arXiv cs.AIPaper
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?
VLA models are hitting the wall where simple task completion is no longer the constraint; reasoning under spatial ambiguity and long-horizon planning is. This benchmark matters because it actually measures what matters in deployed robotics. If your agent framework is trained on toy tasks, RoboSPA will show you exactly where it fails at scale. Worth using if you're shipping embodied AI.