arXiv:2605.17856cs.AI2026-05

构建可被智能体使用的科学模拟知识框架,降低地球科学建模门槛。

KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science

论文配图:KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science
图 1 · 摘自论文原文
  • 将专家经验转化为可执行的模型操作与诊断机制。
  • 智能体使用该框架后成功完成模拟比例达84%,未使用则低于40%。
  • 支持跨领域通用,适合非专业用户和科研协作场景。

过程驱动的模拟模型承载了地球科学数十年的科学认知,但最易受气候风险与资源短缺影响的群体却最难以使用。本文提出知识基础设施(KI),一种可供智能体调用的架构,将专业知识外化为经验证的建模算子、分阶段领域协议与诊断恢复机制。在3,000次耦合水文基准测试中,配备KI的智能体在84%的试验中生成了物理上合理且可验证的端到端模拟,而未使用KI的智能体成功率不足40%。KI具备跨学科泛化能力,其构建被封装为知识解构工具包(KDT),可自动生成117个额外过程模型的KI,覆盖14个地球科学领域。所有119个KI虽基于不同物理机制,但建模决策与故障修复策略趋于一致,表明操作性知识具有结构性而非随机性。演示显示,配备KI的智能体同时降低了非专业人士获取模拟工具的门槛与不同建模社区间的集成壁垒。通过这一架构,过程驱动科学可演变为一个可被需要者响应、可由贡献者扩展的活态科学公共资源。

原文摘要 · Abstract (English)

Process-based simulation models encode decades of scientific understanding across the Earth sciences, yet the communities most exposed to climate risk and resource scarcity are the least able to use them. Here, we introduce knowledge infrastructure (KI), an agent-actionable scaffold that externalizes expertise into validated modelling operators, staged domain protocols, and diagnostic recovery mechanisms. Across a 3,000-trial coupled-hydrology benchmark, agents equipped with KI produced physically plausible, verifiable end-to-end simulations in up to 84% of trials, while agents without KI plateaued below 40%. KI generalizes across disciplines. We packaged its construction into a Knowledge Dissection Toolkit (KDT) that autonomously produced KI enabling end-to-end agent execution of 117 additional process-based models across 14 Earth-science domains. Across all 119 KIs, modelling decisions and failure remedies converged despite different underlying physics, showing that operational expertise is structured and extractable rather than ad hoc. Demonstrations show KI-equipped agents lowering both the access barrier between non-specialist users and process-based simulation, and the integration barrier between modelling communities. Through this scaffold, process-based science can then evolve as a living scientific commons, answerable to whoever needs to know and extendable by whoever can contribute.

科学模拟智能体知识框架地球科学

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。