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

• URL: http://arxiv.org/abs/2608.16590v1
• Date: Mon, 17 Aug 2026 13:49:43 GMT
• Title: Zetta $ζ$: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence
• Abstract summary: Embodied agents are increasingly used to close the gap left by end-to-end policy models.<n>Existing harnesses remain largely open-loop, following fixed skills during rollout and reflecting only after an episode completes.<n>We present Zetta, a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online.
• Score: 35.97081339163319
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents [50.85250898062218]
  Large language model (LLM) agents for long-horizon interactive tasks typically follow a ReAct-style protocol.<n>A natural alternative is to let the agent emit variable-length action chunks.<n>But naively training such policies with standard reinforcement learning fails.
  arXiv  Detail & Related papers  (2026-09-02T03:17:11Z)
• Revisiting Open-Loop Execution in Robotics: Toward Reactive, Higher-Performing Policies [21.50347781480984]
  Action chunking has emerged as a key enabler of recent progress in imitation learning for robotic manipulation.<n> executing long open-loop prefixes reduces reactivity, limiting policies' ability to correct for errors.<n>We argue that long open-loop execution primarily helps short-context policies imitate "non-Markovian demonstrations"
  arXiv  Detail & Related papers  (2026-08-16T21:49:07Z)
• EvoHIL: Self-Evolving Reward and Flow-Matched Policy Optimization for Robust Human-in-the-Loop Reinforcement Learning [14.891400906901433]
  EvoHIL is a unified framework that adapts the reward model, action generator, and visual do main within a staged human-in-the-loop learning process.<n>It improves task success, agreement with human-confirmation labels, motion smoothness, and completion time relative to human-in-the-loop and imitation baselines.
  arXiv  Detail & Related papers  (2026-08-04T16:12:05Z)
• Playful Agentic Robot Learning [108.08954330298549]
  We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive.<n>During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library.
  arXiv  Detail & Related papers  (2026-06-17T17:55:23Z)
• Harnessing LLM Agents with Skill Programs [58.356514745548026]
  We introduce HASP, a new framework that upgrades skills into executable Program Functions (PFs)<n>PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context.<n> HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks.
  arXiv  Detail & Related papers  (2026-05-18T01:35:11Z)
• Continual Harness: Online Adaptation for Self-Improving Foundation Agents [21.599574507129365]
  Continual Harness is a reset-free self-improving harness for embodied agents.<n>It drives sustained in-game milestone progress on Pokemon Red without resetting the environment between training iterations.
  arXiv  Detail & Related papers  (2026-05-11T05:21:33Z)
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses [57.20181537213498]
  Agentic Harness Engineering (AHE) is a closed loop that automates harness engineering.<n>AHE addresses challenges through three matched observability pillars.<n>Ten AHE lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI.<n>On SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains.
  arXiv  Detail & Related papers  (2026-04-28T16:55:02Z)
• RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics [25.944338247511215]
  VLM-based planners treat each step as an observation-to-action mapping, forcing them to reinfer scene geometry from raw pixels at every decision point.<n>We propose SStream-Temporal Fusion Tokens (TF-Tokens), which bind visual evidence to 3D geometric attributes for persistent object grounding.<n>This design enables the planner to trace causal chains and preserve object permanence under occlusion without additional training or fine-tuning.
  arXiv  Detail & Related papers  (2026-03-13T12:34:26Z)
• On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral [59.14787085809595]
  We identify Lazy Likelihood Displacement (LLD) as the core mechanism driving this failure.<n>LLD emerges early and triggers a self-reinforcing LLD Death Spiral, where declining likelihood leads to low-confidence responses.<n>We propose a lightweight likelihood-preserving regularization LLDS for GRPO that activates only when a trajectory's likelihood decreases.
  arXiv  Detail & Related papers  (2025-12-03T19:41:15Z)
• RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction [23.89121398540929]
  We introduce RaC, a new phase of training on human-in-the-loop rollouts after imitation learning pre-training.<n>In RaC, we fine-tune a robotic policy on human intervention trajectories that illustrate recovery and correction behaviors.<n>We show that RaC outperforms the prior state-of-the-art using 10$times$ less data collection time and samples.
  arXiv  Detail & Related papers  (2025-09-09T17:41:29Z)
• Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward [85.84943447589511]
  This paper introduces AC3 (Actor-Critic for Continuous Chunks), a novel RL framework that learns to generate high-dimensional, continuous action sequences.<n>To make this learning process stable and data-efficient, AC3 incorporates targeted stabilization mechanisms for both the actor and the critic.
  arXiv  Detail & Related papers  (2025-08-15T01:27:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.