cs.RONov 13, 2026

ESI: An Embodied Self-Improvement Flywheel for LLM-VLA Agents

Authors: Yundi Cai, Zihan Wang, Chenxi Han, Yi Cheng, Houde Liu, Zilei Wang

Organizations: University of Science and Technology of China · ZERITH Robotics · Tsinghua Shenzhen International Graduate School

Abstract

Independently pretrained language models and vision-language-action (VLA) policies provide complementary building blocks for embodied agents, but connecting them does not automatically produce coordinated behavior. The VLA may generate actions that diverge from the LLM's intended subtask and, upon regaining control after a correction, undo the promising state restored by the LLM. We introduce ESI (Embodied Self-Improvement), an automated flywheel that uses environmental interaction to align reasoning and action. ESI treats the modular agent as the unit of post-training, repeatedly refining the prompts that guide the LLM, the shared skill interface that expresses its intent, and the VLA parameters that realize that intent, then redeploying these components together. Our key insight is that collaboration itself can supply supervision for improving this interface. The LLM's subtask decisions provide semantic supervision for what the policy should execute, while its effective corrections and subsequent student continuations provide action-level supervision for recovery and handoff. The student also learns from its own effective execution, allowing locally useful experience to contribute even when the overall episode fails. On ten selected RoboDojo tasks, ESI achieves a mean Score of 62.03 and a mean success rate of 49.41% using an LLM-VLA agent without generating task-specific control code. On both metrics, it outperforms the published reference results of all hybrid embodied agents, including the Agent+WAM system GO-3 Nano Preview (47.27 Score and 36.60% success), as well as all compared code-based methods.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. EmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent

    Sep 1, 2026Wei Wang, Wenqiao Zhang, Yutong Lin +14Robotic ControlLarge Language Model-Based Robot Planning

  2. ELITE: Experiential Learning and Intent-Aware Transfer for Self-improving Embodied Agents

    Mar 25, 2026Bingqing Wei, Zhongyu Xia, Dingai Liu +3Lifelong Learning AgentsVLMs for Robotics

  3. AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents

    Oct 14, 2026Peidong Wang, Ying Chang, Zhiming Ma +10Self-Improving AgentsRobotics