Latent reasoning

Latent reasoning is the idea that a language model can carry part of its reasoning process inside continuous hidden-state vectors instead of only through explicit words. In an LLM, the prompt is projected into high-dimensional representations, transformed through model layers, and decoded into text. Research on latent reasoning treats a model final hidden state as a reusable representation of an intermediate thought, allowing reasoning to continue directly in latent space.

“Instead of forcing every reasoning step into written text, an experiment may feed a hidden-state vector back into the model and let the next step happen in latent space.”