LiveGraph: A Compound AI System for Evolving Knowledge Graph Construction from Streaming Data

Abstract

Constructing knowledge graphs from streaming data requires coordinating LLMs, embedding models, graph databases, and domain adapters—yet existing systems compose these components through ad-hoc interfaces, making them brittle to component changes and opaque to debugging. We present LiveGraph, a compound AI system that orchestrates these heterogeneous components through a formal graph evolution operator algebra comprising five atomic operators (AddNode, AddEdge, MergeEntity, UpdateRelation, ExpireEdge) with inverses enabling full rollback and operator logs enabling component-level error attribution. The algebra serves as the compositional interface: LLMs produce candidate extractions, embedding models retrieve resolution candidates, and the storage backend applies operators atomically—all through the same shared operator vocabulary. The resulting graph serves as a reasoning substrate—graph traversal discovers multi-hop relational paths unavailable to flat retrieval, and temporal validity windows enable time-aware querying over the evolution history. We evaluate on three domains—meeting conversations (AMI), geopolitical events (ICEWS18), and Wikipedia editor interactions—verifying that the operator algebra enforces temporal coherence (S𝐶 = 1.0) across all three. On downstream QA, graph-augmented retrieval from LiveGraph’s graphs achieves 51% accuracy vs. 29% for Microsoft GraphRAG and 2% for vector retrieval, with the largest gains on temporal (+40pp) and multi-hop (+20pp) questions. The modular architecture enables systematic component evaluation through swappable interfaces and dual storage backends (NetworkX, Neo4j).