cs.AINov 3, 2026

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

Authors: Dazhou Yu, Zerong Wang, Riyang Bao, Longxiang Li, Yang Liu, Liang Zhao

Organizations: Georgia State University

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.

Figures & tables

Explore similar work

CardsList
  1. Bringing Agentic Search to Earth Observation Data Discovery

    Jul 2, 2026Minghan Yu, Youran Sun, Chugang Yi +2Agentic SearchRemote Sensing

  2. Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents

    Sep 11, 2026Zhutao Lv, Chenhao Dang, Yi Feng +5Remote SensingAI Agent Benchmarks

  3. Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation

    Oct 11, 2026Noam Slonim, Aviv Slobodkin, Gil Fidel +34Geospatial QAGeospatial Reasoning