{"ID":5937893,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T05:23:31.724949429Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03709","arxiv_id":"2607.03709","title":"GRASP: Graph-Reasoning Aided Survey Planning for High-Fidelity Related Work Generation","abstract":"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.","short_abstract":"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 algorithm...","url_abs":"https://arxiv.org/abs/2607.03709","url_pdf":"https://arxiv.org/pdf/2607.03709v1","authors":"[\"Haoming Li\",\"Jessica Ouyang\"]","published":"2026-07-04T05:30:01Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}