Metraipolis › archive › dc_db2e7da162d1

RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation — arXiv:2609.32224

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32224
License (as archived)
CC0-1.0
Archived
2026-10-07T20:55:13.749Z
SHA-256 of the archived text
cbeba6de8bafe8b1dac240496d895edd793cbb0ac556cdfc0a273a0e85e1f349
Stable URL of this page
https://metraipolis.com/documento/dc_db2e7da162d1

How to cite

RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation — arXiv:2609.32224 — arXiv (en), https://arxiv.org/abs/2609.32224 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db2e7da162d1 (Metraipolis archive dc_db2e7da162d1, sha256 cbeba6de8bafe8b1dac240496d895edd793cbb0ac556cdfc0a273a0e85e1f349)
BibTeX
@misc{dcdb2e7da162d1,
  title = {RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation — arXiv:2609.32224},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32224},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db2e7da162d1; sha256 cbeba6de8bafe8b1dac240496d895edd793cbb0ac556cdfc0a273a0e85e1f349},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32224. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We explore whether Omni-Language Models (OLMs) can be directly applied to zero-shot Semantic Audio-Visual Navigation (SAVN). Recent work demonstrates that even state-of-the-art specialized models still struggle to achieve generalist multimodal navigation, despite extensive task-specific training. In this paper, we introduce RAO-Nav, short for Reasoning All-in-One OLM, a deployment pipeline for zero-shot SAVN. By leveraging the rich implicit audio-visual knowledge encoded in OLMs, the embodied agent is enabled to ``hear'', ``see'', ``reason'', and ``act'' in the environment. To further elicit the built-in thinking ability of OLMs, we propose a test-time Latent Navigation Reasoning (LNR) module that can be seamlessly integrated into the decoding space. LNR encourages the model to retrieve more target-relevant observations and make effective navigation decisions. Through comprehensive experiments, we show that our framework surpasses existing state-of-the-art baselines on public SAVN benchmarks without using any training data. Moreover, we introduce a new \emph{Global Navigation Instruction} setting to further evaluate the ability of OLMs to serve as embodied navigation agents. Code: this https URL \_Nav.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32224 — 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 2026-10-07T20:29:00.734Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).