Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Junhao Shi, Zezheng Huai, Siyin Wang, Jia Chen, Yubang Wang, Zhaoye Fei, Hechang Chen, Jingjing Gong, Xipeng Qiu, Yu-Gang Jiang
• Venue: arXiv: cs.RO
• Published: 2026-06-25
• Collected: 2026-06-26
• URL: http://arxiv.org/abs/2606.27251v1
• PDF: https://arxiv.org/pdf/2606.27251v1
• DOI: UNKNOWN

Plain-Language Brief

The paper presents OmniAct, a framework for building persistent embodied agents that can operate in unstructured environments. The framework aims to integrate various tools from both cyber and physical domains, handle physical failures, and promote autonomous recovery over extended operation. Key features of OmniAct include a multimodal semantic planner, an adaptive hierarchical memory, and an asynchronous visual preemption engine. The research demonstrates that OmniAct improves end-to-end success across various tasks and maintains low token consumption over extensive interaction.

What the Document Says

• The researchers introduce OmniAct, a framework for building persistent embodied agents in unstructured environments.
• OmniAct integrates tools from cyber (APIs, IoT) and physical domains (manipulation, navigation).
• The goal is to handle physical failures during extended operation and promote autonomous recovery.
• The framework consists of a multimodal semantic planner for skill routing, an adaptive hierarchical memory, and an asynchronous visual preemption engine.
• The research was tested across 40 real-world long-horizon tasks on two robotic platforms coordinating four IoT devices.
• OmniAct achieved consistent improvements in end-to-end success across all complexity levels.

Key Concepts Mentioned

• embodied agents
• unstructured environments
• cyber tools
• physical tools
• physical failures
• autonomous recovery
• multimodal semantic planner
• adaptive hierarchical memory
• asynchronous visual preemption engine

Claims Made by the Document

• OmniAct improves end-to-end success across all complexity levels.

Evidence Used

• Across 40 real-world long-horizon tasks on two robotic platforms, OmniAct demonstrated consistent improvements in end-to-end success.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Building persistent embodied agents in unstructured environments demands unified orchestration of heterogeneous tools spanning both cyber (APIs, IoT) and physical (manipulation, navigation) domains, coupled with autonomous recovery from physical failures that inevitably arise over extended operation. Existing systems treat these as separate problems: VLM-based planners lack a unified cyber-physical action space, agent frameworks accumulate unbounded context that degrades temporal coherence, and VLA policies execute open-loop without detecting their own failures. We argue that persistent autonomy requires not a monolithic model but a hierarchical asynchronous architecture with explicit separation of planning, memory, and verification. To this end, we present OmniAct, a framework integrating a multimodal semantic planner for skill routing across unified action spaces, an adaptive hierarchical memory with event-boundary-driven compression for sub-linear context growth, and an asynchronous visual preemption engine that closes the semantic loop during physical execution. Across 40 real-world long-horizon tasks on two robotic platforms coordinating four IoT devices, OmniAct achieves consistent improvements in end-to-end success across all complexity levels, maintains near-flat token consumption over under 100k+ accumulated interaction tokens, and elevates mid-scale open-weight models to proprietary-level performance.