Bringing Agentic Search to Earth Observation Data Discovery

• URL: http://arxiv.org/abs/2607.02387v1
• Date: Thu, 02 Jul 2026 16:24:16 GMT
• Title: Bringing Agentic Search to Earth Observation Data Discovery
• Abstract summary: NASA holds thousands of geoscience datasets and tools like Worldview, Giovanni, the Science Discovery Engine, and Harmony.<n>We present an agentic search system, deployed as a public service for the geoscience community, that takes a natural-language research query and returns the matching datasets and tools.
• Score: 5.785021425715989
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: NASA and its data centers hold thousands of geoscience datasets and tools like Worldview, Giovanni, the Science Discovery Engine, and Harmony. Finding the right one is hard even for domain experts. We present an agentic search system, deployed as a public service for the geoscience community, that takes a natural-language research query and returns the matching datasets and tools. We demonstrate that, in the era of large language models, the latent value of knowledge graphs (KGs) can be substantially amplified through agentic search. From the NASA Earth Observation Knowledge Graph (NASA EO-KG) we derive NASA-EO-Bench, an open benchmark of 47k query-dataset pairs (21k task-based queries). A neural scorer fine-tuned on NASA-EO-Bench beats cosine and BM25 baselines. Further combining it with BM25 via score fusion raises both Recall@10 (R@10) and MRR by over 5x. On top of this supervised pipeline, we add a zero-shot agentic reranking stage that, without any additional training, lifts MRR by 28% on a stratified N=200 subset, showing that LLM reasoning is complementary to supervised retrieval.

Related papers

• Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent [55.77954024801206]
  Marine lead (Pb) and its isotopes are critical tracers for ocean circulation and anthropogenic pollution.<n>Manual extraction is unscalable, while general-purpose Large Language Models (LLMs) lack the necessary domain-specific knowledge.<n>We introduce an expert-guided adaptation approach that enables LLMs to perform rigorous scientific data extraction without fine-tuning.
  arXiv  Detail & Related papers  (2026-05-28T14:06:25Z)
• AgentIR: Reasoning-Aware Retrieval for Deep Research Agents [76.29382561831105]
  Deep Research agents generate explicit natural language reasoning before each search call.<n> Reasoning-Aware Retrieval embeds the agent's reasoning trace alongside its query.<n>DR- Synth generates Deep Research retriever training data from standard QA datasets.<n>AgentIR-4B achieves 68% accuracy with the open-weight agent Tongyi-DeepResearch.
  arXiv  Detail & Related papers  (2026-03-04T18:47:26Z)
• Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval [26.815539094904278]
  ARK: Adaptive Retriever of Knowledge, gives a language model control over this breadth-depth tradeoff.<n>ARK alternates between breadth-oriented discovery and depth-oriented expansion without depending on a fragile seed selection.<n>ARK reaches 59.1% average Hit@1 and 67.4 average MRR, improving average Hit@1 by up to 31.4% and average MRR by up to 28.0% over retrieval-based and agentic training-free methods.
  arXiv  Detail & Related papers  (2026-01-20T13:46:37Z)
• OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation [68.10925029626709]
  OlmoEarth is a multimodal, sequential-temporal foundation model designed for the Earth observation domain.<n>OlmoEarth achieves state-of-the-art performance compared to 12 other foundation models.<n>We deploy OlmoEarth as the backbone of an end-to-end platform for data collection, labeling, training observation and inference of Earth observation models.
  arXiv  Detail & Related papers  (2025-11-17T18:06:26Z)
• Towards LLM Agents for Earth Observation [63.163707376462405]
  We introduce datasetnamenospace, a benchmark of 140 yes/no questions from NASA Earth Observatory articles across 13 topics and 17 satellite sensors.<n>Using Google Earth Engine API as a tool, LLM agents can only achieve an accuracy of 33% because the code fails to run over 58% of the time.<n>We improve the failure rate for open models by fine-tuning synthetic data, allowing much smaller models to achieve comparable accuracy to much larger ones.
  arXiv  Detail & Related papers  (2025-04-16T14:19:25Z)
• DSBench: How Far Are Data Science Agents from Becoming Data Science Experts? [58.330879414174476]
  We introduce DSBench, a benchmark designed to evaluate data science agents with realistic tasks.<n>This benchmark includes 466 data analysis tasks and 74 data modeling tasks, sourced from Eloquence and Kaggle competitions.<n>Our evaluation of state-of-the-art LLMs, LVLMs, and agents shows that they struggle with most tasks, with the best agent solving only 34.12% of data analysis tasks and achieving a 34.74% Relative Performance Gap (RPG)
  arXiv  Detail & Related papers  (2024-09-12T02:08:00Z)
• GeoGalactica: A Scientific Large Language Model in Geoscience [95.15911521220052]
  Large language models (LLMs) have achieved huge success for their general knowledge and ability to solve a wide spectrum of tasks in natural language processing (NLP) We specialize an LLM into geoscience, by further pre-training the model with a vast amount of texts in geoscience, as well as supervised fine-tuning (SFT) the resulting model with our custom collected instruction tuning dataset. We train GeoGalactica over a geoscience-related text corpus containing 65 billion tokens, preserving as the largest geoscience-specific text corpus. Then we fine-tune the model with 1 million pairs of instruction-tuning
  arXiv  Detail & Related papers  (2023-12-31T09:22:54Z)
• NASA Science Mission Directorate Knowledge Graph Discovery [0.0]
  This paper proposes a pipeline to generate knowledge graphs (KGs) representing different NASA domains. These KGs can be used as the basis for dataset search engines, saving researchers time and supporting them in finding new connections.
  arXiv  Detail & Related papers  (2023-03-20T05:12:43Z)
• EarthNets: Empowering AI in Earth Observation [24.160463837610074]
  Earth observation (EO) aims at monitoring the state of planet Earth using remote sensing data. This paper presents a comprehensive review of more than 500 publicly published datasets. We propose to measure, rank, and select datasets to build a new benchmark for model evaluation.
  arXiv  Detail & Related papers  (2022-10-10T18:09:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.