cs.RONov 9, 2026

How Much of Your VLA Is kNN

Authors: Denis Grachev, Damien LaRocque, Omar Moured

Organizations: Sereact GmbH, Stuttgart, Germany · Karlsruher Institut für Technologie, Karlsruhe, Germany

Abstract

Vision-language-action (VLA) models now exceed 95% success on the LIBERO simulation benchmark, yet it remains unclear how much of this performance requires generalization beyond the training demonstrations. In this work, we show that retrieving nearby demonstrations and reusing their action chunks achieves a success rate of 91.7 % on LIBERO without policy training. Under LIBERO-Plus perturbations, retrieval shows the smallest drop of all evaluated policies. Across nine publicly available VLAs, fine-tuning mostly makes the vision-language backbone a better retrieval key, and the actions of the VLAs remain close to the demonstrations. In addition, we introduce Local Action Consistency (LAC), an offline metric that measures whether nearby observations in representation space are also associated with similar future actions. We show that LAC tracks the success rate of retrieval and can guide the training of a retrieval key. Our evaluation and source code are available at https://github.com/sereact/lerobot_knn.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. When Does Retrieval Help? A Study of In-Context Adaptation in Vision-Language-Action Models

    Oct 4, 2026Zixuan Liu, Joris Köster, Zizhan Zheng +1Vision-Language-Action ModelsRetrieval-Augmented ICL

  2. LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models

    May 11, 2026Boyang Shen, Kaixiang Yang, Hao Wang +4Efficient VLM InferenceEfficient VLA Model Inference