Guardado en:
Detalles Bibliográficos
Autores principales: Atrio, Àlex R., Lopez, Antonio, Rohit, Jino, Ouahidi, Yassine El, Politi, Marcello, Iyer, Vijayasri, Jamil, Umar, Bratières, Sébastien, Longépé, Nicolas
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.13071
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918467426320384
author Atrio, Àlex R.
Lopez, Antonio
Rohit, Jino
Ouahidi, Yassine El
Politi, Marcello
Iyer, Vijayasri
Jamil, Umar
Bratières, Sébastien
Longépé, Nicolas
author_facet Atrio, Àlex R.
Lopez, Antonio
Rohit, Jino
Ouahidi, Yassine El
Politi, Marcello
Iyer, Vijayasri
Jamil, Umar
Bratières, Sébastien
Longépé, Nicolas
contents We introduce Earth Virtual Expert (EVE), the first open-source, end-to-end initiative for developing and deploying domain-specialized LLMs for Earth Intelligence. At its core is EVE-Instruct, a domain-adapted 24B model built on Mistral Small 3.2 and optimized for reasoning and question answering. On newly constructed Earth Observation and Earth Sciences benchmarks, it outperforms comparable models while preserving general capabilities. We release curated training corpora and the first systematic domain-specific evaluation benchmarks, covering MCQA, open-ended QA, and factuality. EVE further integrates RAG and a hallucination-detection pipeline into a production system deployed via API and GUI, supporting 350 pilot users so far. All models, datasets, and code are ready to be released under open licenses as contributions to our field at huggingface.co/eve-esa and github.com/eve-esa.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13071
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EVE: A Domain-Specific LLM Framework for Earth Intelligence
Atrio, Àlex R.
Lopez, Antonio
Rohit, Jino
Ouahidi, Yassine El
Politi, Marcello
Iyer, Vijayasri
Jamil, Umar
Bratières, Sébastien
Longépé, Nicolas
Computation and Language
Artificial Intelligence
We introduce Earth Virtual Expert (EVE), the first open-source, end-to-end initiative for developing and deploying domain-specialized LLMs for Earth Intelligence. At its core is EVE-Instruct, a domain-adapted 24B model built on Mistral Small 3.2 and optimized for reasoning and question answering. On newly constructed Earth Observation and Earth Sciences benchmarks, it outperforms comparable models while preserving general capabilities. We release curated training corpora and the first systematic domain-specific evaluation benchmarks, covering MCQA, open-ended QA, and factuality. EVE further integrates RAG and a hallucination-detection pipeline into a production system deployed via API and GUI, supporting 350 pilot users so far. All models, datasets, and code are ready to be released under open licenses as contributions to our field at huggingface.co/eve-esa and github.com/eve-esa.
title EVE: A Domain-Specific LLM Framework for Earth Intelligence
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.13071