Metraipolis › archive › dc_da40513d1ed3

How Far Can GPT-6-Astra Go? Evaluating Capabilities in Zero-Shot Vision-and-Language Navigation — arXiv:2609.20116

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20116
License (as archived)
CC0-1.0
Archived
2026-10-10T05:25:41.481Z
SHA-256 of the archived text
83007bc0c53691f5c906e41653b6ac732fab086557db6b2698ccaa7b16fb3d31
Stable URL of this page
https://metraipolis.com/documento/dc_da40513d1ed3

How to cite

How Far Can GPT-6-Astra Go? Evaluating Capabilities in Zero-Shot Vision-and-Language Navigation — arXiv:2609.20116 — arXiv (en), https://arxiv.org/abs/2609.20116 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da40513d1ed3 (Metraipolis archive dc_da40513d1ed3, sha256 83007bc0c53691f5c906e41653b6ac732fab086557db6b2698ccaa7b16fb3d31)
BibTeX
@misc{dcda40513d1ed3,
  title = {How Far Can GPT-6-Astra Go? Evaluating Capabilities in Zero-Shot Vision-and-Language Navigation — arXiv:2609.20116},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20116},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da40513d1ed3; sha256 83007bc0c53691f5c906e41653b6ac732fab086557db6b2698ccaa7b16fb3d31},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20116. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study GPT-6-Astra in a zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) system, where it interprets instructions, assesses its surroundings, and proposes actions. The system uses a common observation--decision--execution workflow with direct model API calls, without a packaged agent harness or navigation-specific fine-tuning. In this workflow, each request receives selected observations, execution feedback, and retained progress records. Evaluation covers the complete system, including context management and action control. We evaluate the system on 50 of the 100 R2R-CE val-unseen episodes used by Open-Nav. It achieves a success rate of 52.0\%, an SPL of 48.9\%, and an nDTW of 70.8\%. Our analysis highlights three findings. First, recorded responses link landmarks and earlier actions to instructions using observations and supplied history. Second, reviews include requests for additional views and revisions of uncertain judgments. Third, the results suggest a gap between task understanding and autonomous completion: an unfinished crossing is recognized while rotation continues. At termination, 36.0\% of episodes succeed with a workflow-accepted STOP, while another 16.0\% meet the distance criterion at the step limit. These results highlight a central challenge: translating correct local judgments into sustained progress and appropriate stopping.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.20116 — 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 2026-10-10T04:47:38.889Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).