Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations

ArXi:2509.18953v2 Announce Type: replace-cross Vision-Language-Action (VLA) models have emerged as promising solutions for robotic manipulation, yet their robustness to real-world physical variations remains critically underexplored. To bridge this gap, we propose Eva-VLA, the first unified framework to systematically evaluate the robustness of VLA models by formulating uncontrollable physical variations as continuous optimization problems.