Metraipolis › archive › dc_8dace7769f79

OSGR: Observation-Support Graph Reasoning for Earth Observation Question Answering — arXiv:2611.04301

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04301
License (as archived)
CC0-1.0
Archived
2026-11-04T21:37:51.964Z
SHA-256 of the archived text
580cd1c33a5f32f8af7f5ae382273d3f1aa66cfd196d72515c55eb38863a0504
Stable URL of this page
https://metraipolis.com/documento/dc_8dace7769f79

How to cite

OSGR: Observation-Support Graph Reasoning for Earth Observation Question Answering — arXiv:2611.04301 — arXiv (en), https://arxiv.org/abs/2611.04301 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8dace7769f79 (Metraipolis archive dc_8dace7769f79, sha256 580cd1c33a5f32f8af7f5ae382273d3f1aa66cfd196d72515c55eb38863a0504)
BibTeX
@misc{dc8dace7769f79,
  title = {OSGR: Observation-Support Graph Reasoning for Earth Observation Question Answering — arXiv:2611.04301},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04301},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8dace7769f79; sha256 580cd1c33a5f32f8af7f5ae382273d3f1aa66cfd196d72515c55eb38863a0504},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04301. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Answering geographic queries over Earth observation (EO) archives requires solving a joint retrieval-and-derivation problem under strict spatiotemporal constraints. Existing LLM agents fail to ground observation items or suffer from search-space explosion. We propose OSGR, a two-stage framework that factorizes this search into offline symbolic concept deduction and online Relation-Conditioned Grounding. OSGR leverages an offline Observation-Support Graph to deduce valid target-to-result support paths at the concept level, and applies spatiotemporal compatibility kernels to instantiate grounded observation-item sets. On Earth-Bench and DisasterM3-Reason, OSGR improves GPT-4o accuracy from 49.3\% to 63.7\% while reducing the execution-step ratio from 2.9 to 2.5.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2611.04301 — 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 2026-11-04T21:35:49.532Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).