SurveyAgent-HKA：一种结合大语言模型与人类知识增强的科学综述生成多智能体框架
SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentation
浏览论文内容
中文总结 AI 辅助
提出多智能体框架SurveyAgent-HKA，利用已发表综述和同行评审知识，通过多源检索、大纲细化及专家问题指导修订，提升科学综述生成的引用质量、结构一致性与内容质量。
中文摘要 AI 辅助
自动科学综述生成已成为科学文献处理中的一项重要任务。常见的方法是从单一来源（如arXiv）检索文献，并通过一次性大语言模型（LLM）调用来生成综述，这往往导致参考文献覆盖范围有限，更重要的是，无法复现专家驱动的修订过程，而这一过程对于撰写高质量综述至关重要。在本文中，我们提出了SurveyAgent-HKA，一种多智能体框架，通过整合已发表综述和同行评审意见中获取的知识，改进了端到端的科学综述生成。该框架将综述生成分解为多个由LLM驱动的智能体处理的明确定义的子任务。它首先从多个来源检索相关论文，并通过聚类识别关键主题以构建初始大纲，然后利用相关人工撰写综述的大纲对该大纲进行细化。基于细化后的大纲，检索主题聚焦的论文并重新排序，以选择用于起草有充分依据的综述。随后，我们识别专家在已发表综述的同行评审意见中提出的常见问题，以指导修订并最终完成综述。在两个领域的实验表明，我们的方法在引用质量、结构一致性和内容质量方面优于主流基线。此外，我们的框架在时间和成本上均高效，使其成为更广泛的AI辅助科学写作应用的实用解决方案。
英文摘要
Automatic scientific survey generation has become an important task in scientific document processing. The common approach of retrieving literature from a single source (e.g., arXiv) and generating surveys through a one-pass large language model (LLM) call often leads to limited reference coverage and, more importantly, fails to replicate the expert-driven revision process that is crucial for writing high-quality surveys. In this paper, we introduce SurveyAgent-HKA, a multi-agent framework that improves end-to-end scientific survey generation by incorporating knowledge derived from published surveys and peer-review comments. The framework decomposes survey generation into well-defined sub-tasks handled by LLM-powered agent. It first retrieves relevant papers from multiple sources and identifies key topics through clustering to construct an initial outline, which is then refined using outlines from related human-written surveys. Based on the refined outline, topic-focused papers are retrieved and re-ranked to select for drafting a well-grounded survey. Then, we identify common issues raised by experts in peer-review comments from published surveys to guide the revisions and finalize the survey. Experiments on two domains show that our approach outperforms mainstream baselines in citation quality, structural consistency, and content quality. Furthermore, our framework is efficient in both time and cost, making it a practical solution for broader AI-assisted scientific writing applications.
发表机构
- Nanjing University of Science and Technology（南京理工大学）
- University of Alberta（阿尔伯塔大学）
- Anhui University（安徽大学）
机构由 AI 辅助整理，请以论文原文为准。
