Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models
Tuan Duong Trinh, Naveed Akhtar, Basim Azam
Does adding a reasoning step make a Vision-Language-Action (VLA) model more robust to perturbation? Intuitively, a policy that reasons before acting should absorb a perturbed input…
cs.RO2026
Altered Thoughts, Altered Actions: Probing Chain-of-Thought Vulnerabilities in VLA Robotic Manipulation
Tuan Duong Trinh, Naveed Akhtar, Basim Azam
Recent Vision-Language-Action (VLA) models increasingly adopt chain-of-thought (CoT) reasoning, generating a natural-language plan before decoding motor commands. This internal tex…