From Extraction to Governed Memory: Multi-Agent Knowledge Graph Construction with Domain-Expert Review
Summary
The paper proposes MAGG, a multi-agent framework for constructing governed knowledge graphs with domain-expert review, improving knowledge extraction and question-answering performance over methods like Microsoft GraphRAG.
View Cached Full Text
Cached at: 09/01/26, 12:37 PM
# From Extraction to Governed Memory: Multi-Agent Knowledge Graph Construction with Domain-Expert Review Source: [https://arxiv.org/abs/2608.28642](https://arxiv.org/abs/2608.28642) [View PDF](https://arxiv.org/pdf/2608.28642) > Abstract:Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with little record of who owns a fact, why it was admitted, or how it should be used downstream\. We argue that reliable agentic knowledge systems require governance as an essential component of graph construction to bridge this gap\. We propose MAGG, a principled multi\-agent framework for constructing Governed Knowledge Graphs that introduces explicit governance decisions for reliable and trustworthy knowledge sharing\. A domain classifier first induces entity and relation types directly from document content, enabling operation in open\-world settings without fixed schemas\. Candidate triples are assigned to domain owners, reviewed against supporting evidence, admitted through governance decisions, and stored with audit metadata\. The same ownership structure is reused during question answering, where queries are routed to domain\-specific graph experts rather than answered through undifferentiated retrieval\. Our evaluation demonstrates MAGG's effectiveness: On SciERC, MAGG improves strict triple F1 by 47% and mapped triple F1 by 51% over flat insertion\. A blinded review of 120 triples finds governed\-only triples more often source\-supported than flat\-only ones, and revised triples supported in 100% of cases\. Finally, on MuSiQue, MAGG outperforms Microsoft GraphRAG by 9\.0 exact\-match points and 11\.2 token\-F1 points\. ## Submission history From: Faizan Wajid \[[view email](https://arxiv.org/show-email/c4be2996/2608.28642)\] **\[v1\]**Wed, 12 Aug 2026 01:45:23 UTC \(1,341 KB\)
Similar Articles
RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation
RAGA is an LLM-driven autonomous agent that constructs knowledge graphs via a read-search-verify-construct cognitive loop and integrates hybrid symbolic-vector retrieval for retrieval-augmented generation, with experimental gains on scientific QA datasets.
Building Agentic GraphRAG Systems: From knowledge graphs and ontologies to a unified memory as an MCP server for your AI agent.
The author argues that GraphRAG is fundamentally a data modeling problem rather than just a retrieval algorithm, proposing a five-component architecture using ontologies, knowledge graphs, and an MCP server for unified agent memory.
AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge Graphs
Proposes AgentKGV, an agentic LLM-RAG framework with two-stage training (distillation SFT and trajectory-level GRPO) for verifying facts in knowledge graphs, achieving significant improvements on the T-REx benchmark while reducing retrieval calls.
SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation
SelfGraphRAG introduces a framework that generates synthetic question-answer pairs from knowledge graphs to address the supervision gap in graph-based retrieval-augmented generation, enhancing retrieval precision and reasoning performance.
@pauliusztin_: I spent months optimizing GraphRAG retrieval. But it turned out I was optimizing the wrong thing.... The biggest knowle…
A detailed guide on optimizing knowledge graph ingestion for AI agents, presenting a five-step pipeline (extraction, resolution, embedding, deduplication, routing) to prevent graph corruption and improve retrieval quality.