Metraipolis › archive › dc_2e302bb2ec06

ETA: A New Agentic Paradigm for Embodied Tasks — arXiv:2608.03924

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03924
License (as archived): CC0-1.0
Archived: 2026-10-31T13:08:25.749Z
SHA-256 of the archived text: c70cf3b38eef163f6260d4e23a04c1fe2eefb6afb1d2eaf3412f378771e1c162
Stable URL of this page: https://metraipolis.com/documento/dc_2e302bb2ec06

How to cite

ETA: A New Agentic Paradigm for Embodied Tasks — arXiv:2608.03924 — arXiv (en), https://arxiv.org/abs/2608.03924 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e302bb2ec06 (Metraipolis archive dc_2e302bb2ec06, sha256 c70cf3b38eef163f6260d4e23a04c1fe2eefb6afb1d2eaf3412f378771e1c162)

BibTeX

@misc{dc2e302bb2ec06,
  title = {ETA: A New Agentic Paradigm for Embodied Tasks — arXiv:2608.03924},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03924},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e302bb2ec06; sha256 c70cf3b38eef163f6260d4e23a04c1fe2eefb6afb1d2eaf3412f378771e1c162},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03924. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When will robots have their ChatGPT moment? Such a breakthrough requires a general-purpose robot that can handle unfamiliar tasks in unfamiliar environments, remain controllable over long interactions, and learn from experience. Today's embodied systems largely follow an end-to-end observation-to-action path. Despite rapid progress, they remain far from this goal: their generalization depends heavily on the coverage of robot training data, while long task execution remains difficult to control and inspect. To realize this goal, we introduce the Embodied Task Agent (ETA), a new paradigm for extending digital agents into the physical world, and release OpenETA as its open-source implementation. ETA centers the robot around a Planner that chooses one Tool call at a time, an Interface that controls execution, and a World that returns the result and a fresh observation. This loop allows the agent to verify outcomes, adapt its plan, and turn successful and failed interactions into reusable experience. OpenETA provides replaceable Planners, composable Tools and Skills, auditable memory, replayable trajectories, and common interfaces for simulation and real robots. For Codex, OpenETA can operate as a lightweight plugin that exposes only observe, mark_point, and move_to.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.03924 — 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 2026-10-31T12:55:56.568Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).