Metraipolis › archive › dc_0dec0054b375

GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation — arXiv:2608.29483

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.29483
License (as archived): CC0-1.0
Archived: 2026-10-17T08:08:01.525Z
SHA-256 of the archived text: 7f71381216e3a5441ab7fa38aa82b2a314cfcf07583fe2f2c45e91fb4484eeb2
Stable URL of this page: https://metraipolis.com/documento/dc_0dec0054b375

How to cite

GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation — arXiv:2608.29483 — arXiv (en), https://arxiv.org/abs/2608.29483 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0dec0054b375 (Metraipolis archive dc_0dec0054b375, sha256 7f71381216e3a5441ab7fa38aa82b2a314cfcf07583fe2f2c45e91fb4484eeb2)

BibTeX

@misc{dc0dec0054b375,
  title = {GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation — arXiv:2608.29483},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29483},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0dec0054b375; sha256 7f71381216e3a5441ab7fa38aa82b2a314cfcf07583fe2f2c45e91fb4484eeb2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29483. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern Vision-Language Models (VLMs) perform well above the human baseline in image geolocalization, a task critically important in disaster response, OSINT verification, and location privacy. However, most efforts to study AI behavior on the task remain limited to static image-based retrieval, classification, and predictions. We argue that faithful recreation of the task should involve embodied navigation, where a multimodal agent autonomously explores its surroundings to gather observations before submitting a prediction. To this end, we introduce \textbf{GeoAgent}, an agentic environment-based benchmark that requires agents to navigate Street View environments to refine their geolocalization through sequential reasoning. Our analysis shows that modern VLMs struggle to discern regional patterns while succeeding at country- and continent-level predictions. When compared to static image-based baselines, agentic navigation significantly improves accuracy across established metrics. We also note severe bias in a developed/developing region context across frontier model architectures and poor self-improvement capabilities given incorrect priors. Overall, our work establishes the challenges of embodied navigation and geospatial reasoning. We publicly release our code and the GeoAgent environment: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.29483 — 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 2026-10-17T07:47:52.908Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).