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

arXiv: https://arxiv.org/abs/2605.29966 · HTML: https://mlsanity.com/paper/2605.29966/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 100 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 14 of 14)

- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [PaperQA: Retrieval-Augmented Generative Agent for Scientific Research](https://mlsanity.com/paper/2312.07559/) (2023)
- [AutoWebGLM: A Large Language Model-based Web Navigating Agent](https://mlsanity.com/paper/2404.03648/) (2024)
- [AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation](https://mlsanity.com/paper/2408.00764/) (2024)
- [TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy](https://mlsanity.com/paper/2406.01326/) (2024)
- [K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization](https://mlsanity.com/paper/2306.05064/) (2023)
- [OceanGPT: A Large Language Model for Ocean Science Tasks](https://mlsanity.com/paper/2310.02031/) (2023)
- [From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models](https://mlsanity.com/paper/2310.07338/) (2023)
- [CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systems](https://mlsanity.com/paper/2306.11216/) (2023)
- [MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions](https://mlsanity.com/paper/2502.16796/) (2025)
- [MatViX: Multimodal Information Extraction from Visually Rich Articles](https://mlsanity.com/paper/2410.20494/) (2024)
- [Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance](https://mlsanity.com/paper/2307.03119/) (2023)
- [AceMap: Knowledge Discovery through Academic Graph](https://mlsanity.com/paper/2403.02576/) (2024)

## Abstract (arXiv)

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.