cs.RONov 4, 2026

Can Astra Solve RoboMME without Breaking the Bank?

Authors: Bingao Chen, Haoquan Fang, C. Karen Liu

Organizations: Stanford University

Abstract

Robotic manipulation often requires remembering information that is no longer visible, such as an object's location before occlusion or the order of a demonstrated action sequence. A large vision-language planner can read this history, but calling it before every action chunk is slow and costly. We present a three-tier system for the RoboMME benchmark. GPT-6 Astra (System 2) selects a grounded subtask from stored visual history, a π0.5π_{0.5} vision-language-action policy (System 1) executes it, and a fine-tuned Qwen3-VL-4B monitor (System 1.5) checks after each action chunk whether the subtask is finished. The instruction is kept until the monitor reports completion or a task-specific event occurs, while the policy keeps acting on new observations. On RoboMME, the system succeeds in 79.13% of episodes with an average of 3.63 Astra calls and 80.84 seconds per episode. This is 34.62 points above the best published non-oracle baseline and 4.95 points below GroundSG+Oracle, which gives the low-level policy ground-truth subgoals.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond

    Sep 21, 2026Wenbo Zhang, Kaixuan Wang, Yutao Ouyang +9Language-Conditioned Robot ManipulationGeneralization in Robotic Manipulation

  2. Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens

    Oct 1, 2026Ruiyang Si, Jianxin Bi, Shunyu Yang +12Vision-Language-Action ModelsTool-Augmented Language Model Agents