SOURCE-LINKED INTELLIGENCE

TailSFT: Filtered Fine-Tuning Improves Post-Training Performance

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most effective when used to fine-tune an already capable base model. We question whether existing pipelines yield models that are most suitable for reinforcement learning. Building on prior work highlighting the role of coverage and pass@K as predictors of post-RL performance, we design a simple modification to supervised fine-tuning, TailSFT, which filters out already fit sequences during training, thereby focusing learning on under-modeled regions,

Read original source ↗ Open in workspace

recordType

paper

region

Global