AI加速气候科学评估，但专家把关不可或缺
AI-Assisted Scientific Assessment: A Case Study on Climate Change
- 用AI辅助协同写作，通过反复迭代优化报告
- 13位专家46小时完成79篇文献综述，104轮修订
- AI生成内容多被保留，但需专家提升质量与逻辑
新兴的AI协作者范式聚焦可重复验证的任务，其代理在‘试错’循环中探索搜索空间。然而，该范式不适用于无法重复评估、且真实情况依赖理论与现有证据共识合成的问题。我们评估了一个基于Gemini的AI环境，将其集成至标准科研工作流。在13位气候科学领域的科学家协作下，测试了该系统在大西洋经向翻转环流（AMOC）稳定性这一复杂议题上的表现。结果表明，AI能显著加速科研流程：团队在46人时内完成79篇论文的综合分析，经历104轮修订。AI贡献显著，多数生成内容保留在报告中，并帮助维持逻辑一致性和呈现质量。但专家补充至关重要：报告不足一半由AI生成。此外，仍需大量人工审校以拓展内容并达到严谨科学标准。
原文摘要 · Abstract (English)
The emerging paradigm of AI co-scientists focuses on tasks characterized by repeatable verification, where agents explore search spaces in 'guess and check' loops. This paradigm does not extend to problems where repeated evaluation is impossible and ground truth is established by the consensus synthesis of theory and existing evidence. We evaluate a Gemini-based AI environment designed to support collaborative scientific assessment, integrated into a standard scientific workflow. In collaboration with a diverse group of 13 scientists working in the field of climate science, we tested the system on a complex topic: the stability of the Atlantic Meridional Overturning Circulation (AMOC). Our results show that AI can accelerate the scientific workflow. The group produced a comprehensive synthesis of 79 papers through 104 revision cycles in just over 46 person-hours. AI contribution was significant: most AI-generated content was retained in the report. AI also helped maintain logical consistency and presentation quality. However, expert additions were crucial to ensure its acceptability: less than half of the report was produced by AI. Furthermore, substantial oversight was required to expand and elevate the content to rigorous scientific standards.
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。