A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives

TL;DR

This paper introduces PANGAEA-GPT, a hierarchical multi-agent system that autonomously discovers and analyzes geoscientific data, improving data utilization through complex, multi-step workflows with minimal human input.

Contribution

It presents a novel hierarchical multi-agent architecture with data-type-aware routing and self-correction, enabling autonomous data discovery and analysis in large geoscientific repositories.

Findings

Demonstrated effective autonomous workflows in oceanography and ecology case studies.

Enabled complex multi-step data analysis with minimal human intervention.

Improved data utilization in large geoscientific archives.

Abstract

The rapid accumulation of Earth science data has created a significant scalability challenge; while repositories like PANGAEA host vast collections of datasets, citation metrics indicate that a substantial portion remains underutilized, limiting data reusability. Here we present PANGAEA-GPT, a hierarchical multi-agent framework designed for autonomous data discovery and analysis. Unlike standard Large Language Model (LLM) wrappers, our architecture implements a centralized Supervisor-Worker topology with strict data-type-aware routing, sandboxed deterministic code execution, and self-correction via execution feedback, enabling agents to diagnose and resolve runtime errors. Through use-case scenarios spanning physical oceanography and ecology, we demonstrate the system's capacity to execute complex, multi-step workflows with minimal human intervention. This framework provides a methodology for querying and analyzing heterogeneous repository data through coordinated agent workflows.