Zhenzhao Yuan

Backjump-on-Graph: Empowering LLMs with Reinforced Retrospective Exploration for Agentic KG Reasoning

Grounding Large Language Models (LLMs) in Knowledge Graphs (KGs) has shown significant promise for complex Question Answering (QA) tasks. Since LLMs' limited context window cannot accommodate the sheer volume of large-scale KGs, existing work usually utilizes agents to reason on real-world KGs, whic…