Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
arXiv:2610.12933v1 Announce Type: new Abstract: Large language models have achieved remarkable advances in complex reasoning. However, scaling reasoning post-training with ever-larger corpora can substantially increase training cost without proportional performance gains. In this study, we therefor…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-12 04:00 · arXiv cs.AI
Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training