CLIMATEAGENT: 多智能体编排用于复杂气候数据科学工作流
CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows
AI总结：
ClimateAgent通过多智能体编排和动态API意识，实现端到端自动化气候数据分析，取得优于基线方法的高任务完成率和报告质量。
摘要：
气候科学需要自动化的工作流将广泛的问题转化为数据驱动的陈述，以处理大规模、异构的数据集。然而，通用的LLM智能体和静态脚本管道缺乏气候特定的上下文和灵活性，因此在实践中表现不佳。我们提出了ClimateAgent，一个自主的多智能体框架，用于编排端到端的气候数据分析工作流。ClimateAgent将用户的问题分解为可执行的子任务，由一个Orchestrate-Agent和一个Plan-Agent协调；通过专门的Data-Agents获取数据，这些Data-Agents动态 introspect API以合成稳健的下载脚本；并通过Coding-Agent完成分析和报告，该Coding-Agent生成Python代码、可视化和最终报告，具有内置的自我纠正循环。为了系统评估，我们引入了Climate-Agent-Bench-85，一个包含85个真实世界任务的基准，涵盖大气河流、干旱、极端降水、热浪、海表温度和热带气旋。在Climate-Agent-Bench-85上，ClimateAgent实现了100%的任务完成率和报告质量得分为8.32，优于GitHub-Copilot（6.27）和GPT-5基线（3.26）。这些结果表明，我们的多智能体编排与动态API意识和自我纠正执行显著推进了可靠、端到端自动化气候科学分析任务。
英文摘要：
Climate science demands automated workflows to transform comprehensive questions into data-driven statements across massive, heterogeneous datasets. However, generic LLM agents and static scripting pipelines lack climate-specific context and flexibility and thus perform poorly in practice. We present ClimateAgent, an autonomous multi-agent framework that orchestrates end-to-end climate data analytic workflows. ClimateAgent decomposes user questions into executable subtasks coordinated by an Orchestrate-Agent and a Plan-Agent; acquires data via specialized Data-Agents that dynamically introspect APIs to synthesize robust download scripts; and completes analysis and reporting with a Coding-Agent that generates Python code, visualizations, and a final report with a built-in self-correction loop. To enable systematic evaluation, we introduce Climate-Agent-Bench-85, a benchmark of 85 real-world tasks spanning atmospheric rivers, drought, extreme precipitation, heat waves, sea surface temperature, and tropical cyclones. On Climate-Agent-Bench-85, ClimateAgent achieves 100% task completion and a report quality score of 8.32, outperforming GitHub Copilot (6.27) and a GPT-5 baseline (3.26). These results demonstrate that our multi-agent orchestration with dynamic API awareness and self-correcting execution substantially advances reliable, end-to-end automation for climate science analytic tasks. The source code of ClimateAgent is available at https://github.com/Relaxed-System-Lab/ClimateAgent.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
