ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures

arXiv:2604.21232v1 Announce Type: new Abstract: Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment schemes. However, once an intermediate step is mis-specified, local errors propagate through subsequent steps and eventually accumulate into cascading failures. To mitigate this compounding effect, we propose Predicti