RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation
For researchers and practitioners in knowledge-intensive NLP tasks, RAGA offers a more interpretable and accurate KG construction and retrieval framework, though results are preliminary and incremental.
RAGA introduces an LLM-driven agent for autonomous knowledge graph construction and retrieval-augmented generation, addressing limitations in cross-chunk relation capture and interpretability. Preliminary experiments on QASPER show fusion retrieval outperforms zero-shot baselines, with KG integration improving answer and evidence quality.
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.