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.
Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publication. Existing taxonomy-induction methods are la...
The paper introduces EvoTree, a staged framework for automatically generating evolution trees from citation graphs. It separates backbone learning from temporal refinement, using a graph-aware encoder and hierarchical clustering to build a stable taxonomy, then fine-tunes temporally to attach marginal papers under monotonic-path constraints, and finally labels concepts with an LLM without changing the topology. The authors release an annotated benchmark across 11 AI subfields and report that EvoTree outperforms baselines in NMI, citation-direction accuracy, concept purity, and marginal-paper detection.
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....
How does research evolve, and what substrate would let us forecast where it goes next? Scientific progress is not simply a uniform accumulation of facts: ideas extend prior methods, address known limitations, realize proposed future directions, and sometimes dispute earlier claims.
ScholarCatalyst is a new benchmark that evaluates how well AI systems can retrieve research papers that inspire new work. The dataset was created by having 184 lead authors of 207 recent computer science papers annotate which earlier papers helped their projects, providing detailed rationales. The benchmark tests retrieval from the literature available at the start of a project, revealing that current agentic search and even advanced models like Claude Fable 5.1 perform only modestly better than simple embedding retrieval.
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:2606. 15497v1 Announce Type: new Abstract: The automation of science is a long-standing ambition in the field of AI.
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:2608. 14881v1 Announce Type: new Abstract: AI co-scientists that generate hypotheses, retrieve related work, design experiments, execute code, and draft full papers are beginning to change how research is carried out.
arXiv:2603.20884v4 Announce Type: replace Abstract: To alleviate the heavy burden of paper screening, researchers increasingly rely on existing AI agents, such as AI reviewers or DeepResearch, for pa...
arXiv:2602. 20459v2 Announce Type: replace Abstract: Can AI systems trained on the existing scientific record forecast the advances that will follow?
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.