Metraipolis › archive › dc_b5b49fca5891
GPT-6-Astra Lights Up Embodied Navigation: Evaluation in Zero-Shot Vision-and-Language Navigation in Continuous Environments — arXiv:2609.29861
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29861
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T07:17:04.464Z
- SHA-256 of the archived text
b322b19ac55f2ec7596234768f790dc49ca5d5055f231a2f4573d12474e24a16- Stable URL of this page
https://metraipolis.com/documento/dc_b5b49fca5891
How to cite
GPT-6-Astra Lights Up Embodied Navigation: Evaluation in Zero-Shot Vision-and-Language Navigation in Continuous Environments — arXiv:2609.29861 — arXiv (en), https://arxiv.org/abs/2609.29861 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b5b49fca5891 (Metraipolis archive dc_b5b49fca5891, sha256 b322b19ac55f2ec7596234768f790dc49ca5d5055f231a2f4573d12474e24a16)
BibTeX
@misc{dcb5b49fca5891,
title = {GPT-6-Astra Lights Up Embodied Navigation: Evaluation in Zero-Shot Vision-and-Language Navigation in Continuous Environments — arXiv:2609.29861},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29861},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b5b49fca5891; sha256 b322b19ac55f2ec7596234768f790dc49ca5d5055f231a2f4573d12474e24a16},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29861. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We investigate whether GPT-6-Astra, a general-purpose foundation model, can navigate unfamiliar environments using its own perception, reasoning, and decision-making capabilities. Our evaluation focuses on zero-shot vision-and-language navigation in continuous environments (VLN-CE) through a minimal interface in the Codex harness, aiming to unleash GPT-6-Astra's full potential for navigation. Using monocular RGB, GPT-6-Astra decides when to observe, how to move, and when to stop, without navigation-specific fine-tuning, a trained waypoint predictor, or a pre-built scene map. Our evaluation yields four key findings and implications. First, GPT-6-Astra achieves strong zero-shot navigation performance using only monocular RGB observations. On R2R-CE-100, GPT-6-Astra (ultra reasoning) achieves a success rate of 81.3%, exceeding the strongest reported zero-shot and even train-based success rates by 15.3 and 9.2 percentage points, respectively. Second, GPT-6-Astra exhibits promising capabilities in interpreting multi-stage instructions, understanding the environment, and adjusting routes. Third, execution and goal-verification failures persist even with ultra reasoning. Fourth, these results motivate combining general-purpose model capabilities with navigation-specific expertise. Based on these findings, future VLN research should investigate which aspects of instruction interpretation, spatial understanding, and navigation decision-making general-purpose models can handle directly, and where navigation-specific learning can extend their capabilities. This includes exploring how spatial representations, navigation experience, and learned control skills can improve progress tracking, error recovery, and goal verification while preserving the flexibility to adjust routes. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.29861 — 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 2026-10-08T06:38:53.829Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).