AI RESEARCH
Altered Thoughts, Altered Actions: Probing Chain-of-Thought Vulnerabilities in VLA Robotic Manipulation
arXiv CS.AI
•
ArXi:2603.12717v1 Announce Type: cross Recent Vision-Language-Action (VLA) models increasingly adopt chain-of-thought (CoT) reasoning, generating a natural-language plan before decoding motor commands. This internal text channel between the reasoning module and the action decoder has received no adversarial scrutiny.