Towards Autonomous Graph Data Analytics with Analytics-Augmented Generation

2026-02-25

AI Summary

This work proposes a novel paradigm termed Analysis-Augmented Generation (AAG) to address the limitations of existing large language model (LLM)-based approaches for graph data analysis, which often lack explicit modeling of analytical tasks and struggle to reliably translate user intent expressed in natural language into executable and interpretable analysis pipelines. AAG elevates analytical computation to a first-class citizen by introducing an LLM-guided analysis orchestrator that integrates knowledge-driven task planning, algorithm-aware LLM–analysis interaction, and task-adaptive graph construction. This end-to-end automated framework significantly enhances both the efficiency and interpretability of translating natural language queries into trustworthy graph analytics, thereby enabling non-expert users to effectively perform complex graph analysis tasks.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

This paper argues that reliable end-to-end graph data analytics cannot be achieved by retrieval- or code-generation-centric LLM agents alone. Although large language models (LLMs) provide strong reasoning capabilities, practical graph analytics for non-expert users requires explicit analytical grounding to support intent-to-execution translation, task-aware graph construction, and reliable execution across diverse graph algorithms. We envision Analytics-Augmented Generation (AAG) as a new paradigm that treats analytical computation as a first-class concern and positions LLMs as knowledge-grounded analytical coordinators. By integrating knowledge-driven task planning, algorithm-centric LLM-analytics interaction, and task-aware graph construction, AAG enables end-to-end graph analytics pipelines that translate natural-language user intent into automated execution and interpretable results.

Problem

• graph data analytics
• large language models
• intent-to-execution translation
• task-aware graph construction
• autonomous analytics

Innovation

• Analytics-Augmented Generation
• graph data analytics
• large language models
• task-aware graph construction
• algorithm-centric interaction