OceanMind: A multi-agent AI system for ocean diagnosis

2026-09-30

AI Summary

This study addresses the time-consuming nature and diagnostic challenges of extracting quantitative evidence from complex three-dimensional, time-varying ocean variables. We propose a novel multi-agent collaborative system that couples large language models with 3D ocean states. The system employs a four-stage architecture comprising query routing, skill planning, tool execution, and summary generation, integrating a reusable library of 63 analytical skills alongside a reflection-based replanning mechanism to ensure reliable dynamic workflow execution. Benchmark evaluations demonstrate that our approach improves effectiveness by 41.2% and efficiency by 21.5%, while successfully reproducing published oceanographic diagnostic results. This work provides efficient decision-support capabilities for global environmental governance.

Abstract

Time-dependent, three-dimensional (3D) oceanic multi-variables define coherent states of the evolving ocean to facilitate ocean diagnosis and advance ocean science to better inform environmental and hazard management. However, extracting quantitative evidence from these variables requires substantial and complex analytical effort. We introduce OceanMind, a multi-agent AI system that directly couples large language models (LLMs) with comprehensive time-dependent 3D ocean states for swift and effective diagnosis. OceanMind organizes the analytical process into four coordinated complexity stages: Query Routing, Skill-based Planning, Tool Execution, and Evidence-based Summary Generation. Specialized agents interpret user requests, construct and execute multi-step computational workflows, and synthesize quantitative evidence. To ensure reliable workflow construction, 63 reusable ocean-specific analysis skills serve as procedural manuals that guide the LLM agent in selecting data, conducting diagnostics, and applying analytical tools. With reflection and replanning mechanisms that use execution feedback to repair invalid plans, OceanMind ensures reliable analysis workflows across diverse needs. On a benchmark of 240 computational-workflow queries spanning the four stages, OceanMind outperformed general ReAct agents with the same registered tool pool, achieving relative improvements of 41.2% in effectiveness and 21.5% in efficiency. Beyond the benchmark, OceanMind reproduced published oceanic diagnostics, validated hypotheses, and supported environmental decision-making over global oceans. Overall, OceanMind advances LLMs by integrating them with time-dependent 3D ocean analysis, enabling scientific interpretation and enhancing formulation of environmental policies based on quantitative ocean evidence.

Problem

• ocean diagnosis
• 3D ocean states
• quantitative evidence extraction
• multi-variable analysis

Innovation

• Multi-agent AI system
• Large language models
• 3D ocean diagnosis
• Skill-based planning
• Reflection and replanning