arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.00007cs.CLcs.AIcs.IR
收藏

PPoGA: 基于图的预测计划与动作的知识图谱问答

PPoGA: Predictive Plan-on-Graph with Action for Knowledge Graph Question Answering

MODULABS

MinGyu Jeon, SuWan Cho, JaeYoung Shu

AI总结:

PPoGA通过引入规划器-执行器架构和预测处理机制,提升知识图谱问答的鲁棒性和灵活性,实现状态-of-the-art性能。

摘要:

大型语言模型(LLMs)结合知识图谱(KGs)已推动了复杂问答的发展,但它们在初始高层次推理计划错误时仍容易失败。这种局限性类似于认知固着效应,阻碍了智能体重构方法的能力,导致它们追求不可行的解决方案。为此,我们提出了PPoGA(基于图的预测计划与动作)框架,灵感来源于人类的认知控制和问题解决。PPoGA采用规划器-执行器架构,将高层次策略与低层次执行分离,并利用预测处理机制来预测结果。我们工作的核心创新是一个自我纠正机制,使智能体不仅能对局部执行错误进行路径修正,还能在计划无效时识别、丢弃并重新制定整个计划。我们在三个具有挑战性的多跳KGQA基准测试上进行了广泛的实验:GrailQA、CWQ和WebQSP。结果表明,PPoGA在性能上达到了最先进的水平,显著优于现有方法。我们的工作强调了像问题重构这样的元认知能力在构建更稳健和灵活的人工智能推理系统中的关键作用。

英文摘要:

Large Language Models (LLMs) augmented with Knowledge Graphs (KGs) have advanced complex question answering, yet they often remain susceptible to failure when their initial high-level reasoning plan is flawed. This limitation, analogous to cognitive functional fixedness, prevents agents from restructuring their approach, leading them to pursue unworkable solutions. To address this, we propose PPoGA (Predictive Plan-on-Graph with Action), a novel KGQA framework inspired by human cognitive control and problem-solving. PPoGA incorporates a Planner-Executor architecture to separate high-level strategy from low-level execution and leverages a Predictive Processing mechanism to anticipate outcomes. The core innovation of our work is a self-correction mechanism that empowers the agent to perform not only Path Correction for local execution errors but also Plan Correction by identifying, discarding, and reformulating the entire plan when it proves ineffective. We conduct extensive experiments on three challenging multi-hop KGQA benchmarks: GrailQA, CWQ, and WebQSP. The results demonstrate that PPoGA achieves state-of-the-art performance, significantly outperforming existing methods. Our work highlights the critical importance of metacognitive abilities like problem restructuring for building more robust and flexible AI reasoning systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑