Large reasoning models have recently demonstrated remarkable capabilities in solving complex tasks, where supervised fine-tuning (SFT) on long chain-of-thought data serves as a crucial foundation for eliciting and enhancing their reasoning abilities. Despite rapid progress in both improving and analyzing reasoning-oriented SFT, the field still lacks a systematic survey that consolidates its fast-growing literature.
Methodological design and analytical investigation
To fill this gap, we present a comprehensive review of recent advancements in reasoning SFT, examining the literature through the dual lenses of methodological design and analytical investigation.
Methodological improvements across the SFT pipeline
First, we review methodological improvements across the SFT pipeline and categorize them into data-centric approaches and algorithm-centric innovations.
Analytical studies along three dimensions
Second, we reorganize analytical studies along three dimensions: data characteristics, optimization dynamics, and mechanistic insights.
Research focuses and remaining bottlenecks
Finally, by synthesizing current research focuses and remaining bottlenecks, we outline promising future directions for reasoning SFT.
We hope this survey deepens the understanding of reasoning SFT and paves the way for advanced reasoning models.