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

2026-01-08

arXiv.org

AI Summary

Cross-domain misinformation detection faces significant challenges due to substantial discrepancies in knowledge and discourse across domains, as well as the limited generalization capabilities of existing approaches. This work proposes RAAR, a novel framework that uniquely integrates retrieval-augmented generation with multi-agent reasoning. RAAR retrieves multi-perspective source-domain evidence aligned in semantics, sentiment, and writing style, and constructs verifiable multi-step reasoning paths through collaborative multi-agent generation guided by a unified verifier. By transcending the assumption of identical data distributions, the framework introduces a multi-view collaborative analysis mechanism and employs supervised fine-tuning and reinforcement learning to train a multi-task verifier, yielding the RAAR-8B and RAAR-14B models. Extensive experiments demonstrate that RAAR significantly outperforms current baselines, large language models, and domain adaptation methods across three cross-domain misinformation detection tasks.

Technology Category

• Application Domains: Misinformation & Fake News
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Knowledge Representation and Reasoning: Argumentation

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Responsible Web: Mitigating misinformation and disinformation
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• cross-domain misinformation detection
• knowledge discrepancy
• discourse variation
• generalization
• distribution shift

Innovation

• retrieval-augmented reasoning
• multi-agent collaboration
• cross-domain misinformation detection
• verifiable reasoning paths
• reinforcement learning