ScholarPulse 日报 2026-10-08

2026-10-08 学术简报：2 篇。AI代理在六小时预算内能够从真实观测数据中构建ENSO低阶随机模型，并通过重构和预测未持有年份优于已发表模型，其结构与ENSO暖冷不对称的两个竞争解释相关，这表明代理可以构建竞争性模型并揭示科学家仍争论的问题。

今日速览

序号	标题	来源	日期	主题	推荐等级
1	SciExam for ENSO: Can AI Agents Build Climate Models?	arXiv	2026-10-07	AI-Agent	高
2	LOCAA: An Agentic System for Automated Lossy Compressor Tuning	arXiv	2026-10-07	RAG	高

重点论文与技术动态

1. SciExam for ENSO: Can AI Agents Build Climate Models?

来源：arXiv
日期：2026-10-07
作者/机构：Yinling Zhang, Langchen Liu, Dongbin Xiu, Xueyan Zou, Xu Kuang, Mengdi Wang
主题标签：AI-Agent, arXiv
推荐等级：高
分类：cs.AI, cs.LG, physics.ao-ph

一句话结论

AI代理在六小时预算内能够从真实观测数据中构建ENSO低阶随机模型，并通过重构和预测未持有年份优于已发表模型，其结构与ENSO暖冷不对称的两个竞争解释相关，这表明代理可以构建竞争性模型并揭示科学家仍争论的问题。

核心内容

AI代理在六小时预算内处理观测数据，编写诊断并冻结，然后仅使用这些诊断作为反馈开发模型。
十二个代理系统中六个构建的模型在ENSO统计重构和预测上优于已发表模型。
较强模型的简化形式与ENSO暖冷不对称的两个竞争解释之一兼容。

方法与数据

摘要未明确：两个竞争解释的具体内容和未观测变量的定义。
使用真实观测数据构建低阶随机模型，并与已发表模型进行相同方式的评分测试，包括重构、预测和恢复未观测变量。

价值判断

值得关注：AI代理在科学研究中的潜力，特别是能够构建出在统计上优于人类专家模型的气候模型。
可复用点：SciExam for ENSO基准测试，可以评估代理在无已知答案的开放式科学研究中的表现。
局限/待核查：具体模型的架构细节、未观测变量的具体内容、两个解释的科学基础。

摘要

Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer, a rubric, or a language-model reviewer, none of which can tell whether a new scientific model is valid. The AI Science Exam for El Nino-Southern Oscillation (SciExam for ENSO) is a benchmark in which agents build low-order stochastic models of ENSO, the dominant mode of interannual climate variability, from real observations. Within a six-hour budget, agents process the observations, write their own diagnostics, which are then frozen, and develop a model using only these diagnostics as feedback. Hidden graders then test whether the model reproduces ENSO's statistics, recovers unobserved variables, and forecasts held-out years, and score a published model in the same way. Across twelve agent systems, six produce models that score higher than the published model, mainly through better reconstruction and forecasting. The simplified forms of the stronger models are each compatible with one of the two competing explanations of ENSO's warm-cold asymmetry, an open debate that the task never mentions. Controlled runs of the top system under varied information suggest that its scores do not come from recalling the dated observational record and that the information it receives shapes how it builds its model. SciExam for ENSO can thus evaluate agent research where no answer is known, and the results suggest that agents can already build competitive models whose structures bear on questions that scientists still debate.

2. LOCAA: An Agentic System for Automated Lossy Compressor Tuning

来源：arXiv
日期：2026-10-07
作者/机构：Khondoker Mirazul Mumenin, Dong Dai, Sheng Di, Franck Cappello, Jinzhen Wang
主题标签：RAG, arXiv
推荐等级：高
分类：cs.DC

一句话结论

LOCAA 是一个基于大语言模型的科学损失压缩自动调优代理系统，通过工具集成执行、压缩感知指导和持久内存实现压缩中的循环搜索，能够高效地为用户定义的目标和约束找到合适的压缩配置。

核心内容

LOCAA 支持用户定义的目标和约束，无需专门的搜索策略。
在固定比率压缩搜索中，LOCAA 平均需要 1.98x 更少的评估试验比二进制搜索，5.03x 比 FRaZ 少。
在多个质量约束下，LOCAA 将评估试验从 61.5 减少到 17，减少 72.4%。

方法与数据

LOCAA 使用工具集成执行、压缩感知指导和持久内存进行搜索。
评估在三个科学应用、五个压缩器和三个用例上，包括固定比率压缩、多个质量约束和质量与时间约束。

价值判断

值得关注：LOCAA 展示了工具增强的 LLM 代理在科学数据压缩调优中的潜力，能够灵活高效地处理多样化科学数据和用户目标。
可复用点：该代理方法可应用于其他科学计算任务的自动化优化。
局限/待核查：需要进一步验证在更多数据集和压缩器上的表现；持久内存的优势在多个时间步中显著。

摘要

Large-scale scientific simulations generate substantial data volumes, making lossy compression essential for reducing storage and data movement costs. However, users configure compressors through numerical error bounds (EBs) while often evaluating results using quality metrics and end-to-end performance. Because the relationship between an EB and these outcomes varies across datasets and compressors, identifying a suitable configuration typically requires exhaustive search, which can be time-consuming and computationally demanding. We present LOCAA, an Large language model-based scientific lossy compression auto-tuning agent that performs compression-in-the-loop search using tool-integrated execution, compressor-aware guidance, and persistent memory. LOCAA supports user-defined objectives and constraints without requiring a specialized search strategy. We evaluate LOCAA across three scientific applications, five compressors, and three use cases: fixed-ratio compression, compression tuning under multiple quality constraints, and compression tuning under quality and time constraints. For fixed-ratio search across twelve fields from two applications, LOCAA requires 1.98x fewer evaluation trials than binary search and 5.03x fewer than FRaZ on average. For compression ratio maximization under joint Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure constraints across six fields from the Community Earth System Model application, LOCAA reduces the average evaluation trials from 61.5 using binary search to 17, corresponding to a 72.4% reduction. Persistent memory further reduces the average number of trials by 27.9% across multiple timesteps of the same field. These results demonstrate the potential of tool-augmented LLM agents to provide flexible and efficient compressor tuning across diverse scientific data and user-defined objectives.