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

TL;DR

This paper introduces a multi-agent framework leveraging large language models to generate accurate, context-aware summaries of multi-dimensional enterprise data, improving over traditional table-to-text methods especially in complex trade-off scenarios.

Contribution

The paper presents a novel multi-agent pipeline that enhances data reasoning and summarization capabilities over hierarchical enterprise tables using LLMs, addressing limitations of existing models.

Findings

Achieves 83% faithfulness to data

Scores 4.4/5 on relevance

Outperforms baseline methods in insight quality

Abstract

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.