Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Siyi, Liang, Chiaxin, Bi, Ziqian, Zhao, Leyi, Wang, Tianyang, Song, Junhao, Zhang, Yichao, Chen, Keyu, Peng, Benji, Song, Xinyuan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.26012
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912742129008640
author Wu, Siyi
Liang, Chiaxin
Bi, Ziqian
Zhao, Leyi
Wang, Tianyang
Song, Junhao
Zhang, Yichao
Chen, Keyu
Peng, Benji
Song, Xinyuan
author_facet Wu, Siyi
Liang, Chiaxin
Bi, Ziqian
Zhao, Leyi
Wang, Tianyang
Song, Junhao
Zhang, Yichao
Chen, Keyu
Peng, Benji
Song, Xinyuan
contents The rapid growth of research literature, particularly in large language models (LLMs), has made producing comprehensive and current survey papers increasingly difficult. This paper introduces autosurvey2, a multi-stage pipeline that automates survey generation through retrieval-augmented synthesis and structured evaluation. The system integrates parallel section generation, iterative refinement, and real-time retrieval of recent publications to ensure both topical completeness and factual accuracy. Quality is assessed using a multi-LLM evaluation framework that measures coverage, structure, and relevance in alignment with expert review standards. Experimental results demonstrate that autosurvey2 consistently outperforms existing retrieval-based and automated baselines, achieving higher scores in structural coherence and topical relevance while maintaining strong citation fidelity. By combining retrieval, reasoning, and automated evaluation into a unified framework, autosurvey2 provides a scalable and reproducible solution for generating long-form academic surveys and contributes a solid foundation for future research on automated scholarly writing. All code and resources are available at https://github.com/annihi1ation/auto_research.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26012
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys
Wu, Siyi
Liang, Chiaxin
Bi, Ziqian
Zhao, Leyi
Wang, Tianyang
Song, Junhao
Zhang, Yichao
Chen, Keyu
Peng, Benji
Song, Xinyuan
Artificial Intelligence
The rapid growth of research literature, particularly in large language models (LLMs), has made producing comprehensive and current survey papers increasingly difficult. This paper introduces autosurvey2, a multi-stage pipeline that automates survey generation through retrieval-augmented synthesis and structured evaluation. The system integrates parallel section generation, iterative refinement, and real-time retrieval of recent publications to ensure both topical completeness and factual accuracy. Quality is assessed using a multi-LLM evaluation framework that measures coverage, structure, and relevance in alignment with expert review standards. Experimental results demonstrate that autosurvey2 consistently outperforms existing retrieval-based and automated baselines, achieving higher scores in structural coherence and topical relevance while maintaining strong citation fidelity. By combining retrieval, reasoning, and automated evaluation into a unified framework, autosurvey2 provides a scalable and reproducible solution for generating long-form academic surveys and contributes a solid foundation for future research on automated scholarly writing. All code and resources are available at https://github.com/annihi1ation/auto_research.
title AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys
topic Artificial Intelligence
url https://arxiv.org/abs/2510.26012