用四个智能体协作检测新闻假信息，准确率达95.3%。
MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection
- 四类智能体分工：机器学习、维基查证、连贯性检测、网页数据提取
- 集成系统准确率95.3%，F1达0.964，显著优于单个模型
- 模块化设计易扩展，决策过程可追溯，适合安全敏感场景
虚假信息在数字平台的广泛传播对信息真实性构成重大挑战。本文提出一种基于关系抽取的多智能体系统，用于检测新闻文章中的假信息，重点分析标题和短文本片段。该智能体系统由四个组件构成：(i) 机器学习代理（逻辑回归），(ii) 维基百科知识验证代理（依赖命名实体识别），(iii) 连贯性检测代理（使用大模型提示工程），(iv) 网页抓取数据解析器，用于提取关系三元组进行事实核查。系统通过模型上下文协议（MCP）协调，实现组件间共享上下文与实时学习。实验表明，多智能体集成系统达到95.3%准确率，F1分数为0.964，显著优于单一代理及传统方法。基于个体代理误分类率推导的加权聚合方法，优于算法阈值优化。模块化架构便于扩展，同时保留决策细节。
原文摘要 · Abstract (English)
The large spread of disinformation across digital platforms creates significant challenges to information integrity. This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles, focusing on titles and short text snippets. The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent (which relies on named entity recognition), (iii) a coherence detection agent (using LLM prompt engineering), and (iv) a web-scraped data analyzer that extracts relational triplets for fact checking. The system is orchestrated via the Model Context Protocol (MCP), offering shared context and live learning across components. Results demonstrate that the multi-agent ensemble achieves 95.3% accuracy with an F1 score of 0.964, significantly outperforming individual agents and traditional approaches. The weighted aggregation method, mathematically derived from individual agent misclassification rates, proves superior to algorithmic threshold optimization. The modular architecture makes the system easily scalable, while also maintaining details of the decision processes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。