Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence
Abstract: Existing embodied-agent harnesses remain largely open-loop, following fixed skills during rollout and reflecting only after an episode ends. Zetta is a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Its three timescale-separated loops provide action-frequency governance, rollout-level critic-recovery proposals, and validation-gated skill updates. With Z-Infra, Zetta reaches 90.8% success on LIBERO-Pro and 93.6% on RoboCasa, delivers an 11.1x inference speedup, and transfers learned skills zero-shot.
BibTeX
@article{zetta,
title={Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence},
author={Xin Ding and Liang Mi and Mingzhe Huang and Zixuan Wang and Chao Zhang and Zixu Hao and Fu Chen and Xiangyu Li and Yikai Zheng and Yaoyu Guo and Weijun Wang and Kun Li and Hao Wu and Yunxin Liu and Ting Cao},
journal={arXiv preprint arXiv:2608.16590},
eprint={2608.16590},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2608.16590},
year={2026}
}