A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914349875986432 |
|---|---|
| author | Pantiukhin, Dmitrii Kuznetsov, Ivan Shapkin, Boris Jost, Antonia Anna Jung, Thomas Koldunov, Nikolay |
| author_facet | Pantiukhin, Dmitrii Kuznetsov, Ivan Shapkin, Boris Jost, Antonia Anna Jung, Thomas Koldunov, Nikolay |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21351 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives Pantiukhin, Dmitrii Kuznetsov, Ivan Shapkin, Boris Jost, Antonia Anna Jung, Thomas Koldunov, Nikolay Artificial Intelligence Information Retrieval Multiagent Systems 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. |
| title | A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives |
| topic | Artificial Intelligence Information Retrieval Multiagent Systems |
| url | https://arxiv.org/abs/2602.21351 |