SOURCE-LINKED INTELLIGENCE

Reflection Steering: Disentangling Reflection from Reasoning in Activation Space for Token-Efficient Inference

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Large reasoning models often produce reasoning traces with verification, revision, and backtracking. When reflection merely re-checks established results, it wastes reasoning tokens and increases latency. Most existing reflection steering methods add a label-derived mean-difference direction across preset layers, but its entanglement with reasoning and length signals destabilizes the accuracy-efficiency trade-off. In this paper, we propose Reflection Steering, a training-free framework for controlling reflection-associated computation within LLMs by disentangling reflection-related activations

Read original source ↗ Open in workspace

recordType

paper

region

Global