KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment

TL;DR

KARMA introduces a multi-agent LLM framework that automates knowledge graph enrichment from scientific literature, significantly increasing entity discovery and improving graph accuracy across multiple domains.

Contribution

This work presents a novel multi-agent LLM system for automated knowledge graph enrichment, integrating entity discovery, relation extraction, and conflict resolution.

Findings

Identified up to 38,230 new entities in scientific literature.

Achieved 83.1% correctness verified by LLMs.

Reduced conflict edges by 18.6% through multi-layer assessments.

Abstract

Maintaining comprehensive and up-to-date knowledge graphs (KGs) is critical for modern AI systems, but manual curation struggles to scale with the rapid growth of scientific literature. This paper presents KARMA, a novel framework employing multi-agent large language models (LLMs) to automate KG enrichment through structured analysis of unstructured text. Our approach employs nine collaborative agents, spanning entity discovery, relation extraction, schema alignment, and conflict resolution that iteratively parse documents, verify extracted knowledge, and integrate it into existing graph structures while adhering to domain-specific schema. Experiments on 1,200 PubMed articles from three different domains demonstrate the effectiveness of KARMA in knowledge graph enrichment, with the identification of up to 38,230 new entities while achieving 83.1\% LLM-verified correctness and reducing conflict edges by 18.6\% through multi-layer assessments.