Paper page - Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

Source: https://huggingface.co/papers/2608.16590 Published on Aug 17

#3 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Zetta is a closed-loop embodied harness that evolves runtime critics and recovery skills online to govern physical execution at action frequency, achieving high success on robot benchmarks with faster inference and scaling self-exploration.

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, aclosed-loop embodied harnessthat evolvescode-based runtime criticsandrecovery skillsonline while keeping the base policy frozen. Through three timescale-separated loops, Zetta providesaction-frequency governance,rollout-level critic-recoveryproposal, andvalidation-gated skill updates. Together withZ-Infra, a rollout infrastructure decoupling agent logic from heterogeneous execution resources, Zetta achieves state-of-the-art success onLIBERO-ProandRoboCasaunder our current rollout budget, reaching 90.8% and 93.6%, with an 11.1x inference speedup; success continues to scale withself-explorationexperience; 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.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2608\.16590

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.16590 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.16590 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.16590 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.