KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search

Understand

Knowledge Base Question Answering (KBQA) aims to answer natural language questions with a large-scale structured knowledge base (KB).

• Despite advancements with large language models (LLMs), KBQA still faces challenges in weak KB awareness, imbalance between effectiveness and efficiency, and high reliance on annotated data.
• To address these challenges, we propose KBQA-o1, a novel agentic KBQA method with Monte Carlo Tree Search (MCTS).
• It introduces a ReAct-based agent process for stepwise logical form generation with KB environment exploration.