GRASP：用于高保真相关工作生成的图推理辅助综述规划
GRASP: Graph-Reasoning Aided Survey Planning for High-Fidelity Related Work Generation
AI总结：
研究如何写文献综述，核心方法是结合大语言模型规划与图算法，主要贡献是提出GRASP框架，其两层图结构及拓扑感知剪枝能生成与人工撰写匹配的相关工作部分。
摘要：
撰写文献综述需要深入理解被引用论文之间的关系：它们如何相互借鉴、挑战或提供替代观点。我们提出了图推理辅助综述规划（GRASP），这是一个将用于相关工作生成的大语言模型规划与图算法相结合的框架，以提取被引用论文之间的关键关系。我们的两层图结构由思想图和论点-反论点规划网络组成，在不同粒度级别表示被引用论文，并且我们通过斯坦纳树应用拓扑感知剪枝来识别图中捕获的核心论文间关系。我们基于引用分析的评估表明，GRASP生成的相关工作部分（RWS）在引用的话语角色、意图和分组方面与人工撰写的目标密切匹配。
英文摘要：
Writing a literature review requires a deep understanding of the relationships among cited papers: how they build on, challenge, or offer alternative perspectives to one another. We present Graph-Reasoning Aided Survey Planning (GRASP), a framework combining LLM planning for related work generation with graph algorithms to extract key relationships among cited papers. Our two-layer graph structure consists of a Graph of Thoughts and an Argument-Counterargument Planning Network, representing the cited papers at different levels of granularity, and we apply topology-aware pruning via a Steiner tree to identify the core inter-paper relationships captured in our graph. Our citation analysis-based evaluation shows that GRASP generates related work sections (RWS) that closely match human-written targets in terms of the discourse roles, intents, and grouping of citations.
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。
