Metraipolis › archive › dc_ee3e4dcb830e

EVEREST:Endogenous Vision-Language Reinforcement Reasoning Exploration for Urban Socio-Semantic Segmentation — arXiv:2608.24640

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.24640
License (as archived): CC0-1.0
Archived: 2026-10-18T07:02:41.377Z
SHA-256 of the archived text: 69e12af40cb1c6c4f442c296a07267928b079e083ae9b23382f9c6d3154da2db
Stable URL of this page: https://metraipolis.com/documento/dc_ee3e4dcb830e

How to cite

EVEREST:Endogenous Vision-Language Reinforcement Reasoning Exploration for Urban Socio-Semantic Segmentation — arXiv:2608.24640 — arXiv (en), https://arxiv.org/abs/2608.24640 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee3e4dcb830e (Metraipolis archive dc_ee3e4dcb830e, sha256 69e12af40cb1c6c4f442c296a07267928b079e083ae9b23382f9c6d3154da2db)

BibTeX

@misc{dcee3e4dcb830e,
  title = {EVEREST:Endogenous Vision-Language Reinforcement Reasoning Exploration for Urban Socio-Semantic Segmentation — arXiv:2608.24640},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24640},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee3e4dcb830e; sha256 69e12af40cb1c6c4f442c296a07267928b079e083ae9b23382f9c6d3154da2db},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24640. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Urban socio-semantic segmentation leverages digital and satellite imagery to provide critical spatial semantic information for downstream applications such as urban resource allocation. Although existing methods achieve high segmentation accuracy, they still suffer from inaccurate delineation of target boundaries. The underlying issue is that current models primarily rely on passively aggregated global cross-modal cues, lacking active exploration of the environment. To address this limitation, we propose the EVEREST model, which adopts an egocentric exploration strategy that enables the model to actively investigate boundary cues and perform self-correction. In addition, we formulate discrete natural-language prompts as pseudocode to regularize the execution logic. Reinforcement learning is further employed to implement this irreducible process and elicit the model's structured reasoning capability. Our EVEREST achieves optimal performance on all metrics in the real world urban socio-semantic dataset, demonstrating the superiority of our model. Codes are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.MM).
Categorie arXiv: Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.24640 — 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 2026-10-18T07:00:47.826Z dalla pagina https://arxiv.org/catchup/cs.MM/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).