SOURCE-LINKED INTELLIGENCE

RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate because reviews and research ideas lack uniquely verifiable outcomes. We introduce Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes. At each cut-off, an LLM agent searches a temporally restricted arXiv corpus and predicts the next six months' paper shares across eight frozen research directions. Search generally helps, but all four diagnostic models perform worse than an exact-count exponentially

Read original source ↗ Open in workspace

recordType

paper

region

Global