Metraipolis › archive › dc_ec2d41d8755c

Toward the Era of Agentic Embodied Intelligence — arXiv:2611.09124

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09124
License (as archived)
CC0-1.0
Archived
2026-11-09T22:46:01.102Z
SHA-256 of the archived text
b5c998430748cad494d8d6db43371e4432b48e43943d254c6bdf9e74519c9c45
Stable URL of this page
https://metraipolis.com/documento/dc_ec2d41d8755c

How to cite

Toward the Era of Agentic Embodied Intelligence — arXiv:2611.09124 — arXiv (en), https://arxiv.org/abs/2611.09124 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec2d41d8755c (Metraipolis archive dc_ec2d41d8755c, sha256 b5c998430748cad494d8d6db43371e4432b48e43943d254c6bdf9e74519c9c45)
BibTeX
@misc{dcec2d41d8755c,
  title = {Toward the Era of Agentic Embodied Intelligence — arXiv:2611.09124},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09124},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec2d41d8755c; sha256 b5c998430748cad494d8d6db43371e4432b48e43943d254c6bdf9e74519c9c45},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09124. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Foundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure recovery. We introduce A2-MEAS, an embodied multi-agent framework built around code as a scaling interface. Learned correction codes combine corrective language, spatial evidence, execution history, and action proposals. MetaBrain provides training supervision and runtime guidance. A correction encoder and adapter absorb this knowledge into policy weights during training, while fresh codes adapt behavior with frozen weights at deployment. The action model, A2-WLA, adds motion-aware history and a latent world model to a vision-language-action policy. Surprisingly, this simple design with action pretraining and task specialization reaches 0.5755 Q-score on the 50-task BEHAVIOR 2026 public subset before online correction, 2.21x the 2025 winner's reported 0.2605 across different benchmark editions and training configurations. On all 100 BEHAVIOR 2026 public tasks, A2-MEAS achieves 0.6411 Q-score and 45.40% task success. On RoboTwin 2.0, A2-WLA achieves 93.98% average success, rising to 95.05% with the complete system. Across 12 real-robot tasks in five household settings, A2-WLA achieves 57.92% average success versus 26.67% for pi0.5. In long-horizon pour-over coffee preparation, a history-conditioned adapter raises post-failure completion at two filter-handling steps from 14% to 94% and from 8% to 82%, compared with A2-WLA retries. Our training infrastructure delivers 427.1 samples per second, 4.03x the throughput of a pi0.5 reference implementation on matched hardware. We will release the system, models, training scripts, and infrastructure to support efficient embodied learning.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.09124 — 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 2026-11-09T22:38:02.186Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).