SFT and RL cannot be decoupled in LLM post-training because each step increases the loss or lowers the reward of the prior step under KL and PL analyses.
The synergy dilemma of long-cot sft and rl: Investigating post-training techniques for reasoning vlms
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
citing papers explorer
-
On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training
SFT and RL cannot be decoupled in LLM post-training because each step increases the loss or lowers the reward of the prior step under KL and PL analyses.
-
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.