Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts

• URL: http://arxiv.org/abs/2606.09105v3
• Date: Wed, 10 Jun 2026 01:31:19 GMT
• Title: Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts
• Abstract summary: Graph2Idea is a knowledge graph-guided framework for retrieval-augmented scientific idea generation.<n>It first retrieves papers according to the input topic, transforms them into structured knowledge triples, and dynamically constructs a target-centered knowledge graph.<n>It then extracts compact graph-derived contexts that retain target-relevant relational evidence while reducing noisy textual input.
• Score: 3.548612755859995
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating novel, feasible, and high-quality research ideas is an important yet challenging task in scientific discovery. Recent Large Language Model (LLM)-based methods often ground idea generation with retrieved literature, but the retrieved evidence is usually provided as flat text, such as titles, abstracts, or summaries. Such flat contexts may contain redundant or weakly relevant information, while making cross-paper relations among problems, methods, mechanisms, and findings difficult to identify and trace. To address this challenge, we propose Graph2Idea, a knowledge graph-guided framework for retrieval-augmented scientific idea generation.Graph2Idea first retrieves papers according to the input topic, transforms them into structured knowledge triples, and dynamically constructs a target-centered knowledge graph to make literature relations explicit. It then extracts compact graph-derived contexts that retain target-relevant relational evidence while reducing noisy textual input. Based on these contexts, a two-stage generation process first identifies promising research directions and then guides the LLM to synthesize candidate ideas from graph-grounded evidence. Experiments on a scientific idea generation benchmark show that Graph2Idea outperforms representative baselines under the automatic evaluation protocol. Compared with the strongest baseline scores, it improves Novelty from 0.45 to 0.52, Quality from 0.24 to 0.29, and Feasibility from 0.22 to 0.28. These results suggest that graph-structured evidence helps LLMs generate research ideas through more explicit, compact, and traceable recombination of prior scientific knowledge.

Related papers

• From topology learning to graph generation: A unifying perspective [61.18730621087076]
  Learning graph structures from data is a fundamental problem that spans a wide range of signal processing and machine learning tasks.<n>Existing research has largely evolved along two parallel directions.<n>This review presents a unified framework that connects these formulations by viewing them as inverse problems of a common generation process for graph data.
  arXiv  Detail & Related papers  (2026-09-02T08:36:36Z)
• LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation [57.70907667652966]
  Introduction writing is especially challenging, which demands logical soundness and verifiable faithfulness.<n>Most AI-assisted methods treat the task as text generation instead of reasoning and structuring, leading to severe drawbacks.<n>We propose LECTOR, a novel Logic-Expression Co-Reinforcement Learning framework that can strictly follow the scientist's logic, add high-quality citations and keep structured expressions.
  arXiv  Detail & Related papers  (2026-05-25T15:41:16Z)
• Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation [1.2232326171442904]
  This paper proposes a scientific idea generation system called GYWI.<n>It combines author knowledge graphs with retrieval-augmented generation (RAG) to form an external knowledge base.<n>The generated ideas are evaluated from the following five dimensions: novelty, feasibility, clarity, relevance, and significance.
  arXiv  Detail & Related papers  (2025-12-05T03:38:23Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [79.75818239774952]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs [9.718354494802002]
  Contextualized Graph Retrieval-Augmented Generation (CG-RAG) is a novel framework that integrates sparse and dense retrieval signals within graph structures.<n>First, we propose a contextual graph representation for citation graphs, effectively capturing both explicit and implicit connections within and across documents.<n>Second, we introduce Lexical-Semantic Graph Retrieval (LeSeGR), which seamlessly integrates sparse and dense retrieval signals with graph encoding.<n>Third, we present a context-aware generation strategy that utilizes the retrieved graph-structured information to generate precise and contextually enriched responses.
  arXiv  Detail & Related papers  (2025-01-25T04:18:08Z)
• GRAG: Graph Retrieval-Augmented Generation [14.98084919101233]
  Graph Retrieval-Augmented Generation (GRAG) tackles the fundamental challenges in retrieving textual subgraphs.<n>We propose a novel divide-and-conquer strategy that retrieves the optimal subgraph structure in linear time.<n>Our experiments on graph reasoning benchmarks demonstrate that our GRAG approach significantly outperforms current state-of-the-art RAG methods.
  arXiv  Detail & Related papers  (2024-05-26T10:11:40Z)
• H2CGL: Modeling Dynamics of Citation Network for Impact Prediction [13.00224680454585]
  We construct hierarchical and heterogeneous graphs for target papers with an annual perspective. The graphs can record the annual dynamics of target papers' scientific context information. A novel graph neural network, Hierarchical and Heterogeneous Contrastive Graph Learning Model, is proposed.
  arXiv  Detail & Related papers  (2023-04-16T13:04:32Z)
• Scientific Paper Extractive Summarization Enhanced by Citation Graphs [50.19266650000948]
  We focus on leveraging citation graphs to improve scientific paper extractive summarization under different settings. Preliminary results demonstrate that citation graph is helpful even in a simple unsupervised framework. Motivated by this, we propose a Graph-based Supervised Summarization model (GSS) to achieve more accurate results on the task when large-scale labeled data are available.
  arXiv  Detail & Related papers  (2022-12-08T11:53:12Z)
• Enhancing Scientific Papers Summarization with Citation Graph [78.65955304229863]
  We redefine the task of scientific papers summarization by utilizing their citation graph. We construct a novel scientific papers summarization dataset Semantic Scholar Network (SSN) which contains 141K research papers in different domains. Our model can achieve competitive performance when compared with the pretrained models.
  arXiv  Detail & Related papers  (2021-04-07T11:13:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.