arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.26012cs.AI
收藏

AutoSurvey2:赋能研究人员的下一代自动化文献综述

AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys

University of Texas at Arlington(德克萨斯理工大学);AI Agent Lab(人工智能代理实验室);Indiana University(印第安纳大学);Ohio State University(俄亥俄州立大学);Imperial College London(伦敦帝国理工学院);Georgia Institute of Technology(佐治亚理工学院);Appcubic(Appcubic公司);Emory University(埃默里大学)

Siyi Wu, Chiaxin Liang, Ziqian Bi, Leyi Zhao, Tianyang Wang, Junhao Song, Yichao Zhang, Keyu Chen, Benji Peng, Xinyuan Song

AI总结:

AutoSurvey2通过多阶段流程实现自动化文献综述生成,结合检索增强合成与结构化评估,提升综述的连贯性与相关性,为学术写作提供可扩展解决方案。

摘要:

研究文献的快速增长,特别是在大语言模型(LLMs)领域,使得生成全面且最新的综述论文变得愈发困难。本文介绍了AutoSurvey2,一种多阶段流程,通过检索增强的合成和结构化评估自动化综述生成。系统整合了并行部分生成、迭代优化和实时检索最新出版物,以确保主题完整性和事实准确性。质量通过多LLM评估框架进行评估,该框架测量覆盖范围、结构和相关性,与专家评审标准一致。实验结果表明,AutoSurvey2在结构连贯性和主题相关性方面优于现有检索和自动化基线,同时保持了强劲的引用保真度。通过将检索、推理和自动化评估整合到统一框架中,AutoSurvey2为生成长篇学术综述提供了可扩展且可重复的解决方案,并为未来自动化学术写作研究奠定了坚实基础。所有代码和资源均在https://github.com/annihi1ation/auto_research上提供。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑