04:00
2026-07-13
arxiv.org
artificial-intelligence
AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge Graphs
Researchers propose AgentKGV, an agentic LLM-RAG framework for verifying facts in knowledge graphs, using dynamic routing and iterative query rewriting. A two-stage training strategy combining distill…