Metraipolis › archive › dc_873ff28e901e
VerNav: Verifier-First Low-Latency Vision-and-Language Navigation — arXiv:2609.00920
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00920
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:14:04.059Z
- SHA-256 of the archived text
8f28dc933853009fad4dd7ef3dd9235e4be27f08c4c909a22209fa331b0a9440- Stable URL of this page
https://metraipolis.com/documento/dc_873ff28e901e
How to cite
VerNav: Verifier-First Low-Latency Vision-and-Language Navigation — arXiv:2609.00920 — arXiv (en), https://arxiv.org/abs/2609.00920 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_873ff28e901e (Metraipolis archive dc_873ff28e901e, sha256 8f28dc933853009fad4dd7ef3dd9235e4be27f08c4c909a22209fa331b0a9440)
BibTeX
@misc{dc873ff28e901e,
title = {VerNav: Verifier-First Low-Latency Vision-and-Language Navigation — arXiv:2609.00920},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00920},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_873ff28e901e; sha256 8f28dc933853009fad4dd7ef3dd9235e4be27f08c4c909a22209fa331b0a9440},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00920. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-and-Language Navigation (VLN) requires an agent to navigate through unseen 3D environments according to natural-language instructions. Explicit reasoning can improve instruction understanding and semantic grounding, but autoregressive generation at every step accumulates large decision-stage latency over multi-step navigation. We propose VerNav, a verifier-first framework for low-latency LLM-based VLN. The verifier reduces decision-stage latency by replacing per-step autoregressive generation with batched action verification, while an entropy-based adaptive generator is invoked only for uncertain decisions to produce compact state evidence. To further improve navigation performance with the verifier, we introduce a two-stage alignment scheme: (i) VPO improves local action-preference alignment in static verifier training, and (ii) step-level reinforcement fine-tuning provides dense progress rewards over multi-step navigation rollouts during dynamic task execution. Experiments on the Room-to-Room (R2R) benchmark show that the verifier-only decision path of VerNav achieves competitive navigation performance among representative LLM-based VLN agents while reducing average decision-stage LLM latency per step by more than $10\times$ compared with autoregressive methods. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.00920 — 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 2026-10-17T07:00:59.016Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).