EVE: A Domain-Specific LLM Framework for Earth Intelligence

TL;DR

EVE is an open-source framework for developing domain-specific large language models tailored for Earth Intelligence, featuring a specialized 24B model, new benchmarks, and deployment tools.

Contribution

It introduces EVE-Instruct, a domain-adapted LLM, along with curated datasets, benchmarks, and a production system for Earth Science applications.

Findings

EVE-Instruct outperforms comparable models on Earth Observation benchmarks.

The system supports 350 pilot users via API and GUI.

All resources are publicly released under open licenses.

Abstract

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.