A recent study on long-horizon Earth observation reasoning has gained significant attention. 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. To address this issue, researchers introduced the LongEarth-Bench benchmark, containing approximately 120k question-answering samples derived from 117k unique images. These sequences average 15.14 frames and extend to 30 frames, covering 12 tasks across evolution summarization, spatial reasoning, anomaly identification, and logical prediction. A 30k-sample subset further provides structured reasoning traces linking key frames and changed regions to final answers. Researchers developed LongEarth through supervised fine-tuning with explicit sequence identifiers and structured chain-of-thought supervision. Building on LongEarth, LongEarth-R1 applies group relative policy optimization with format, temporal, and spatial rewards. LongEarth-R1 achieves the best results on all 12 long-sequence tasks while remaining competitive on standard remote sensing benchmarks. Blogger's Review: The introduction of LongEarth-R1 marks a significant breakthrough in the field of long-horizon Earth observation reasoning, with potential applications in environmental monitoring, climate change research, and more.