AI evidence extraction

Mixture of Knowledge Minigraph Agents for Literature Review Generation

Zhi Zhang, Yan Liu, Sheng-hua Zhong, Gong Chen, Yang Yu, Jiannong Cao · Proceedings of the AAAI Conference on Artificial Intelligence · 2025

AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.

9/10

Relevance

0/4

Quality (LMQS)

Evidence

Citations

0.00

FWCI

This is an AI analysis. Read the peer-reviewed original at the publisher: https://doi.org/10.1609/aaai.v39i24.34796

Methodology & findings

Study design

Artifact design and evaluation.

Primary method

design_science

Main result

The study demonstrates that "Experimental results show the effectiveness of the proposed method, further revealing promising applications of LLMs in scientific research." The framework successfully automates literature review generation by constructing knowledge minigraphs and leveraging large language models to organize concepts and generate review paragraphs across multiple perspectives.

Research paradigm

computational_design_science

Author conclusions

The authors conclude that "the process of conducting a comprehensive literature review is yet time-consuming" and propose that the collaborative knowledge minigraph agents framework addresses this challenge by automating scholarly literature reviews, demonstrating "promising applications of LLMs in scientific research."

Open questions raised

The paper identifies that "the process of conducting a comprehensive literature review is yet time-consuming," suggesting the research gap of needing automated approaches for scholarly literature review generation.

Data: not_statedCode: not_statedExtracted from: pdfAgreement 82%

Explore related topics

Systematic Review Automation Literature Discovery Design Science