MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection

2025-08-13

AI Summary

To address the proliferation of misinformation on digital platforms and the inefficiency of fact-checking short textual content—particularly news headlines—this paper proposes a Model Context Protocol (MCP)-driven multi-agent collaborative detection framework. The framework integrates named entity recognition, logistic regression, large language model prompt engineering, web crawling, and relation triple extraction, with MCP enabling shared contextual awareness and dynamic cooperative learning among modules. Crucially, it introduces a misclassification-rate-driven weighted fusion strategy, replacing conventional threshold-based optimization. Experimental results demonstrate an accuracy of 95.3% and an F1-score of 0.964—substantially outperforming single-agent baselines and state-of-the-art methods. The framework exhibits high scalability, robustness against adversarial inputs, and transparent, interpretable decision-making, making it suitable for real-world deployment in automated fact-checking systems.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Multiagent Systems: Adversarial Agents
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• Detects disinformation in news articles using multi-agent system
• Combines relation extraction and fact-checking for accuracy
• Improves detection via modular, scalable AI ensemble approach

Innovation

• Multi-agent system for disinformation detection
• Relation extraction and LLM prompt engineering
• Model Context Protocol for shared learning