arXiv:2607. 01233v1 Announce Type: cross Abstract: LLMs are increasingly used to brainstorm research ideas, but existing evaluations mostly judge individual ideas by novelty, feasibility, or expert preference.
arXiv:2609.14057v1 Announce Type: new Abstract: Frontier LLMs are increasingly capable of conducting automated research, yet their creativity in this setting has not been systematically evaluated. In...
LitPivot is a tool that supports researchers in developing well-situated research ideas by dynamically linking literature exploration with idea refinement. It introduces literature-initiated pivots, where engaging with relevant papers prompts revisions to an idea, and vice versa, updating the set of pertinent literature. In a lab study with 17 participants, users produced higher-rated ideas and reported a stronger understanding of the literature space, while an open-ended study with five participants illustrated how LitPivot facilitates iterative idea evolution.
arXiv:2606. 12071v1 Announce Type: cross Abstract: LLMs are increasingly used to generate and judge scientific ideas.
The paper "Learning to Ideate for Scientific Impact" explores using delayed signals of scientific uptake—specifically citation-normalized impact—as feedback to steer large language models toward generating high‑impact research ideas. The authors build a dataset of over 100,000 computer science papers, train a reward model to predict citation impact from goal‑idea pairs, and align an idea generator via supervised fine‑tuning and reinforcement learning. Evaluation with a reference‑grounded protocol shows that the RL‑tuned model consistently produces ideas with higher estimated impact than baseline models.
arXiv:2607. 04439v1 Announce Type: new Abstract: Large language models have made research ideation increasingly accessible, yet effective idea development requires more than generating candidate directions.
arXiv:2606. 26130v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to guide research methodology, yet their default methodological tendencies under minimal prompting remain unclear.
arXiv:2609.15996v1 Announce Type: new Abstract: Chen, Zhao, and Cohan introduce a valuable distributional evaluation of LLM-generated research ideas. This comment raises a narrower identification con...
arXiv:2608. 10740v1 Announce Type: new Abstract: Effective research ideation requires moving beyond a static understanding of prior work to trace how research problems and solutions evolve across the literature.
The paper introduces SciMuse, an AI system that generates personalized research ideas by combining a knowledge graph of 58 million papers with a large language model. A large-scale evaluation involving over 100 research group leaders across disciplines rated more than 4,400 ideas, yielding modest overall interest scores but showing that 24.9% were rated highly. The study also demonstrates that graph-derived features can predict idea interest and can be used to control idea properties, offering a new methodology for generating and assessing scientific ideas.
arXiv:2510. 20091v3 Announce Type: replace-cross Abstract: Creativity is often seen as a hallmark of human intelligence.
arXiv:2605. 10574v3 Announce Type: replace Abstract: As artificial intelligence advances, models are not improving uniformly.
RATIO (Retrieval Across Typed Ideation Operations) is a large-scale benchmark designed to evaluate how well retrieval systems can support scientific inspiration. It defines relevance through three ideation moves—Address, Broaden, and Specify—each targeting different levels of abstraction in literature retrieval. The benchmark is built from millions of full-text CS papers using a novel discourse-marker distant supervision method, and includes extensive LLM and human vetting to ensure quality.