DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking
DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking
Multimodal Entity Linking (MEL) aims to associate textual and visual mentions with entities in a multimodal knowledge graph. Despite its importance, current methods face challenges such as incomplete contextual information, coarse cross-modal fusion, and the difficulty of jointly large language models (LLMs) and large visual models (LVMs). To address these issues, we propose DeepMEL, a novel framework based on multi-agent collaborative reasoning, which achieves efficient alignment and disambiguation of textual and visual modalities through a role-specialized division strategy. DeepMEL integrates four specialized agents, namely Modal-Fuser, Candidate-Adapter, Entity-Clozer and Role-Orchestrator, to complete end-to-end cross-modal linking through specialized roles and dynamic coordination. DeepMEL adopts a dual-modal alignment path, and combines the fine-grained text semantics generated by the LLM with the structured image representation extracted by the LVM, significantly narrowing the modal gap. We design an adaptive iteration strategy, combines tool-based retrieval and semantic reasoning capabilities to dynamically optimize the candidate set and balance recall and precision. DeepMEL also unifies MEL tasks into a structured cloze prompt to reduce parsing complexity and enhance semantic comprehension. Extensive experiments on five public benchmark datasets demonstrate that DeepMEL achieves state-of-the-art performance, improving ACC by 1%-57%. Ablation studies verify the effectiveness of all modules.
Fang Wang、Tianwei Yan、Zonghao Yang、Minghao Hu、Jun Zhang、Zhunchen Luo、Xiaoying Bai
计算技术、计算机技术
Fang Wang,Tianwei Yan,Zonghao Yang,Minghao Hu,Jun Zhang,Zhunchen Luo,Xiaoying Bai.DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking[EB/OL].(2025-08-21)[2025-09-05].https://arxiv.org/abs/2508.15876.点此复制
评论