用多个AI代理自动整理文献综述，质量远超传统方法。
Agentic AutoSurvey: Let LLMs Survey LLMs
- 四类AI代理协同工作：找论文、聚主题、写综述、评质量。
- 在6个课题上平均得分8.18分（满分10），远超基线4.77分。
- 能处理每主题75至443篇论文，覆盖率达80%以上，适合快速追踪前沿。
科学文献的指数级增长给研究人员跨领域知识整合带来前所未有的挑战。我们提出 extbf{Agentic AutoSurvey}，一种多代理框架，用于自动化生成文献综述，解决了现有方法的根本局限。系统由四个专业代理（论文搜索专家、主题挖掘与聚类、学术综述撰写、质量评估）协同运作，生成综合性强、合成质量高的文献综述。在COLM 2024六个代表性大模型研究主题上的实验表明，该多代理方法显著优于现有基线，在12维评估中得分为8.18/10，而AutoSurvey仅为4.77/10。每个主题处理论文75至443篇（共847篇），通过专业化代理调度实现高引用覆盖率（在75–100篇的集合中常达≥80%；在如RLHF等大规模集合中较低）。评估涵盖组织性、融合性与批判性分析，超越基础指标。结果表明，多代理架构是快速演进科学领域中自动化文献综述的重要进步。
原文摘要 · Abstract (English)
The exponential growth of scientific literature poses unprecedented challenges for researchers attempting to synthesize knowledge across rapidly evolving fields. We present \textbf{Agentic AutoSurvey}, a multi-agent framework for automated survey generation that addresses fundamental limitations in existing approaches. Our system employs four specialized agents (Paper Search Specialist, Topic Mining \& Clustering, Academic Survey Writer, and Quality Evaluator) working in concert to generate comprehensive literature surveys with superior synthesis quality. Through experiments on six representative LLM research topics from COLM 2024 categories, we demonstrate that our multi-agent approach achieves significant improvements over existing baselines, scoring 8.18/10 compared to AutoSurvey's 4.77/10. The multi-agent architecture processes 75--443 papers per topic (847 total across six topics) while targeting high citation coverage (often $\geq$80\% on 75--100-paper sets; lower on very large sets such as RLHF) through specialized agent orchestration. Our 12-dimension evaluation captures organization, synthesis integration, and critical analysis beyond basic metrics. These findings demonstrate that multi-agent architectures represent a meaningful advancement for automated literature survey generation in rapidly evolving scientific domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。