Skip to main content
Search

# ERR-Env

1 related articles

Subscribe to updates
  1. arXiv

    A 2B embodied VLM learns to replan after its own mistakes, lifting strict success 10.25 points over its supervised start

    Embodied vision-language models that make an execution error often need to replan from the damaged scene state to keep going. ERR-Env, built on RoboTwin 2.0, provides an executable, verifiable interaction environment whose task-specific checkers judge progress, completion, execution errors and visibility; ERR-Bench built on it holds 1,503 held-out snapshots spanning nominal, intermediate and error states. ERR-VLM, initialized from Qwen3-VL-2B-Thinking and trained online with AGT-GSPO, raises Strict Success Rate for error-free completion by 10.25 percentage points and Recovery Rate by 22.95 percentage points over its supervised initialization.

You’re all caught up