Back to papers
October 23, 2026cs.CLcs.AIcs.LG

On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models

Leon Sick, Lukas Hoyer, Yannick Strümpler, Christian Reisswig, Timo Ropinski, Federico Tombari
Read on arXivDownload PDF
HF Upvotes

4

Categories

cs.CL, cs.AI, cs.LG