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

2025-08-10

AI Summary

Traditional table-to-text models struggle to capture the multi-level hierarchical structure and context-sensitive variations inherent in enterprise business reports. To address this, we propose a large language model–based multi-agent collaborative framework that decouples data slicing, difference detection, contextual modeling, and semantic generation into distinct, specialized agents. These agents coordinate via context-aware reasoning to enable cross-level trend identification and trade-off analysis. Evaluated on the Kaggle enterprise dataset, our approach achieves 83% data fidelity and an insight relevance score of 4.4/5—significantly outperforming baseline models. It demonstrates particular strength in detecting subtle business fluctuations and generating decision-grade insights, thereby advancing the state of structured data interpretation for strategic reporting.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Multiagent Systems: Modeling other Agents
• Machine Learning: Structured Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Bridging structured and unstructured data

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.

Problem

• Summarizing enterprise data across multiple dimensions
• Reasoning over hierarchical structures and context-aware deltas
• Generating decision-critical insights from complex tables

Innovation

• LLM-based multi-agent pipeline for summarization
• Context-aware reasoning over hierarchical data
• Automated variance detection and insight generation