PAMAS: Self-Adaptive Multi-Agent System with Perspective Aggregation for Misinformation Detection

TL;DR

PAMAS introduces a self-adaptive multi-agent framework with perspective aggregation to improve misinformation detection by highlighting anomalies and reducing bias from overwhelming truthful content.

Contribution

The paper proposes PAMAS, a novel multi-agent system with hierarchical perspective aggregation and self-adaptive mechanisms for scalable and accurate misinformation detection.

Findings

Achieves superior accuracy on benchmark datasets.

Enhances efficiency through dynamic topology optimization.

Effectively mitigates information drowning in social media data.

Abstract

Misinformation on social media poses a critical threat to information credibility, as its diverse and context-dependent nature complicates detection. Large language model-empowered multi-agent systems (MAS) present a promising paradigm that enables cooperative reasoning and collective intelligence to combat this threat. However, conventional MAS suffer from an information-drowning problem, where abundant truthful content overwhelms sparse and weak deceptive cues. With full input access, agents tend to focus on dominant patterns, and inter-agent communication further amplifies this bias. To tackle this issue, we propose PAMAS, a multi-agent framework with perspective aggregation, which employs hierarchical, perspective-aware aggregation to highlight anomaly cues and alleviate information drowning. PAMAS organizes agents into three roles: Auditors, Coordinators, and a Decision-Maker. Auditors capture anomaly cues from specialized feature subsets; Coordinators aggregate their perspectives to enhance coverage while maintaining diversity; and the Decision-Maker, equipped with evolving memory and full contextual access, synthesizes all subordinate insights to produce the final judgment. Furthermore, to improve efficiency in multi-agent collaboration, PAMAS incorporates self-adaptive mechanisms for dynamic topology optimization and routing-based inference, enhancing both efficiency and scalability. Extensive experiments on multiple benchmark datasets demonstrate that PAMAS achieves superior accuracy and efficiency, offering a scalable and trustworthy way for misinformation detection.