Training-Free Action Correction for VLA Model Failures via Language Feedback
技术动态
来源：arXiv cs.RO发布时间待核实
arXiv:2608.29967v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models demonstrate strong semantic understanding yet exhibit systematic failures during deployment. The conditions under which these failures occur, and whether they can be corrected without retraining, remain poorly understood. In this paper, we take steps toward addressing this gap.