Agentic Science

TL;DR for operators If two research systems start from the same candidate papers, use the same reranking process, have the same ten-paper writing budget, and use the same GPT-4o writer, should their final citations differ much? In Huang et al.’s study1, they do. When the writer also receives structured views that break papers into claims, premises, reasoning steps, conditions, and provenance, citation F1 rises by 5.3 points on ScholarQA-CS and 5.1 points on ScholarQA-Multi, with both precision and recall improving. ...

A lab does not fail because the scientist forgot how to think. It fails more often for duller reasons: the data table is in the wrong format, the simulation script only works on one cluster, the instrument queue is opaque, the boundary condition was changed but not logged, the literature trail cannot be reconstructed, and the “promising result” lives in someone’s notebook like a small hostage. ...