EA-Agent: A Structured Multi-Step Reasoning Agent for Entity Alignment

2026-04-13

AI Summary

This work addresses the limitations of traditional entity alignment methods under noisy or weakly supervised settings and the poor interpretability and high inference costs of existing large language model (LLM)-based approaches. It introduces, for the first time, a structured multi-step reasoning agent into the entity alignment task. The proposed framework employs a plan-and-execute mechanism to yield interpretable alignment decisions and incorporates attribute- and relation-based triple selectors to pre-filter redundant information, thereby enhancing computational efficiency. By integrating LLMs, multi-step reasoning, triple selection, and knowledge graph representation learning, the method achieves state-of-the-art performance across three benchmark datasets while simultaneously ensuring interpretability and computational efficiency, thus overcoming the black-box limitations commonly associated with LLM applications.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Natural Language Processing: Information Extraction
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Entity alignment (EA) aims to identify entities across different knowledge graphs (KGs) that refer to the same real-world object and plays a critical role in knowledge fusion and integration. Traditional EA methods mainly rely on knowledge representation learning, but their performance is often limited under noisy or sparsely supervised scenarios. Recently, large language models (LLMs) have been introduced to EA and achieved notable improvements by leveraging rich semantic knowledge. However, existing LLM-based EA approaches typically treat LLMs as black-box decision makers, resulting in limited interpretability, and the direct use of large-scale triples substantially increases inference cost. To address these challenges, we propose \textbf{EA-Agent}, a reasoning-driven agent for EA. EA-Agent formulates EA as a structured reasoning process with multi-step planning and execution, enabling interpretable alignment decisions. Within this process, it introduces attribute and relation triple selectors to filter redundant triples before feeding them into the LLM, effectively addressing efficiency challenges. Experimental results on three benchmark datasets demonstrate that EA-Agent consistently outperforms existing EA methods and achieves state-of-the-art performance. The source code is available at https://github.com/YXNan0110/EA-Agent.

Problem

• Entity Alignment
• Knowledge Graph
• Large Language Models
• Interpretability
• Inference Efficiency

Innovation

• Entity Alignment
• Large Language Models
• Multi-step Reasoning
• Interpretable AI
• Triple Filtering