Technology Category
Knowledge Representation and Reasoning: Computational Complexity of ReasoningReasoning under Uncertainty: Other Foundations of Reasoning under UncertaintySearch and Optimization: Metareasoning and Metaheuristics
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
🤖 AI Summary
To address key challenges in knowledge base question answering (KBQA)—including weak knowledge awareness, inefficiency-effectiveness trade-offs, and heavy reliance on strong supervision—this paper proposes the first end-to-end reasoning framework that integrates Monte Carlo Tree Search (MCTS) into a ReAct agent. The method enables deep environment interaction via policy-driven, stepwise logical form generation and knowledge-base-guided heuristic exploration; it further supports high-quality self-labeling and incremental fine-tuning under low-resource conditions. Evaluated on GrailQA, our approach achieves 78.5% F1 with Llama-3.1-8B using only limited annotated data—substantially outperforming the prior state of the art (GPT-3.5-turbo, 48.5% F1). This demonstrates MCTS’s effectiveness and novelty in enhancing both reasoning quality and generalization capability in KBQA.
Technology Category
Application Category
📝 Abstract
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. Moreover, it employs MCTS, a heuristic search method driven by policy and reward models, to balance agentic exploration's performance and search space. With heuristic exploration, KBQA-o1 generates high-quality annotations for further improvement by incremental fine-tuning. Experimental results show that KBQA-o1 outperforms previous low-resource KBQA methods with limited annotated data, boosting Llama-3.1-8B model's GrailQA F1 performance to 78.5% compared to 48.5% of the previous sota method with GPT-3.5-turbo.
Problem
Research questions and friction points this paper is trying to address.
Knowledge Base Question Answering
Data Dependency
Efficiency and Effectiveness Balance
Innovation
Methods, ideas, or system contributions that make the work stand out.
KBQA-o1
Monte Carlo Tree Search (MCTS)
Self-generated Training Data
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
