Towards Autonomous Graph Data Analytics with Analytics-Augmented Generation

TL;DR

This paper argues that reliable end-to-end graph data analytics cannot be achieved by retrieval- or code-generation-centric LLM agents alone and visions Analytics-Augmented Generation as a new paradigm that treats analytical computation as a first-class concern and positions LLMs as knowledge-grounded analytical coordinators.

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.

Figures (7)

• Figure 1: An example of human-centric graph data analytics and the motivation of our design.
• Figure 2: Comparison of Analytics-Augmented Generation (AAG) with existing approaches.
• Figure 3: Analytics-augmented generation overview.
• Figure 4: Hierarchical knowledge organization for efficient retrieval of massive graph algorithms.
• Figure 5: The original problem is transformed into an executable task DAG using the external knowledge base.