GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoning

TL;DR

GRAIL introduces an interactive framework that enhances reasoning over large knowledge graphs by combining LLM-guided exploration, path filtering, and a two-stage policy training, significantly improving accuracy and F1 scores.

Contribution

The paper presents GRAIL, a novel method for dynamic, interactive graph retrieval that improves reasoning performance over knowledge graphs compared to existing approaches.

Findings

GRAIL achieves an average accuracy improvement of 21.01% on knowledge graph QA datasets.

GRAIL attains a 22.43% F1 score increase across evaluated datasets.

The framework effectively balances retrieval precision and breadth through a two-stage training process.

Abstract

Large Language Models (LLMs) integrated with Retrieval-Augmented Generation (RAG) techniques have exhibited remarkable performance across a wide range of domains. However, existing RAG approaches primarily operate on unstructured data and demonstrate limited capability in handling structured knowledge such as knowledge graphs. Meanwhile, current graph retrieval methods fundamentally struggle to capture holistic graph structures while simultaneously facing precision control challenges that manifest as either critical information gaps or excessive redundant connections, collectively undermining reasoning performance. To address this challenge, we propose GRAIL: Graph-Retrieval Augmented Interactive Learning, a framework designed to interact with large-scale graphs for retrieval-augmented reasoning. Specifically, GRAIL integrates LLM-guided random exploration with path filtering to establish a data synthesis pipeline, where a fine-grained reasoning trajectory is automatically generated for each task. Based on the synthesized data, we then employ a two-stage training process to learn a policy that dynamically decides the optimal actions at each reasoning step. The overall objective of precision-conciseness balance in graph retrieval is decoupled into fine-grained process-supervised rewards to enhance data efficiency and training stability. In practical deployment, GRAIL adopts an interactive retrieval paradigm, enabling the model to autonomously explore graph paths while dynamically balancing retrieval breadth and precision. Extensive experiments have shown that GRAIL achieves an average accuracy improvement of 21.01% and F1 improvement of 22.43% on three knowledge graph question-answering datasets. Our source code and datasets is available at https://github.com/Changgeww/GRAIL.