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

TL;DR

PPoGA introduces a novel framework for knowledge graph question answering that incorporates self-correction and predictive mechanisms, significantly improving robustness and accuracy over existing methods.

Contribution

The paper presents PPoGA, a new KGQA model with a Planner-Executor architecture and self-correction capabilities, enabling dynamic plan reformulation and improved reasoning.

Findings

Achieves state-of-the-art results on GrailQA, CWQ, and WebQSP benchmarks.

Demonstrates the effectiveness of plan correction and predictive processing in KGQA.

Outperforms existing methods in multi-hop question answering accuracy.

Abstract

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.