arXiv Machine Learning
The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 15
Large Language Models Extend Known Research But Do Not Create New Research Directions
arXiv:2610.17439v1 Announce Type: new Abstract: The success of autonomous research systems relies on the quality of the scientific hypotheses they generate. Recent studies report that human reviewers...
arXiv AI
Sep 10
AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era
arXiv:2609.07611v1 Announce Type: new Abstract: Scientific ideation is the capacity to formulate novel and testable hypotheses from scientific evidence, and autonomous AI scientists depend on it. Exi...
arXiv AI
Jun 16
LLM Jaggedness Unlocks Scientific Creativity
arXiv:2605. 10574v3 Announce Type: replace Abstract: As artificial intelligence advances, models are not improving uniformly.
arXiv AI
Oct 2
Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers
The paper "Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers" introduces SciSlopBench, a dataset of 390 AI‑generated papers paired with human‑written counterparts, and defines six measures across Structure, Argument, and Artifacts to detect scientific slop. The authors show that these measures can identify AI papers with 85.9% accuracy and that higher slop correlates with lower ICLR ratings and distinguishes rejected from accepted papers. They also propose SciSlopHarness, a framework that guides a fixed LLM to revise only evidence‑supported sections, reducing the AI‑human gap by 63% without human reference targets.
arXiv AI
Jun 9
Contemporary AI lacks the imagination to diverge or negate in science
arXiv:2606. 08251v1 Announce Type: cross Abstract: Bold projections that artificial intelligence will accelerate scientific discovery have raced ahead of evidence from working scientists, and the field still lacks large-scale, scientist-in-the-loop tests of these claims.
arXiv Computation and Language
1d ago
Tracing the Influence of Retrieved Literature on Scientific Ideation in LLMs
Large language models (LLMs) are increasingly used to generate research ideas from scientific literature, but the impact of the retrieval strategy on the ideas produced is unclear. This study isolates that contribution by comparing five retrieval strategies and a no‑literature baseline across 45,000 ideas in 15 machine learning topics and ten open‑weight models. The results show that while all retrieval strategies reduce diversity within a single set of papers, they increase diversity when ideas from different sets are pooled; effects on quality and novelty are modest but topic‑dependent, and a JSD‑based attribution method reveals that most ideas are driven by one or two key papers, with more varied source attribution correlating with greater idea diversity.