Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification

TL;DR

SHARP is a schema-aware, training-free agent that enhances knowledge graph triple verification by combining strategic planning, active investigation, and evidence reasoning, significantly outperforming existing methods.

Contribution

The paper introduces SHARP, a novel autonomous agent that integrates internal KG structure and external evidence for reliable, interpretable triple verification without training.

Findings

SHARP achieves 4.2% and 12.9% accuracy improvements on FB15K-237 and Wikidata5M-Ind.

It provides transparent evidence chains for each verification decision.

SHARP outperforms state-of-the-art baselines in complex verification tasks.

Abstract

Knowledge Graphs (KGs) serve as a critical foundation for AI systems, yet their automated construction inevitably introduces noise, compromising data trustworthiness. Existing triple verification methods, based on graph embeddings or language models, often suffer from single-source bias by relying on either internal structural constraints or external semantic evidence, and usually follow a static inference paradigm. As a result, they struggle with complex or long-tail facts and provide limited interpretability. To address these limitations, we propose SHARP (Schema-Hybrid Agent for Reliable Prediction), a training-free autonomous agent that reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. Specifically, SHARP combines a Memory-Augmented Mechanism with Schema-Aware Strategic Planning to improve reasoning stability, and employs an enhanced ReAct loop with a Hybrid Knowledge Toolset to dynamically integrate internal KG structure and external textual evidence for cross-verification. Experiments on FB15K-237 and Wikidata5M-Ind show that SHARP significantly outperforms existing state-of-the-art baselines, achieving accuracy gains of 4.2% and 12.9%, respectively. Moreover, SHARP provides transparent, fact-based evidence chains for each judgment, demonstrating strong interpretability and robustness for complex verification tasks.