Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
10 Jun 2026
General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring.
12 Jun 2026
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using…
16 Jun 2026
Game generation is an emerging application of coding agents, requiring models to transform natural-language specifications into playable interactive systems. Unlike traditional coding tasks, game generation takes place within a game engine, where scripts, scenes, assets,…
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.