문헌 리뷰를 작성하려면 인용 논문들 간의 관계, 즉 논문들이 서로를 어떻게 발전시키고, 반박하거나, 대안적 관점을 제시하는지에 대한 깊은 이해가 필요하다. 우리는 관련 연구 생성을 위한 대규모 언어 모델(LLM) 계획과 그래프 알고리즘을 결합하여 인용 논문들 간의 핵심 관계를 추출하는 프레임워크인 Graph-Reasoning Aided Survey Planning(GRASP)을 제안한다. 우리의 2층(two-layer) 그래프 구조는 사고의 그래프(Graph of Thoughts)와 논증-반론 계획 네트워크(Argument-Counterargument Planning Network)로 구성되어 인용 논문들을 서로 다른 세분화 수준으로 표현하며, Steiner 트리를 통한 위상 인식 가지치기(topology-aware pruning)를 적용하여 그래프에 포착된 핵심 논문 간 관계를 식별한다. 인용 분석 기반 평가 결과, GRASP가 생성한 관련 연구 섹션(RWS)은 담화 역할, 의도, 인용 그룹화 측면에서 인간이 작성한 목표 텍스트와 매우 유사하게 일치함을 보였다.
Large language models have shown strong fluency in scientific writing, yet the evaluation of related work generation (RWG) remains limited. Existing RWG evaluations largely inherit summarization-oriented metrics, using lexical or semantic similarity to reference sections as proxies for quality. However, related work writing is fundamentally a citation-level scholarly positioning task: it requires selecting, organizing, and framing prior work to clarify how a target paper relates to, differs from, and contributes beyond existing research.As a result, models may generate coherent and semantically-relevant text while exhibiting academically critical failures, such as inappropriate citation selection or misplaced references, that conventional metrics do not capture.To this end, we introduce \textbf{RWGBench}, a benchmark that evaluates RWG from the perspective of citation decision-making rather than text similarity. RWGBench is constructed from a large-scale collection of 40,108 computer science papers and a retrieval corpus of 1.09 million documents, with a carefully curated test set comprising 100 papers and their corresponding published related work sections.We propose a multi-dimensional evaluation framework that assesses citation selection, contextual appropriateness, organization, and discourse structure.Experiments reveal systematic limitations in current systems that are obscured by standard evaluations, while Oracle studies further disentangle retrieval-level and generation-level bottlenecks. Human evaluation further shows that our citation-centric metrics align substantially better with expert judgment than surface-level text metrics. RWGBench offers a citation-centric testbed for developing and evaluating related work generation systems that are better aligned with scholarly writing practices.