mlsanityData to 14 Oct 2026

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

arXiv 2602.21351 ↗First posted 24 Feb 2026cs.AI cs.IR cs.MAcited by 4

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 29 of its 53 references that are in the map. First posted on arXiv 24 Feb 2026.

Builds on

29 of 53 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search10 Apr
  2. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG15 Jan
  3. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning9 Sep
  4. 2024Data Interpreter: An LLM Agent For Data Science28 Feb
  5. 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning27 Feb

Other references · 24

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  8. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  9. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  10. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  11. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  12. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
12 more
  1. 2025Accelerating scientific discovery with Co-Scientistcited by 401
  2. 2023SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Modelscited by 256
  3. 2023Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflowcited by 76
  4. 2025Robin: A multi-agent system for automating scientific discoverycited by 62
  5. 2023OceanGPT: A Large Language Model for Ocean Science Taskscited by 43
  6. 2023GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPTcited by 41
  7. 2024AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligencecited by 36
  8. 2023GeoGalactica: A Scientific Large Language Model in Geosciencecited by 33
  9. 2024An Autonomous GIS Agent Framework for Geospatial Data Retrievalcited by 26
  10. 2024An LLM Agent for Automatic Geospatial Data Analysiscited by 21
  11. 2025Accelerating Earth Science Discovery via Multi-Agent LLM Systemscited by 13
  12. 2025AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agentscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026HVR-Met: A Hypothesis-Verification-Replanning Agentic System for Extreme Weather Diagnosiscited by 2
  2. 2026Towards Multi-Agent Autonomous Reasoning in Hydrodynamicscited by 0
  3. 2026Earth Science Foundation Models: From Perception to Reasoning and Discoverycited by 0
  4. 2026CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate Sciencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasets
  2. 2026ST-Bench: A Spatial-Temporal Benchmark for Multi-Agent System Generation on Scientific Research Tasks
  3. 2026NORA: A Harness-Engineered Autonomous Research Agent for End-to-End Spatial Data Science
  4. 2026HERMES: a multi-agent framework for structured knowledge extraction from ultra-long documents in geoscience
  5. 2026EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
  6. 2026AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding
  7. 2026AutoKD: Autonomous Knowledge Discovery
  8. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics