arXiv cs.AI· Yuquan Lin, Wenshuo Zhang, Yilin Ye, Shuchang Xu, Zhao Chen, Weiqi Wang, Huamin Qu·· 12 小时前AI 评分27
InsightRAG：聚合分布式学术判断生成科学综述
InsightRAG: Aggregating Distributed Scholarly Judgments for Scientific Survey Generation
AI 导读
InsightRAG 通过挖掘论文作者撰写的 Related Work 部分中的引用关系与判断，重建经核验的研究范围并组织关系证据，再以最小冲突目标聚合为反映作者视角的分类体系来指导综述生成。在 10 个主题上的结果显示，其在范围重建、分类质量、引用支持和参考文献可靠性方面均有提升。
正文 · 原文
Abstract:The rapid growth of scientific literature makes survey writing increasingly challenging, motivating automatic survey generation. Yet, existing systems must search an open space of papers and an open space of concepts with no trace of how the community itself has navigated them, leading to incomplete scope, weak taxonomies, and unreliable citations. Our core insight is that author-written Related Work sections contain the human judgments needed to address both limitations: authors curate the citations relevant to their contributions and explain how the cited works relate, yielding paths for scope reconstruction and relational evidence for organization. We propose InsightRAG. Its insight-guided retrieval follows author-supported citation relations to reconstruct a verified research scope and structure the resulting relational evidence. It aggregates these judgments under a minimum-conflict objective into a taxonomy that reflects recurring author-written perspectives in the retrieved literature, guides generation, and bounds each section's evidence. Results on ten topics show gains in scope reconstruction, taxonomy quality, citation support, and reference reliability.
| Subjects: | Artificial Intelligence (cs.AI); Digital Libraries (cs.DL) |
| Cite as: | arXiv:2610.28085 [cs.AI] |
| (or arXiv:2610.28085v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28085 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuquan Lin [view email]
[v1]
Tue, 20 Oct 2026 12:04:17 UTC (1,693 KB)
来源：arXiv cs.AI · arxiv.org