Firehose

22 JUL 2026 · Paper

SLPO: Scaling Latent Reasoning via a Surrogate Policy

This paper introduces a new method, Surrogate Latent Policy Optimization (SLPO), to improve the performance of autoregressive latent reasoners in reinforcement learning by combining outcome-reward RL with latent reasoning. Practitioners might care because SLPO can help scale the performance of these models at test time, which is currently a major challenge.

reinforcement learning latent reasoning surrogate policy outcome-reward RL autoregressive models

Browse by tag

SLPO: Scaling Latent Reasoning via a Surrogate Policy