Reproduce “Rethinking On-Policy Self-Distillation for Thinking Models” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Simran Kaur, Narutatsu Ri, Yinghui He, Liam Fowl, Sanjeev Arora

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.