Metraipolis › archive › dc_2c385aa66f91

NavHarness: Adaptive Goals for Agentic Vision-Language Navigation — arXiv:2609.39915

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39915
License (as archived)
CC0-1.0
Archived
2026-10-07T14:46:31.316Z
SHA-256 of the archived text
6aeade12df0edd369bbe8c7857e820761bc89fca3b935d31cae69a30a116686e
Stable URL of this page
https://metraipolis.com/documento/dc_2c385aa66f91

How to cite

NavHarness: Adaptive Goals for Agentic Vision-Language Navigation — arXiv:2609.39915 — arXiv (en), https://arxiv.org/abs/2609.39915 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c385aa66f91 (Metraipolis archive dc_2c385aa66f91, sha256 6aeade12df0edd369bbe8c7857e820761bc89fca3b935d31cae69a30a116686e)
BibTeX
@misc{dc2c385aa66f91,
  title = {NavHarness: Adaptive Goals for Agentic Vision-Language Navigation — arXiv:2609.39915},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39915},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c385aa66f91; sha256 6aeade12df0edd369bbe8c7857e820761bc89fca3b935d31cae69a30a116686e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39915. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language Navigation (VLN) requires embodied agents to generate actions based on instructions and observations. General-purpose multimodal agents offer a promising basis for this task, but selecting plausible local actions does not ensure that execution remains consistent with the intended route, particularly in long-horizon tasks. Moreover, the accumulated interaction history increases the input required for subsequent decisions, resulting in a significant inference overhead. To this end, we introduce \method, an Agentic VLN framework that includes a Goal Agent that sets adaptive goals for local actions, a Verify Agent that dynamically verifies whether a goal has been completed, a Memory Agent for multimodal context compression, and a Visuomotor Agent to execute adaptive goals. Specifically, the Goal Agent formulates adaptive goals based on the instruction, current observation, and execution history. Then the Visuomotor Agent executes navigation actions to achieve each goal, while the Verify Agent uses a goal-specific verification question to dynamically assess whether the observed outcomes satisfy the intended completion condition. Verified goal completion then marks a boundary for the Memory Agent to compress the corresponding multimodal interaction history while preserving information needed for subsequent navigation. We evaluate navigation on R2R-CE and RxR-CE, examine framework variants across three model backbones, and study context evolution during execution. For Real-World evaluation, \method achieves 83.3\% success and 1.51\,m navigation error across eight challenging routes evaluated three times each.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.39915 — 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 2026-10-07T14:19:00.826Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).