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

• URL: http://arxiv.org/abs/2604.11686v1
• Date: Mon, 13 Apr 2026 16:30:08 GMT
• Title: EA-Agent: A Structured Multi-Step Reasoning Agent for Entity Alignment
• Abstract summary: We propose textbfEA-Agent, a reasoning-driven agent for entity alignment (EA)<n> EA-Agent formulates EA as a structured reasoning process with multi-step planning and execution, enabling interpretable alignment decisions.<n> Experimental results on three benchmark datasets demonstrate that EA-Agent consistently outperforms existing EA methods.
• Score: 18.328937183667396
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments [60.3427704389541]
  Large Language Models are being increasingly deployed as the decision-making core of autonomous agents.<n>Yet, in conversational benchmarks, these agents frequently fail due to the cascading effects of incorrect decision-making.<n>We present the Failure-Aware Meta-Agentic framework to tackle these challenges.
  arXiv  Detail & Related papers  (2026-04-28T02:21:53Z)
• Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate [13.025981335381637]
  We propose AgentEA, a reliable EA framework based on multi-agent debate.<n>AgentEA improves embedding quality through entity representation preference optimization.<n>It then introduces a two-stage multi-role debate mechanism consisting of lightweight debate verification and deep debate alignment.
  arXiv  Detail & Related papers  (2026-04-15T06:54:27Z)
• Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition [51.68340973140949]
  Multimodal Named Entity Recognition (GMNER) aims to extract text-based entities, assign them semantic categories, and ground them to corresponding visual regions.<n> MLLMs exhibit $textbfmodality bias$, including visual bias and textual bias, which stems from their tendency to take unimodal shortcuts.<n>We propose Modality-aware Consistency Reasoning ($bfMCR$), which enforces structured cross-modal reasoning.
  arXiv  Detail & Related papers  (2026-02-04T12:12:49Z)
• AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress [71.02263260394261]
  Large language models (LLMs) still encounter challenges in multi-turn decision-making tasks.<n>We build process reward models (PRMs) to evaluate each decision and guide the agent's decision-making process.<n>AgentPRM captures both the interdependence between sequential decisions and their contribution to the final goal.
  arXiv  Detail & Related papers  (2025-11-11T14:57:54Z)
• Think Then Embed: Generative Context Improves Multimodal Embedding [51.76690812535934]
  We propose a Think-Then-Embed (TTE) framework for Universal Multimodal Embeddings (UME), composed of a reasoner and an embedder.<n>By leveraging a powerful MLLM reasoner, we achieve state-of-the-art performance on the MMEB-V2 benchmark, surpassing proprietary models trained on massive in-house datasets.
  arXiv  Detail & Related papers  (2025-10-06T16:53:56Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• LLM-Align: Utilizing Large Language Models for Entity Alignment in Knowledge Graphs [22.621781704528786]
  Embedding-based entity alignment (EA) has recently gained considerable attention.<n>EA seeks to identify and match corresponding entities across different Knowledge Graphs (KGs)
  arXiv  Detail & Related papers  (2024-12-06T01:05:37Z)
• Entity Alignment with Noisy Annotations from Large Language Models [15.189701951003611]
  We propose a unified framework, LLM4EA, to effectively leverage Large Language Models for EA. Specifically, we design a novel active learning policy to significantly reduce the annotation space. We iteratively optimize the policy based on the feedback from a base EA model.
  arXiv  Detail & Related papers  (2024-05-27T03:52:55Z)
• Unlocking the Power of Large Language Models for Entity Alignment [29.628079581217374]
  ChatEA is an innovative framework that incorporates large language models (LLMs) to improve EA. To address the constraints of limited input KG data, ChatEA introduces a KG-code translation module. To overcome the over-reliance on entity embedding comparisons, ChatEA implements a two-stage EA strategy.
  arXiv  Detail & Related papers  (2024-02-23T01:55:35Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• High-quality Task Division for Large-scale Entity Alignment [28.001266850114643]
  DivEA achieves higher EA performance than alternative state-of-the-art solutions. We devise a counterpart discovery method that exploits the locality principle of the EA task and the power of trained EA models.
  arXiv  Detail & Related papers  (2022-08-22T14:46:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.