Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection

2026-09-16

AI Summary

为解决假新闻检测中信息过载和模态不匹配问题，提出MAGER框架自动发现优化的元路径，并结合图上下文学习策略，提高冻结大语言模型的推理能力。

Abstract

Propagation structures provide crucial evidence for fake news detection, yet existing approaches primarily rely on supervised GNN-based models, which require substantial labeled data and exhibit limited generalization. Although large language models (LLMs) exhibit strong reasoning capabilities, directly feeding them raw propagation graphs creates a significant modality mismatch and severe information overload, making structure-aware reasoning unreliable in zero-shot and few-shot settings. To bridge this gap, we propose MAGER, a multi-agent genetic evolution framework that automatically discovers meta-paths optimized for LLM reasoning. By compressing complex propagation graphs into informative subgraphs, the evolved meta-paths alleviate both information overload and modality mismatch, enabling frozen LLMs to perform structure-aware veracity reasoning. We further introduce a graph in-context learning strategy that retrieves semantically and structurally similar demonstrations to strengthen classification and reasoning. Extensive experiments show that MAGER substantially improves frozen LLMs as standalone fake news detectors in data-efficient settings. Our code is available at https://github.com/SenticNet/MAGER.

Problem

• fake news detection
• propagation structures
• large language models
• information overload
• modality mismatch

Innovation

• multi-agent genetic evolution
• meta-path discovery
• structure-aware reasoning
• frozen LLMs
• graph in-context learning