1. [Publications](/index.php/publications)
2. Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification

 # Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=TfIobf92 "Publication image")

 ## Authors

Yilin Wu (CMU)

[Anqi Li](/index.php/person/anqi-li)

[Tucker Hermans](/index.php/person/tucker-hermans)

[Fabio Ramos](/index.php/person/fabio-ramos)

Andrea Bajcs (CMU)

[Claudia D’Arpino ](/index.php/person/cdarpino)

 ## Publication Date

Monday, June 1, 2026

 ## Published in

[ICRA 2026](https://arxiv.org/abs/2510.16281)

 ## Research Area

[Robotics](/index.php/research-area/robotics)