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.
The paper introduces LDC, a framework that learns to generate research ideas with dynamic control. It combines supervised fine‑tuning on paper‑idea pairs with controllable reinforcement learning that optimizes novelty, feasibility, and effectiveness. During inference, sentence‑level controllers steer the generation process to balance these dimensions.
arXiv:2602. 20459v2 Announce Type: replace Abstract: Can AI systems trained on the existing scientific record forecast the advances that will follow?
arXiv:2606. 24894v2 Announce Type: replace-cross Abstract: Large language models have shown strong fluency in scientific writing, yet the evaluation of related work generation (RWG) remains limited.
arXiv:2609.14248v1 Announce Type: cross Abstract: Faithful citation attribution begins with identifying the intended source for a scientific claim. We study this source-identification capability thro...
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.
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:2606.22342v2 Announce Type: replace Abstract: How does research evolve, and can we trace it at the level of individual claims? Scientific progress is not simply a uniform accumulation of facts....
arXiv:2608. 16645v1 Announce Type: new Abstract: Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography?
arXiv:2603. 26791v3 Announce Type: replace-cross Abstract: Assessing a cited paper's impact is typically done by analyzing its citation context in isolation within the citing paper.
arXiv:2606. 09105v1 Announce Type: new Abstract: Generating novel, feasible, and high-quality research ideas is an important yet challenging task in scientific discovery.
The paper proposes a new method for credit scoring research articles that distinguishes between a paper’s original contribution and the prior work it builds upon. It introduces a hierarchical ‘contribution tree’ framework that conserves importance across a document’s structure and separates original from citation-derived credit. Large language models are employed as noisy comparative estimators to scale the analysis, and the approach is extended to collections of articles via weighted citation graphs to produce corpus-level contributions and normalized influence scores.
arXiv:2603. 27435v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports.