Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent

• URL: http://arxiv.org/abs/2605.29966v1
• Date: Thu, 28 May 2026 14:06:25 GMT
• Title: Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent
• Abstract summary: 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.
• Score: 55.77954024801206
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Marine lead (Pb) and its isotopes are critical tracers for ocean circulation and anthropogenic pollution, yet in-situ observations remain costly and sparse. While vast historical records exist, they lie buried within the unstructured content of academic papers, creating "data silos" inaccessible to comprehensive analysis. Manual extraction is unscalable, while general-purpose Large Language Models (LLMs) lack the necessary domain-specific knowledge, leading to hallucinations and scientifically invalid outputs. To address this, we introduce an expert-guided adaptation approach that enables LLMs to perform rigorous scientific data extraction without fine-tuning. We operationalize this approach through Compass, an LLM agent framework enhanced by a Knowledge Tree co-designed with marine scientists, which decomposes complex tasks into verifiable steps, guiding the agent's reasoning to ensure scientific validity. Deploying Compass across a corpus of over 230,000 relevant open-access papers, we successfully extract 3,751 previously unincorporated Pb records. This effort establishes the largest integrated marine Pb database to date. Beyond standard metrics, Compass demonstrates superior reliability through multi-layered validation, achieving 92% accuracy as confirmed through expert manual verification. The newly integrated data expand coverage in previously under-sampled regions such as the East China Sea and the Southern Ocean, providing an enriched data foundation for future scientific discoveries. We release an interactive visualization platform to facilitate open scientific access. Our work demonstrates that expert-guided agents can effectively bridge the gap between general-purpose LLMs and high-stakes scientific domains, enabling scalable data discovery in geosciences.

Related papers

• HERMES: a multi-agent framework for structured knowledge extraction from ultra-long documents in geoscience [41.77130029890288]
  HERMES is a scalable multi-agent framework that extracts structured data from scientific documents.<n>It integrates domain constraints, validation rules and evidence tracing within a unified document-level extraction process.<n>The system produced a structured database of 32,277 fossil entities and 451,878 attributes, released online at https://treatise.geolex.org.
  arXiv  Detail & Related papers  (2026-08-14T07:59:58Z)
• SciDataSailor: Deep Scientific Data Exploring [11.927301007678244]
  We present SciDataSailor, a framework for synthesizing tool-interactive trajectories by balancing broad exploration with targeted exploitation.<n>We construct SciDataSailor-SFT-2K for supervised fine-tuning and SciDataSailor-Bench for evaluation, with the latter comprising 627 meta-information summarization tasks and 586 scientific question-answering tasks across 27 datasets.
  arXiv  Detail & Related papers  (2026-07-29T05:08:21Z)
• OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models [57.19693589926157]
  OceanPile is a large-scale multimodal corpus designed for ocean foundation models.<n>It comprises three key components: OceanCorpus, OceanInstruction, and OceanBenchmark.<n>All datasets are publicly released to advance the field of marine artificial intelligence.
  arXiv  Detail & Related papers  (2026-04-25T14:53:37Z)
• Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration [63.61423859450929]
  This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses.<n>We identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery.
  arXiv  Detail & Related papers  (2026-01-20T18:46:42Z)
• MARVEL: A Multi Agent-based Research Validator and Enabler using Large Language Models [2.0725712989738994]
  We present MARVEL, a framework for domain-aware question answering and assisted scientific research.<n>MARVEL combines a fast path for straightforward queries with a more deliberate DeepSearch mode that integrates retrieval-augmented generation and Monte Carlo Tree Search.<n>We applied this framework in the context of gravitational-wave research related to the Laser Interferometer Gravitational-wave Observatory.
  arXiv  Detail & Related papers  (2026-01-06T21:47:22Z)
• A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers [251.23085679210206]
  Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research.<n>This survey reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate.<n>We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge.
  arXiv  Detail & Related papers  (2025-08-28T18:30:52Z)
• OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction [70.48962924608033]
  This work presents the first systematic effort to construct an Ocean Knowledge Graph (OKG) specifically designed to represent diverse ocean knowledge for SST prediction.<n>We develop a graph embedding network to learn the comprehensive semantic and structural knowledge within the OKG, capturing both the unique characteristics of individual sea regions and the complex correlations between them. Finally, we align the learned knowledge with fine-grained numerical SST data and leverage a pre-trained LLM to model SST patterns for accurate prediction.
  arXiv  Detail & Related papers  (2025-07-31T02:06:03Z)
• Accelerating Earth Science Discovery via Multi-Agent LLM Systems [0.1398098625978622]
  This Perspective explores the transformative potential of Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) in the geosciences.<n>MAS possesses transformative potential for improving scientists' interaction with geoscientific data by enabling intelligent data processing, natural language interfaces, and collaborative problem-solving capabilities.
  arXiv  Detail & Related papers  (2025-03-07T13:25:56Z)
• OceanBench: The Sea Surface Height Edition [5.307677318971956]
  Ocean satellite data presents challenges for information extraction due to their sparsity and irregular sampling, signal complexity, and noise. Machine learning (ML) techniques have demonstrated their capabilities in dealing with large-scale, complex signals. OceanBench is a unifying framework that provides standardized processing steps that comply with domain-expert standards.
  arXiv  Detail & Related papers  (2023-09-27T12:00:40Z)
• Toward the Automated Construction of Probabilistic Knowledge Graphs for the Maritime Domain [60.76554773885988]
  International maritime crime is becoming increasingly sophisticated, often associated with wider criminal networks. This has led to research and development efforts aimed at combining hard data with other types of data. We propose Maritime DeepDive, an initial prototype for the automated construction of probabilistic knowledge graphs.
  arXiv  Detail & Related papers  (2023-05-04T00:24:30Z)

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.