用结构化检索生成论文综述，让AI更懂学术脉络。
STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation
- 构建多智能体图谱动态抽取实体关系与分类体系
- 相比纯向量检索，召回率提升2.9（ROUGE-1）和1.0（ROUGE-2）
- 适合需要高质量综述生成的研究者与学术写作助手
科学论文的快速增长使得追踪和综合研究进展愈发困难。尽管大语言模型（LLMs）可支持自动撰写综述，但现有方法依赖非结构化数据检索，需模型在生成阶段推断概念、方法与分类关系。我们提出STRUCTSURVEY，一种分层多智能体框架，通过动态构建基于图的实体、关系与主题分类体系，将结构化推理从生成环节转移到检索环节。我们在新推出的参考基准（ACL综述论文）上评估该方法，用于可复现的长篇科学摘要生成。相较于仅使用嵌入的基线方法，STRUCTSURVEY在平均上使ROUGE-1召回率提升2.9，ROUGE-2召回率提升1.0，同时不降低精度。此外，在基于LLM的评分中，其逻辑结构、深度与综合能力均显著优于基线，表明显式结构化检索能生成更接近人工撰写的组织与推理效果。
原文摘要 · Abstract (English)
The rapid growth of scientific publications makes it increasingly difficult to track and synthesize research progress. While Large Language Models (LLMs) can support automated survey generation, existing methods retrieve unstructured data and require models to infer conceptual, methodological, and taxonomic relations from raw text at generation time. We introduce STRUCTSURVEY, a hierarchical multi-agent framework that shifts structural reasoning from generation to retrieval by dynamically constructing graph-based representations of entities, relations, and topical taxonomies. We evaluate STRUCTSURVEY on a new reference-grounded benchmark of ACL survey papers for reproducible long-form scientific summarization. Compared with embedding-only retrieval baselines, STRUCTSURVEY improves ROUGE-1 recall by +2.9 and ROUGE-2 recall by +1.0 on average, without reducing precision. It also improves LLM-as-a-Judge ratings for logical structure, depth, and synthesis, showing that explicit structural retrieval yields surveys closer to human-written organization and reasoning.
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。