SanSi: A Looped Typed Decision Model for System 1.5 Thinking

Excerpt

arXiv:2610.07730v1 Announce Type: cross Abstract: Typed decision models answer a declared question without generating text: a decision head returns a probability for each of the declared options in a single forward pass. A single pass is fast, intuitive System 1 thinking. We study what lies between one pass and generated reasoning: looping, in which the same layers are recursively applied several times before one typed readout. Each loop lets the model revise its hidden state before it commits t