Mixture of Knowledge Minigraph Agents for Literature Review Generation

TL;DR

This paper introduces CKMAs, a framework using knowledge minigraphs and large language models to automate and improve the efficiency of scientific literature reviews.

Contribution

The paper presents a novel prompt-based algorithm for constructing knowledge minigraphs and a multi-path summarization approach for literature review generation.

Findings

Effective on three benchmark datasets

Improves organization of concepts from multiple viewpoints

Demonstrates promising applications of LLMs in research

Abstract

Literature reviews play a crucial role in scientific research for understanding the current state of research, identifying gaps, and guiding future studies on specific topics. However, the process of conducting a comprehensive literature review is yet time-consuming. This paper proposes a novel framework, collaborative knowledge minigraph agents (CKMAs), to automate scholarly literature reviews. A novel prompt-based algorithm, the knowledge minigraph construction agent (KMCA), is designed to identify relations between concepts from academic literature and automatically constructs knowledge minigraphs. By leveraging the capabilities of large language models on constructed knowledge minigraphs, the multiple path summarization agent (MPSA) efficiently organizes concepts and relations from different viewpoints to generate literature review paragraphs. We evaluate CKMAs on three benchmark datasets. Experimental results show the effectiveness of the proposed method, further revealing promising applications of LLMs in scientific research.