arXiv cs.CL
· Papers
SLPO: Scaling Latent Reasoning via a Surrogate Policy
arXiv:2607.19691v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in explicit Chain-of-Thought reasoners. Yet this scaling path remains computationally costly, since every intermediate step must be decoded as a language token