Skip to main content
Search

# Agentic-Teacher

1 related articles

Subscribe to updates
  1. arXiv

    An agentic teacher patches VLA failures: simulation success rises to 87.8%, 90.6% and 30.0%

    Pretrained vision-language-action (VLA) models fail when environmental noise or accumulated control error push them into states outside their training distribution, and DAgger-style correction needs repeated human monitoring and demonstration. Agentic-Teacher has coding agents analyze failed rollouts, localize causal frames, cluster failures by mode, and write closed-loop code policies that finish the remaining task from the failure state, then turns those successes into learnable demonstrations. In simulation, average success rises from 79.4% to 87.8% on LIBERO-10, from 80.4% to 90.6% on MetaWorld-10, and from 0% to 30.0% across three RoboCasa tasks.

You’re all caught up