[2604.04190] Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification

Computer Science > Artificial Intelligence arXiv:2604.04190 (cs) [Submitted on 5 Apr 2026] Title:Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification Authors:Xinyan Ma (1), Xianhao Ou (1), Weihao Zhang (1), Shixin Jiang (1), Runxuan Liu (1), Dandan Tu (2), Lei Chen (3), Ming Liu (1), Bing Qin (1) ((1) Harbin Institute of Technology, Harbin, China, (2) Huawei Technologies Co., Ltd., Beijing, China, (3) Bay Area International Business School, Beijing Normal University, Beijing, China) View a PDF of the paper titled Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification, by Xinyan Ma (1) and 18 other authors View PDF HTML (experimental) 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 ev...