arXiv cs.CV
· Papers
CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
arXiv:2512.10342v3 Announce Type: replace Abstract: Vision Language Models (VLMs) have shown promising planning capabilities, yet their success remains confined to the text domain, leaving visual decision-making relatively underexplored. Addressing this gap, we introduce Corrective Sequence Planning (CoSPlan) benchmark