Metraipolis › archive › dc_dcfa9570d72c
Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents — arXiv:2609.12533
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12533
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:03:27.868Z
- SHA-256 of the archived text
10c726afcdd0f786dd44091b80733b4ec111b932c6881e4c34a44bae99b9cdde- Stable URL of this page
https://metraipolis.com/documento/dc_dcfa9570d72c
How to cite
Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents — arXiv:2609.12533 — arXiv (en), https://arxiv.org/abs/2609.12533 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcfa9570d72c (Metraipolis archive dc_dcfa9570d72c, sha256 10c726afcdd0f786dd44091b80733b4ec111b932c6881e4c34a44bae99b9cdde)
BibTeX
@misc{dcdcfa9570d72c,
title = {Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents — arXiv:2609.12533},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12533},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcfa9570d72c; sha256 10c726afcdd0f786dd44091b80733b4ec111b932c6881e4c34a44bae99b9cdde},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12533. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Real-world Earth observation (EO) agents must translate high-level scientific questions into executable workflows to acquire observations, prepare data, perform domain computations, and derive conclusions from runtime evidence. Existing EO agents typically start from supplied observations, while benchmarks typically provide prepared inputs or candidate answers, leaving full-chain open-world EO execution largely untested. We present Earth-Agent-Pro, an execution-adaptive Plan-and-Execute framework using expert-authored skills to constrain planning and runtime tool use. Workflow-centered structured memory records planned steps, accepted evidence, and their dependencies, enabling repair of only the affected workflow suffix when runtime evidence invalidates a step. Separate large language model adapters use sequence-level supervised fine-tuning for planner workflow composition and node-level group relative policy optimization with locally verifiable rewards for executor tool-argument grounding. Earth-Bench-Pro instantiates 248 expert-curated task cores as 744 questions under three matched regimes. Its 248 Open-World Execution questions span RGB imagery, spectral observations, and remote sensing products, pairing high-level requests with runtime data requirements, executable trajectories, and open-ended answers grounded in execution evidence. With a shared GPT-5 backbone, Earth-Agent-Pro achieves 66.13% LLM-as-Judge accuracy, exceeding ReAct by 20.95 points in this metric and 24.44 points in Tools-In-Order. Joint adapter tuning raises Qwen3.5-9B LLM-as-Judge accuracy from 38.31% to 50.00%, an 11.69-point gain over the untuned configuration. Planning-only evaluation and execution with the reference workflow show that the adapters improve workflow composition and argument grounding, respectively. Code and datasets will be released soon. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.12533 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T02:51:27.920Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).