Large Language Models (LLMs) have demonstrated exceptional comprehension capabilities and a vast knowledge base, suggesting that LLMs can serve as efficient tools for automated survey generation. However, recent research related to automated survey generation remains constrained by some critical limitations like finite context window, lack of in-depth content discussion, and absence of systematic evaluation frameworks. Inspired by human writing processes, we propose SurveyX, an efficient and organized system for automated survey generation that decomposes the survey composing process into two phases: the Preparation and Generation phases. By innovatively introducing online reference retrieval, a pre-processing method called AttributeTree, and a re-polishing process, SurveyX significantly enhances the efficacy of survey composition. Experimental evaluation results show that SurveyX outperforms existing automated survey generation systems in content quality (0.259 improvement) and citation quality (1.76 enhancement), approaching human expert performance across multiple evaluation dimensions. Examples of surveys generated by SurveyX are available on www.surveyx.cn
@article{arxiv.2502.14776,
title = {SurveyX: Academic Survey Automation via Large Language Models},
author = {Xun Liang and Jiawei Yang and Yezhaohui Wang and Chen Tang and Zifan Zheng and Shichao Song and Zehao Lin and Yebin Yang and Simin Niu and Hanyu Wang and Bo Tang and Feiyu Xiong and Keming Mao and Zhiyu li},
journal= {arXiv preprint arXiv:2502.14776},
year = {2025}
}