Bringing Agentic Search to Earth Observation Data Discovery
cs.IR, cs.LG, physics.ao-ph
Submitted: 2026-07-02
Updated: 2026-09-24
Comments: Accepted at CIKM 2026 (full research paper). v2: camera-ready version; LLM rerank model sweep extended from N=200 to N=600 test queries with paired-bootstrap significance tests; adds a fine-tuned cross-encoder (bge-reranker-v2-m3) as a supervised reranking baseline
License: http://creativecommons.org/licenses/by/4.0/
The gist: NASA and its data centers hold thousands of geoscience datasets and tools like Worldview, Giovanni, the Science Discovery Engine, and Harmony.
Terminology
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 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.
Sources
- FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering
- AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing
- Precise Zero-Shot Dense Retrieval without Relevance Labels
- AutoClimDS: Climate Data Science Agentic AI -- A Knowledge Graph is All You Need
- HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL
- Towards Intelligent Geospatial Data Discovery: a knowledge graph-driven multi-agent framework powered by large language models
- Zero-Shot Listwise Document Reranking with a Large Language Model
- Accelerating Earth Science Discovery via Multi-Agent LLM Systems
- RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!
- Toolformer: Language Models Can Teach Themselves to Use Tools
- DSEBench: A Test Collection for Explainable Dataset Search with Examples
- Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
- ReSearch: A Multi-Stage Machine Learning Framework for Earth Science Data Discovery
- Multi-Disciplinary Dataset Discovery from Citation-Verified Literature Contexts
- A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search
- Rank-K: Test-Time Reasoning for Listwise Reranking
- ReAct: Synergizing Reasoning and Acting in Language Models
- Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusion
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
- MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
- Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition