AgREE: Agentic Reasoning for Knowledge Graph Completion on Emerging Entities

2025-08-06

AI Summary

Open-domain knowledge graph completion (KGC) faces critical challenges in handling emerging entities—namely, information scarcity, high dynamism, and severe label sparsity—rendering existing supervised methods ineffective for cold-start entities. To address this, we propose AgREE, the first agent-based zero-shot KGC framework specifically designed for emerging entities. AgREE integrates multi-step retrieval-reasoning coordination, dynamic knowledge tracking, and large language model–driven logical inference, enabling fully autonomous construction of knowledge triples for unseen emerging entities without any training. We introduce the first dedicated benchmark for emerging-entity evaluation and propose a novel assessment protocol grounded in real-world emergence dynamics. Experiments demonstrate that AgREE achieves state-of-the-art zero-shot performance on unseen emerging entities—outperforming prior methods by up to 13.7%—while incurring zero training cost, thereby overcoming a fundamental bottleneck in modeling novel entities within traditional KGC paradigms.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

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

Open-domain Knowledge Graph Completion (KGC) faces significant challenges in an ever-changing world, especially when considering the continual emergence of new entities in daily news. Existing approaches for KGC mainly rely on pretrained language models' parametric knowledge, pre-constructed queries, or single-step retrieval, typically requiring substantial supervision and training data. Even so, they often fail to capture comprehensive and up-to-date information about unpopular and/or emerging entities. To this end, we introduce Agentic Reasoning for Emerging Entities (AgREE), a novel agent-based framework that combines iterative retrieval actions and multi-step reasoning to dynamically construct rich knowledge graph triplets. Experiments show that, despite requiring zero training efforts, AgREE significantly outperforms existing methods in constructing knowledge graph triplets, especially for emerging entities that were not seen during language models' training processes, outperforming previous methods by up to 13.7%. Moreover, we propose a new evaluation methodology that addresses a fundamental weakness of existing setups and a new benchmark for KGC on emerging entities. Our work demonstrates the effectiveness of combining agent-based reasoning with strategic information retrieval for maintaining up-to-date knowledge graphs in dynamic information environments.

Problem

• Addresses challenges in Knowledge Graph Completion for emerging entities
• Overcomes limitations of existing methods needing extensive supervision
• Enhances dynamic triplet construction with agent-based reasoning

Innovation

• Agent-based framework for dynamic knowledge construction
• Iterative retrieval and multi-step reasoning combined
• Zero training outperforms existing methods significantly