CoMCo: Consistency-Aware Multi-Agent Coordination for Zero-Shot Cross-Modal Entity Matching
Shiqi Zhang, Weixin Zeng, Ziheng Zhang, Wenzhe Hou, Weidong Xiao, Xiang Zhao
Abstract
Entity Matching (EM) is a fundamental task in data integration, traditionally studied over structured data such as tables and knowledge graphs. In modern repositories, real-world objects are often represented across multiple modalities, including structured entities with symbolic attributes and visual entities in image-centric collections. This motivates cross-modal entity matching, which aims to identify visual-structured entity pairs that refer to the same object. Existing methods typically rely on pretrained vision-language models to compute entity pair similarity and derive correspondence via local ranking, which, however, can be unreliable given noisy and ambiguous cross-modal data and may produce globally inconsistent correspondences across related entities. Multimodal large language models (MLLMs) offer richer cross-modal cues for matching, but exhaustive MLLM reasoning over large candidate spaces is prohibitively expensive. To address these limitations, in this work, we propose øurq, a blackboard-based multi-agent framework for zero-shot cross-modal entity matching that performs iterative, self-correcting refinement by fusing multiple matching signals, explicitly regulating global consistency, and selectively invoking an MLLM only for hard cases. We further construct two new benchmarks from real-world visual and structured data. Extensive experiments show that øurq consistently outperforms competitive baselines, providing an effective solution for zero-shot cross-modal entity matching. We release our data and code at https://github.com/Q-17/CoMCo.
Ask Lune
Know where this paper stands in minutes, not an afternoon.
Lune can read the top-tier papers that cite it and the ones closest to it, and tells you what it claims, what came after and where it falls short, each point cited to the paper it comes from. No skimming, no AI slop.
Related papers
- Connecting the Dots: Training-Free Visual Grounding via Agentic ReasoningLiqin Luo, Guangyao Chen, Xiawu Zheng, Yongxing Dai et al.AAAI 2026
- CrossETR: A Semantic-Driven Framework for Entity Matching Across Images and GraphQin Yuan, Zhenyu Wen, Jiaxu Qian, Ye Yuan et al.ICDE 2025 · 1 citation
- CrossEM: A Prompt Tuning Framework for Cross-Modal Entity MatchingQin Yuan, Ye Yuan, Zhenyu Wen, Chi Chen et al.ICDE 2025 · 1 citation
- U-MERE: Unconstrained Multimodal Entity and Relation Extraction with Collaborative Modeling and Order-Sensitive OptimizationWei Jia, Li Jin, Kaiwen Wei, Yuying Shang et al.ACM MM 2025
- I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity LinkingZiyan Liu, Junwen Li, Kaiwen Li, Tong Ruan et al.ACM MM 2025 · 2 citations
