# Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs > Source: > Published: 2026-11-05 01:39:39+00:00 Reasoning vision-language-action (VLA) models pair physical control with natural-language rationales that supervisors can read to monitor embodied safety. Prior attacks on VLA reasoning corrupt the rationale itself and leave visible evidence in the text. We show that visual perturbations can instead