LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification

ArXi:2605.07315v1 Announce Type: new Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token generation by propagating continuous states, yet replacing explicit derivations with latent computation can hurt tasks that require symbolic checking.