arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.18320cs.AIeess.SP
收藏

利用 LLM 智能体实现 SASP 问题的自动化优化建模:一种基于 Graph-RAG 的方法

Leveraging LLM Agents for Automated Optimization Modeling for SASP Problems: A Graph-RAG based Approach

Shenzhen Research Institute of Big Data(深圳大数据研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

Tianpeng Pan, Wenqiang Pu, Licheng Zhao, Rui Zhou

AI总结:

针对LLM在传感器阵列信号处理领域缺乏领域知识导致自动化优化建模效果差的问题,提出基于多智能体和Graph-RAG的MAG-RAG方法,有效匹配领域知识并超越现有基准。

摘要:

随着大型语言模型(LLMs)的快速发展,自动化优化建模(AOM)引起了广泛关注。现有方法主要依赖于提示工程,利用精心设计的专家响应链或结构化指导。然而,由于缺乏特定领域知识,基于提示的技术在传感器阵列信号处理(SASP)领域表现不佳。为了解决这一问题,我们提出了一种基于检索增强生成(RAG)技术的自动化建模方法,该方法包含两个主要组件:多智能体(MA)结构和基于图的 RAG(Graph-RAG)过程。MA 结构专为架构 AOM 过程而定制,每个智能体均基于人类建模程序的原则进行设计。Graph-RAG 过程用于将用户查询与特定的 SASP 建模知识相匹配,从而增强建模结果。在十个经典信号处理问题上的结果表明,所提出的方法(称为 MAG-RAG)优于多个 AOM 基准。

英文摘要:

Automated optimization modeling (AOM) has evoked considerable interest with the rapid evolution of large language models (LLMs). Existing approaches predominantly rely on prompt engineering, utilizing meticulously designed expert response chains or structured guidance. However, prompt-based techniques have failed to perform well in the sensor array signal processing (SASP) area due the lack of specific domain knowledge. To address this issue, we propose an automated modeling approach based on retrieval-augmented generation (RAG) technique, which consists of two principal components: a multi-agent (MA) structure and a graph-based RAG (Graph-RAG) process. The MA structure is tailored for the architectural AOM process, with each agent being designed based on principles of human modeling procedure. The Graph-RAG process serves to match user query with specific SASP modeling knowledge, thereby enhancing the modeling result. Results on ten classical signal processing problems demonstrate that the proposed approach (termed as MAG-RAG) outperforms several AOM benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑