# Bringing Agentic Search to Earth Observation Data Discovery

arXiv: https://arxiv.org/abs/2607.02387 · HTML: https://mlsanity.com/paper/2607.02387/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [Zero-Shot Listwise Document Reranking with a Large Language Model](https://mlsanity.com/paper/2305.02156/) (2023)
- [Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval](https://mlsanity.com/paper/2312.15503/) (2023)
- [An Analysis of Fusion Functions for Hybrid Retrieval](https://mlsanity.com/paper/2210.11934/) (2022)
- [Rank-K: Test-Time Reasoning for Listwise Reranking](https://mlsanity.com/paper/2505.14432/) (2025)
- [FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering](https://mlsanity.com/paper/2508.14052/) (2025)
- [Accelerating Earth Science Discovery via Multi-Agent LLM Systems](https://mlsanity.com/paper/2503.05854/) (2025)
- [AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing](https://mlsanity.com/paper/2602.17607/) (2026)
- [AutoClimDS: Climate Data Science Agentic AI -- A Knowledge Graph is All You Need](https://mlsanity.com/paper/2509.21553/) (2025)
- [Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusion](https://mlsanity.com/paper/2507.01354/) (2025)
- [Multi-Disciplinary Dataset Discovery from Citation-Verified Literature Contexts](https://mlsanity.com/paper/2601.05099/) (2026)
- [Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy](https://mlsanity.com/paper/2606.24177/) (2026)
- [ReSearch: A Multi-Stage Machine Learning Framework for Earth Science Data Discovery](https://mlsanity.com/paper/2601.14176/) (2026)
- [DSEBench: A Test Collection for Explainable Dataset Search with Examples](https://mlsanity.com/paper/2510.17228/) (2025)
- [Correcting Mean Bias in Text Embeddings: A Refined Renormalization with Training-Free Improvements on MMTEB](https://mlsanity.com/paper/2511.11041/) (2025)
- [Towards Intelligent Geospatial Data Discovery: a knowledge graph-driven multi-agent framework powered by large language models](https://mlsanity.com/paper/2603.20670/) (2026)
- [A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search](https://mlsanity.com/paper/2604.16394/) (2026)
- [HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL](https://mlsanity.com/paper/2605.17792/) (2026)

## Built on by (most cited first, 1 of 1)

- [Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents](https://mlsanity.com/paper/2609.12533/) (2026)

## Abstract (arXiv)

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 framework for geoscience data discovery that takes a natural-language research query and returns 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 to over 5x the unadapted cosine baseline. On top of this supervised pipeline, a zero-shot reranking stage lifts MRR by 16%, significant under a paired bootstrap, with no additional training, and autonomous web and arXiv tool use adds a further gain, showing that LLM reasoning is complementary to supervised retrieval.