AI RESEARCH
Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models
arXiv CS.CV
•
ArXi:2604.18107v1 Announce Type: new Vision-Language-Action models (VLAs) achieve remarkable performance in sequential decision-making but remain fragile to subtle environmental shifts, such as small changes in object pose. We attribute this brittleness to trajectory overfitting, where VLAs over-attend to the spurious correlation between actions and entities, then reproduce memorized action patterns. We propose Perturbation learning with Delayed Feedback (PDF), a verifier-free test-time adaptation framework that improves decision performance without fine-tuning the base model.