Metraipolis › archive › dc_744aafa5935a
Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs — arXiv:2608.22657
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22657
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:44:55.696Z
- SHA-256 of the archived text
e9416761d4eb8948ec39f62057ed7848a9e8f4f2dbc9f98580bb24a012bbe0a8- Stable URL of this page
https://metraipolis.com/documento/dc_744aafa5935a
How to cite
Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs — arXiv:2608.22657 — arXiv (en), https://arxiv.org/abs/2608.22657 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_744aafa5935a (Metraipolis archive dc_744aafa5935a, sha256 e9416761d4eb8948ec39f62057ed7848a9e8f4f2dbc9f98580bb24a012bbe0a8)
BibTeX
@misc{dc744aafa5935a,
title = {Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs — arXiv:2608.22657},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22657},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_744aafa5935a; sha256 e9416761d4eb8948ec39f62057ed7848a9e8f4f2dbc9f98580bb24a012bbe0a8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22657. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic AI frameworks interpret open-ended task goals and decompose them into multi-step plans. Richer information about embodiment-specific capabilities, physical preconditions, and cross-robot coordination improves grounding, but does not eliminate infeasible, mistimed, or unsafe physical actions. Physical robot crews therefore require an explicit architectural interface between semantic planning and execution, where every planned action is verified against robot capabilities, system state, and workflow constraints before actuation. This paper introduces Physical Agentic AI, a framework for skill-grounded robot agent orchestration, in which each robot exposes a typed library of executable skills while a foundation model planner decomposes a task into phases and assigns each phase to a robot-skill pair. A Robot Orchestration layer exposes the skill library, robot state, named locations, and workflow contracts to a non-actuating Mission Planner, while a deterministic Robot Orchestrator validates and authorizes one skill at a time. We evaluate on a drone-UGV search-and-dispatch mission, where every mission in every condition is executed live in Gazebo, and on a humanoid-quadruped transportation task using hardware-equivalent skill interfaces plus two physical trials on a Unitree G1 and Go2. Varying planner knowledge and runtime enforcement independently, we find that retrieval raises skill grounding from 51% to 96% yet leaves informed planners dispatching 23-29% of faulted steps. Per-dispatch enforcement reduces false dispatch to 0% with no false blocks, and a held-plan ablation confirms that the gate, not plan variation, is responsible. Live execution makes the difference physical: without enforcement all eight injected faults crossed the orchestration boundary and six produced robot motion; with enforcement all eight were refused before motion. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2608.22657 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T07:37:52.890Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).