Papers

22 Jun 2026

Terminal-using agents have quickly become the most popular downstream application of language models (LMs). Despite their prevalence, relatively little academic work has examined RL-based training of these models, likely due to difficult benchmarks, a lack of data, and a lack of…

23 Jun 2026

We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move beyond reproduction toward discovery on real scientific problems.