Metraipolis › archive › dc_1bd3bb42cada

AR-WAM: A Visual-Conditioned Agent-Ready World Action Model for Robotic Manipulation — arXiv:2609.23578

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23578
License (as archived)
CC0-1.0
Archived
2026-10-09T22:24:00.883Z
SHA-256 of the archived text
3de232bafdb1d591b3104e1ded68a7a3f8f35b997772da8e64febe5f15d74f94
Stable URL of this page
https://metraipolis.com/documento/dc_1bd3bb42cada

How to cite

AR-WAM: A Visual-Conditioned Agent-Ready World Action Model for Robotic Manipulation — arXiv:2609.23578 — arXiv (en), https://arxiv.org/abs/2609.23578 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1bd3bb42cada (Metraipolis archive dc_1bd3bb42cada, sha256 3de232bafdb1d591b3104e1ded68a7a3f8f35b997772da8e64febe5f15d74f94)
BibTeX
@misc{dc1bd3bb42cada,
  title = {AR-WAM: A Visual-Conditioned Agent-Ready World Action Model for Robotic Manipulation — arXiv:2609.23578},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23578},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1bd3bb42cada; sha256 3de232bafdb1d591b3104e1ded68a7a3f8f35b997772da8e64febe5f15d74f94},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23578. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As AI agents become increasingly capable, agent-driven robotic control is emerging as a compelling paradigm. However, prevailing vision-language-action (VLA) models and world action models (WAMs) still rely on natural-language instructions to specify manipulation tasks, an ill-suited interface for agent-driven control: referentially ambiguous, spatially imprecise, redundant with the agent's inherent language understanding, and entangling intent with execution. We present AR-WAM, a visual-conditioned, agent-ready world action model that replaces language with two complementary conditions: a visual grounding prompt (a bounding box of the target) denoting the interaction object and location, and a learnable operation token dictating the atomic skill to execute. Our compact 0.5B-parameter model, with a frozen pretrained visual encoder and no language encoder, predicts scene evolution within compact latent states while decoding actions, exposing the policy's intent through explicit, supervisable reasoning signals. A model-agnostic compatibility layer provides three primitives (detect, execute, and query) so that local VLMs or online agent APIs can drive the policy directly, with long-horizon memory and closed-loop error recovery delegated to the agent side. On RoboTwin 2.0, RMBench, and a real Astribot S1 dual-arm platform, AR-WAM attains the highest average success on standard manipulation (85.7% over the clean and randomized settings) and outperforms all baselines on memory-dependent and real-robot long-horizon tasks, improving success rates by 5.9% and 36.7%, respectively, while maintaining the lowest inference latency (14.1 ms). Project page is at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.23578 — 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 2026-10-09T21:59:59.602Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).