发表机构
University of North Carolina at Charlotte; University of Delaware; Argonne National Laboratory（北卡罗来纳大学夏洛特分校; 特拉华大学; 阿贡国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
LOCAA是基于大语言模型的智能体系统，通过工具集成搜索和持久记忆，自动为科学数据调优有损压缩器，在多个应用和约束下显著减少评估试验次数，提升调优效率。
AI 中文摘要
大规模科学模拟会产生大量数据，使得有损压缩对于降低存储和数据移动成本至关重要。然而，用户通过数值误差界（EB）配置压缩器，却常常使用质量指标和端到端性能来评估结果。由于误差界与这些结果之间的关系因数据集和压缩器而异，确定合适的配置通常需要穷举搜索，这可能耗时且计算量大。我们提出了LOCAA，一个基于大语言模型的科学有损压缩自动调优智能体，它通过工具集成执行、压缩器感知指导和持久记忆执行压缩在环搜索。LOCAA支持用户定义的目标和约束，无需专门的搜索策略。我们在三个科学应用、五个压缩器和三个用例中评估了LOCAA：固定比率压缩、多质量约束下的压缩调优，以及质量和时间约束下的压缩调优。对于来自两个应用的十二个字段的固定比率搜索，LOCAA平均需要的评估试验次数比二分搜索少1.98倍，比FRaZ少5.03倍。在社区地球系统模型应用的六个字段上，在联合峰值信噪比（PSNR）和结构相似性指数度量约束下最大化压缩比时，LOCAA将平均评估试验次数从使用二分搜索的61.5次减少到17次，对应减少了72.4%。持久记忆进一步将同一字段多个时间步的平均试验次数减少了27.9%。这些结果展示了工具增强的大语言模型智能体在多样科学数据和用户定义目标下提供灵活高效压缩器调优的潜力。
英文摘要
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.
