Abstract
Generating novel, feasible, and high-quality research ideas is an important yet challenging task in scientific this http URL 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 this http URL 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 this http URL then extracts compact graph-derived contexts that retain target-relevant relational evidence while reducing noisy textual this http URL 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 this http URL on a scientific idea generation benchmark show that Graph2Idea outperforms representative baselines under the automatic evaluation this http URL 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 this http URL results suggest that graph-structured evidence helps LLMs generate research ideas through more explicit, compact, and traceable recombination of prior scientific knowledge.
Abstract (translated)
URL
https://arxiv.org/abs/2606.09105
