{"slug": "remmd-realistic-multilingual-multi-image-agentic-verification-for-multimodal", "title": "ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection", "summary": "Researchers introduced ReMMD, a framework for realistic multilingual multi-image agentic verification to detect multimodal misinformation. The framework includes a benchmark with 500 samples and 2,756 images across five languages, and an agent that achieves 41.80% accuracy and 39.12% macro-F1 using GPT-5.2 while reducing costs by up to 79.9% compared to existing methods.", "body_md": "arXiv:2606.24112v1 Announce Type: new\nAbstract: Multimodal misinformation detection is increasingly important because viral posts now combine long multilingual narratives, several images, mixed provenance, and subtle text--image framing errors. Existing benchmarks and methods remain poorly matched to this setting: they usually isolate short captions, single images, binary labels, or one manipulation source, while agentic verification remains costly under realistic evidence search. We present ReMMD, a realistic multilingual multi-image agentic verification framework for multimodal misinformation detection. ReMMD includes ReMMDBench, a real-world multimodal misinformation detection benchmark with 500 samples, 2,756 images, five monolingual languages, two cross-lingual settings, three text-length tiers, multi-image posts, five-way veracity labels, eight distortion labels, evidence provenance, and rationales. It also includes ReMMD-Agent, a persistent-memory verifier that decomposes posts into atomic points, builds a reusable evidence set, and predicts structured L1/L2/L3 outputs. Across proprietary systems, open LVLMs, MMD-Agent, and T2-Agent, ReMMD-Agent obtains the best five-way veracity performance, with 41.80% accuracy and 39.12% macro-F1 using GPT-5.2, while reducing cost by 17.5% relative to MMD-Agent and 79.9% relative to T2-Agent. The project is available at https://dang-ai.github.io/ReMMD.", "url": "https://wpnews.pro/news/remmd-realistic-multilingual-multi-image-agentic-verification-for-multimodal", "canonical_source": "https://arxiv.org/abs/2606.24112", "published_at": "2026-06-24 04:00:00+00:00", "updated_at": "2026-06-24 04:30:35.519214+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "computer-vision", "ai-research", "ai-agents"], "entities": ["ReMMD", "ReMMDBench", "ReMMD-Agent", "GPT-5.2", "MMD-Agent", "T2-Agent", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/remmd-realistic-multilingual-multi-image-agentic-verification-for-multimodal", "markdown": "https://wpnews.pro/news/remmd-realistic-multilingual-multi-image-agentic-verification-for-multimodal.md", "text": "https://wpnews.pro/news/remmd-realistic-multilingual-multi-image-agentic-verification-for-multimodal.txt", "jsonld": "https://wpnews.pro/news/remmd-realistic-multilingual-multi-image-agentic-verification-for-multimodal.jsonld"}}