用AI自动读论文、跑数据、自检，实现气候研究全流程自治。
CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate Science
- 结合文献检索与自动化执行，通过工具链完成气候数据分析任务。
- 在4类气候研究中实现端到端自主运行，成功率达92.3%。
- 内置多重审查机制，可识别代码漏洞与逻辑错误，适合科研团队协作使用。
第六次耦合模式比较计划（CMIP6）产生了数千篇同行评审论文，记录了模型配置、评估流程、涌现约束及投影不确定性。随着社区向CMIP7过渡，高效提取并利用这些非结构化知识与实时数据分析成为关键瓶颈。本文提出CMIP-Forge，一个融合检索增强生成（RAG）与自主分析的系统，连接科学文献与地球系统网格联邦（ESGF）数据存档。该系统整合6,581篇开放获取的CMIP6相关论文（共101,828个索引块），并通过代理式工作流，在实时气候数据上执行Python分析，同时由独立评审模型全程审计方法。CMIP-Forge采用多层纵深防御架构，通过抽象语法树（AST）静态分析、经验证的科学原语和自主对抗性同行评审协议，强制执行物理与方法学约束。我们展示了从大气遥相关、海洋动力学到区域极端事件与全球变暖预测的完整自主研究流程。基于同行评审文献、受自动代码防护限制、经独立对抗审查循环验证的代理系统，可自主完成复杂气候研究任务。相同实验暴露了审查环的具体失效模式（如阿谀奉承回归、未解决的REVISE判断、提交空代码等），均可通过不可篡改的遥测与溯源记录诊断。
原文摘要 · Abstract (English)
The Coupled Model Intercomparison Project Phase 6 (CMIP6) has generated thousands of peer-reviewed publications documenting model configurations, evaluation procedures, emergent constraints, and projection uncertainties. As the community transitions toward CMIP7, efficiently extracting and operationalizing this unstructured knowledge alongside live data analysis represents a critical bottleneck. Here we present CMIP-Forge, a hybrid retrieval-augmented generation (RAG) and autonomous analysis system that bridges the gap between scientific literature and Earth System Grid Federation (ESGF) data archives. The system pairs a curated corpus of 6,581 CMIP6-related open-access publications (101,828 indexed chunks) with an agentic pipeline in which a tool-augmented worker plans and executes Python workflows over live climate data, while a panel of independent reviewer models audits its methodology end to end. CMIP-Forge introduces a multi-layered Defense-in-Depth architecture that enforces physical and methodological invariants through executable mechanisms: Abstract Syntax Tree (AST) static analysis, audited scientific primitives, and an autonomous adversarial peer-review protocol. We demonstrate the system's capabilities through end-to-end autonomous research pipelines spanning atmospheric teleconnections, ocean dynamics, regional extremes, and global warming projections. An agentic analysis system grounded in peer-reviewed literature, constrained by automated code guardrails, and audited by an independent adversarial review loop can complete complex climate-research workflows autonomously. The same experiments expose concrete failure modes of the review loop (sycophantic regression, REVISE verdicts that are never resolved, and the submission of stub code for review), each diagnosable from the immutable telemetry and provenance record released with the article.
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。