Recent progress with LLM-based agents has shown promising results across various tasks. However, their use in answering questions from knowledge bases remains largely unexplored. Implementing a KBQA system using traditional methods is challenging due to the shortage of task-specific training data and the complexity of creating task-focused model structures. In this paper, we present Triad, a unified framework that utilizes an LLM-based agent with three roles for KBQA tasks. The agent is assigned three roles to tackle different KBQA subtasks: agent as a generalist for mastering various subtasks, as a decision maker for the selection of candidates, and as an advisor for answering questions with knowledge. Our KBQA framework is executed in four phases, involving the collaboration of the agent's multiple roles. We evaluated the performance of our framework using three benchmark datasets, and the results show that our framework outperforms state-of-the-art systems on the LC-QuAD and YAGO-QA benchmarks, yielding F1 scores of 11.8% and 20.7%, respectively.

翻译：近期基于大语言模型（LLM）智能体的研究在各类任务中展现出显著进展，但其在知识库问答中的应用仍鲜有探索。由于缺乏任务特定训练数据以及构建任务聚焦模型结构的复杂性，传统方法实现KBQA系统面临诸多挑战。本文提出Triad统一框架，采用具有三种角色的LLM智能体执行KBQA任务：智能体被赋予通才角色以掌握多类子任务、决策者角色以筛选候选方案、顾问角色以基于知识进行问答。我们的KBQA框架通过四个阶段执行，涉及智能体多角色的协同合作。基于三个基准数据集的评估结果表明，本框架在LC-QuAD与YAGO-QA基准上分别以11.8%和20.7%的F1分数超越现有最优系统。