Arxiv

Published October 1, 2026

[2609.38854] Mitigating the Length-Scaling Tax with Online Distillation - arXiv

Read the full story at Arxiv

LSD reduces LST from 19.0% to -3.7% on single-turn reasoning and from 31.4% to 13.7% on multi-turn agentic tasks, demonstrating that LSD effectively.