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LLM的智能体在各种任务中展现出令人瞩目的进展。然而，其在知识库问答领域的应用仍鲜有探索。由于缺乏任务特化的训练数据以及构建聚焦任务模型结构的复杂性，使用传统方法实施KBQA系统面临诸多挑战。本文提出Triad——一个统一的框架，采用具备三种角色的LLM智能体处理KBQA任务。该智能体被赋予三种角色以应对不同的KBQA子任务：作为通才型智能体掌握多种子任务，作为决策者进行候选项选择，以及作为顾问利用知识回答问题。我们的KBQA框架分四个阶段执行，涉及智能体多角色的协同配合。我们采用三个基准数据集评估框架性能，结果表明，在LC-QuAD和YAGO-QA基准上，该框架分别以11.8%和20.7%的F1得分超越了当前最先进系统。