---
title: "OSGR: Observation-Support Graph Reasoning for Earth Observation Question Answering"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04301v1"
permalink: "https://feed.astralor.com/items/itm_a8031992b456af5b023e9263"
published: "2026-11-03T04:31:43.000Z"
score: 54
channel: "tech"
tags: ["LLM","AI Agent","OpenAI","RAG","OSGR","Observation-Support Graph Reasoning","Earth Observation Question","Answering Answering"]
---

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

## At a glance

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 o…

## Key points

- 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.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_a8031992b456af5b023e9263