supervised fine-tuning (SFT) and reinforcement learning (RL) in enabling this capability. Key findings highlight that while SFT on long CoT data improves performance and facilitates better RL, carefully designed reward functions are crucial for stable CoT length and enhanced…