发表机构
The Hong Kong University of Science and Technology（香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
OceanMind是一个多智能体AI系统，通过将大语言模型与三维海洋数据耦合，实现快速有效的海洋诊断，显著提升分析效能。
AI 中文摘要
随时间变化的三维（3D）海洋多变量定义了演化海洋的相干状态，有助于海洋诊断并推动海洋科学更好地为环境和灾害管理提供信息。然而，从这些变量中提取定量证据需要大量且复杂的分析工作。我们引入了OceanMind，一个多智能体AI系统，它直接将大型语言模型（LLMs）与全面的随时间变化的三维海洋状态耦合，以实现快速有效的诊断。OceanMind将分析过程组织为四个协调的复杂度阶段：查询路由、基于技能的规划、工具执行和基于证据的摘要生成。专门的智能体解释用户请求，构建并执行多步骤计算工作流，并综合定量证据。为确保可靠的工作流构建，63个可重用的海洋特定分析技能作为程序手册，指导LLM智能体选择数据、进行诊断和应用分析工具。通过利用执行反馈修复无效计划的反思和重新规划机制，OceanMind确保在各种需求下都能实现可靠的分析工作流。在一个涵盖四个阶段的240个计算工作流查询的基准测试中，OceanMind优于使用相同注册工具池的通用ReAct智能体，在有效性上实现了41.2%的相对提升，在效率上实现了21.5%的相对提升。在基准测试之外，OceanMind重现了已发表的海洋诊断结果，验证了假设，并支持了全球海洋的环境决策。总体而言，OceanMind通过将LLMs与随时间变化的3D海洋分析相结合，推动了LLMs的发展，实现了科学解释，并增强了基于定量海洋证据的环境政策制定。
英文摘要
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.
