OSGR: Observation-Support Graph Reasoning for Earth Observation Question Answering

arXiv:2611.04301 · cs.AI, cs.IR · Submitted 2026-11-03 · Read on arXiv

cs.AI, cs.IR

Submitted: 2026-11-03

Updated: 2026-11-03

License: http://creativecommons.org/licenses/by/4.0/

The gist: Answering geographic queries over Earth observation (EO) archives requires solving a joint retrieval-and-derivation problem under strict spatiotemporal constraints.

Abstract

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.

Sources

Related papers