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 2508.07186cs.AIcs.MA
收藏

基于企业表格上下文感知推理的多维摘要智能体

Multi-Dimensional Summarization Agents with Context-Aware Reasoning over Enterprise Tables

Amazon(亚马逊)

Amit Dhanda

AI总结:

提出基于LLM的多智能体框架,通过切片、差异检测、上下文构建与生成实现企业表格多维摘要,在忠实度、相关性与洞察质量上显著优于基线方法。

摘要:

我们提出了一种新颖的框架,使用基于大语言模型(LLM)的智能体跨多个维度总结结构化企业数据。传统的表转文本模型通常缺乏跨层次结构和上下文感知增量进行推理的能力,而这些在业务报告任务中至关重要。我们的方法引入了多智能体流水线,通过切片、差异检测、上下文构建和基于LLM的生成等智能体来提取、分析和总结多维数据。结果显示,该框架优于传统方法,实现了83%的底层数据忠实度,对重大变化的覆盖更优,且在决策关键洞察上获得高相关性评分(4.4/5)。在涉及细微权衡的类别中改进尤为显著,例如在单位销量下降时因价格变动导致收入增加,竞争方法要么忽略,要么仅有限地处理。我们在Kaggle数据集上评估了该框架,并在忠实度、相关性和洞察质量上相比基线表摘要方法展现出显著提升。

英文摘要:

We propose a novel framework for summarizing structured enterprise data across multiple dimensions using large language model (LLM)-based agents. Traditional table-to-text models often lack the capacity to reason across hierarchical structures and context-aware deltas, which are essential in business reporting tasks. Our method introduces a multi-agent pipeline that extracts, analyzes, and summarizes multi-dimensional data using agents for slicing, variance detection, context construction, and LLM-based generation. Our results show that the proposed framework outperforms traditional approaches, achieving 83\% faithfulness to underlying data, superior coverage of significant changes, and high relevance scores (4.4/5) for decision-critical insights. The improvements are especially pronounced in categories involving subtle trade-offs, such as increased revenue due to price changes amid declining unit volumes, which competing methods either overlook or address with limited specificity. We evaluate the framework on Kaggle datasets and demonstrate significant improvements in faithfulness, relevance, and insight quality over baseline table summarization approaches.

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。

↑