发表机构
University of Maryland（马里兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对智能体知识图谱缺乏管控的问题，提出多智能体框架MAGG构建受管控知识图谱，在SciERC、MuSiQue等数据集上显著提升三元组抽取性能与问答效果。
AI 中文摘要
智能体系统使用的知识图谱常被视为抽取三元组的扁平存储，几乎不记录事实归属主体、准入原因或下游使用方式。本文认为可靠的智能体知识系统需将管控作为图谱构建的必要组件以填补该空白，提出MAGG——一种用于构建受管控知识图谱的原则性多智能体框架，该框架引入明确的管控决策以实现可靠可信的知识共享。领域分类器首先直接从文档内容中诱导实体与关系类型，支持开放世界设置下无固定模式运行；候选三元组被分配给领域所有者，经依据支撑证据评审、通过管控决策准入后，以审计元数据存储。问答阶段复用相同的所有权结构，查询被路由至特定领域的图谱专家，而非通过无差异检索回答。评估显示MAGG的有效性：在SciERC数据集上，MAGG较扁平插入方法将严格三元组F1提升47%，映射三元组F1提升51%；对120个三元组的盲审发现，仅受管控的三元组更常具备来源支撑，经修订的三元组100%有支撑；在MuSiQue数据集上，MAGG较Microsoft GraphRAG在精确匹配指标上高出9.0个百分点，在令牌F1指标上高出11.2个百分点。
英文摘要
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.
Comments23 pages total, 10 pages main text, 12 pages of appendix, 2 figures, 6 tables
