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：近年来，基于大语言模型的智能体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。由于缺乏特定任务的训练数据以及构建任务导向模型结构的复杂性，传统方法实现KBQA系统面临诸多挑战。本文提出Triad框架——一种利用具备三种角色的LLM智能体解决KBQA任务的统一框架。该智能体被赋予三种角色以应对不同KBQA子任务：作为通才掌握多种子任务，作为决策者进行候选方案选择，以及作为顾问利用知识回答问题。我们的KBQA框架通过四个阶段执行，涉及智能体多角色间的协同合作。我们在三个基准数据集上评估了框架性能，结果显示该框架在LC-QuAD和YAGO-QA基准上超越现有最优系统，分别取得11.8%和20.7%的F1得分。