SOURCE-LINKED INTELLIGENCE

The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of thought runs about twice as long as the model's own answer probability takes to settle, and how much of that excess is removable varies from problem to problem, so a global length penalty cannot take it out. We take it out by internalizing a causal interpretability finding into the weights. The mechanism is a halt vector: a difference-of-means direction at layer 18 of this model whose steering strength controls how long it thinks, while a replicated value axis does nothing. Installing that inter

Read original source ↗ Open in workspace

recordType

paper

region

Global