RAAR: Retrieval Augmented Agentic Reasoning for Cross-Domain Misinformation Detection

TL;DR

RAAR introduces a retrieval-augmented, multi-agent reasoning framework that significantly improves cross-domain misinformation detection by leveraging multi-perspective evidence and systematic reasoning paths.

Contribution

It is the first framework to combine retrieval-augmented reasoning with multi-agent collaboration for cross-domain misinformation detection.

Findings

RAAR outperforms existing methods and advanced LLMs on multiple tasks.

The framework enhances reasoning and verification capabilities.

Models trained with RAAR achieve superior cross-domain generalization.

Abstract

Cross-domain misinformation detection is challenging, as misinformation arises across domains with substantial differences in knowledge and discourse. Existing methods often rely on single-perspective cues and struggle to generalize to challenging or underrepresented domains, while reasoning large language models (LLMs), though effective on complex tasks, are limited to same-distribution data. To address these gaps, we introduce RAAR, the first retrieval-augmented agentic reasoning framework for cross-domain misinformation detection. To enable cross-domain transfer beyond same-distribution assumptions, RAAR retrieves multi-perspective source-domain evidence aligned with each target sample's semantics, sentiment, and writing style. To overcome single-perspective modeling and missing systematic reasoning, RAAR constructs verifiable multi-step reasoning paths through specialized multi-agent collaboration, where perspective-specific agents produce complementary analyses and a summary agent integrates them under verifier guidance. RAAR further applies supervised fine-tuning and reinforcement learning to train a single multi-task verifier to enhance verification and reasoning capabilities. Based on RAAR, we trained the RAAR-8b and RAAR-14b models. Evaluation on three cross-domain misinformation detection tasks shows that RAAR substantially enhances the capabilities of the base models and outperforms other cross-domain methods, advanced LLMs, and LLM-based adaptation approaches. The project will be released at https://github.com/lzw108/RAAR.