RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation

TL;DR

RAGA is an autonomous framework that combines LLMs with graph-building capabilities to improve knowledge graph construction and retrieval, emphasizing provenance, interpretability, and high-stakes domain reliability.

Contribution

It introduces a novel LLM-based agent with a full lifecycle KG toolkit, a hybrid retrieval mechanism, and provenance verification, advancing autonomous knowledge graph construction.

Findings

RAGA's fusion retrieval outperforms zero-shot baselines.

KG integration improves answer and evidence quality.

The framework offers a reference for autonomous KG construction.

Abstract

Existing LLM-driven knowledge graph (KG) construction methods predominantly employ stateless batch processing pipelines, exhibiting structural deficiencies in cross-chunk semantic relation capture, entity disambiguation, and construction process interpretability. These limitations undermine KG quality, retrieval precision, and deployment trust in high-stakes domains. We propose RAGA (Reading And Graph-building Agent), an LLM-based autonomous KG construction and retrieval fusion framework. RAGA provides an atomic toolset supporting full KG lifecycle CRUD operations and embeds a Read-Search-Verify-Construct cognitive constraint into a ReAct tool loop. A KG-vector synchronization mechanism enables hybrid symbolic-vector retrieval, while evidence-anchored verification links every knowledge entry to its source text for auditable provenance. Preliminary experiments on a subset of the QASPER scientific QA dataset indicate that RAGA's fusion retrieval outperforms zero-shot baselines, with KG integration providing measurable gains in both answer and evidence quality. The framework design and experimental baseline serve as a reference for agent-driven autonomous KG construction.