# Zetta ζ：一种用于自演化物理智能的高效闭环具身框架

> 原文链接：https://robotics.hellobike.com/papers/2026-08-17-2608-16590
> 频道：papers | 更新日期：2026-08-17 | 标签：arxiv, cs.RO
> 核心摘要：Zetta通过三时间尺度闭环在线演化运行时评判器与恢复技能，在LIBERO-Pro和RoboCasa上验证自演化物理智能。

# Zetta ζ：一种用于自演化物理智能的高效闭环具身框架

::: v-pre
> 原文链接：[Zetta $ζ$: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence](https://arxiv.org/abs/2608.16590)（arXiv 2608.16590 · 发布日期：2026-08-17）

**Zetta $ζ$: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence**

Zetta通过三时间尺度闭环在线演化运行时评判器与恢复技能，在LIBERO-Pro和RoboCasa上验证自演化物理智能。

## 核心要点

- 现有具身框架多为开环，执行中依赖固定技能，事后反思难以及时治理物理交互。
- Zetta冻结基础策略，在线演化代码化运行时评判器与恢复技能，实现闭环执行治理。
- 三类分离时间尺度循环分别负责动作频率治理、rollout级提案和验证门控技能更新。
- 在LIBERO-Pro和RoboCasa当前rollout预算下达到90.8%和93.6%成功率，并有11.1倍推理加速。

**验证范围与局限**：验证范围为LIBERO-Pro和RoboCasa当前rollout预算；摘要未说明真机验证或机器人数量。

## 英文摘要 (Abstract)

Embodied agents are increasingly used to close the gap left by end-to-end policy models. Yet the agentic path has not realized closed-loop learning in physical execution: existing harnesses remain largely open-loop, following fixed skills during rollout and reflecting only after an episode completes. Such post-hoc reflection cannot govern execution as it unfolds, because physical interaction requires decisions to track rapidly changing robot-environment states at a frequency beyond today's large agentic models. We present Zetta, a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Through three timescale-separated loops, Zetta provides action-frequency governance, rollout-level critic-recovery proposal, and validation-gated skill updates. Together with Z-Infra, a rollout infrastructure decoupling agent logic from heterogeneous execution resources, Zetta achieves state-of-the-art success on LIBERO-Pro and RoboCasa under our current rollout budget, reaching 90.8% and 93.6%, with an 11.1x inference speedup; success continues to scale with self-exploration experience; learned skills transfer zero-shot, and clear robotic "Aha Moments" emerge. These results show that closed-loop harness self-evolution opens a scaling path for reliable physical intelligence.

作者：Xin Ding, Liang Mi, Mingzhe Huang, Zixuan Wang, Chao Zhang, Zixu Hao, Fu Chen, Xiangyu Li, Yikai Zheng, Guo, Yaoyu
:::

## 原始参考来源 (Sources)

- [arXiv 2608.16590：Zetta $ζ$: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence](https://arxiv.org/abs/2608.16590)