{
  "id": 19168,
  "url": "https://arxiv.org/abs/2608.13344v1",
  "title": "LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning",
  "summary": "Long-horizon Earth observation reasoning requires models to organize multi-stage geographic evolution, localize spatial changes, detect temporal anomalies, and infer future from extended image sequences. However, existing remote sensing vision-language models mainly focus on isolated images, image pairs, or short sequences, limiting reliable grounding in the relevant frames and regions. We introduce LongEarth-Bench, a benchmark containing approximately 120k question-answering samples derived fro",
  "authors": "Yupan Ding, Jing Xiao, Zhenyuan Zhang, Chaofeng Chen, Liang Liao, Gui-Song Xia et al.",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T15:14:59.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19168",
  "original_url": "https://arxiv.org/abs/2608.13344v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}