# Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection

Source: [Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection](<https://www.sota2.com/research/paper/68fa770c1e209131cea70b9c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:47:55.951Z

Authors: Han Zhang, Langshi Zhou, Hanfang Yang

Published: 2025-02-20T06:38:48.000Z

## Abstract

Extensive research has investigated the integration of large language models (LLMs) with knowledge graphs to enhance the reasoning process. However, understanding how models perform reasoning utilizing structured graph knowledge remains underexplored. Most existing approaches rely on LLMs or retrievers to make binary judgments regarding the utilization of knowledge, which is too coarse. Meanwhile, there is still a lack of feedback mechanisms for reflection and correction throughout the entire reasoning path. This paper proposes an Active self-Reflection framework for knowledge Graph reasoning ARG, introducing for the first time an end-to-end training approach to achieve iterative reasoning grounded on structured graphs. Within the framework, the model leverages special tokens to \\textit{actively} determine whether knowledge retrieval is necessary, performs \\textit{reflective} critique based on the retrieved knowledge, and iteratively reasons over the knowledge graph. The reasoning paths generated by the model exhibit high interpretability, enabling deeper exploration of the model's understanding of structured knowledge. Ultimately, the proposed model achieves outstanding results compared to existing baselines in knowledge graph reasoning tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Knowledge Graph Question Answering on MetaQA 3-hop 1.0](<https://www.sota2.com/research/sota/knowledge-graph-question-answering-on-metaqa-3-hop-1-0.md>): Knowledge Graph Question Answering; MetaQA 3-hop 1.0; Hit@1: 87.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.14932>)

[PDF](<https://arxiv.org/pdf/2502.14932.pdf>)