Skip to content
Sagan

Paper

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

Unreadunread

AI summary

arXiv:2606. 25354v1 Announce Type: new Abstract: Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains single-threaded, while sentence- or solution-level search can be computationally expensive and hard to train end-to-end.