# Latest research April 30, 2026 [**AstaBench update: New results, plus adoption from industry**](/content/blog/astabench-update-spring-2026/index.html) AstaBench’s latest update adds new frontier-model results, including GPT-5.5, and highlights growing adoption from groups including the UK AISI, General Reasoning, Elicit, SciSpace, Distyl AI, and EvoScientist. April 23, 2026 [**Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis**](/content/blog/olmoearth-embeddings/index.html) OlmoEarth Studio now lets users export custom Earth-observation embeddings from our OlmoEarth foundation models and use them for tasks like similarity search, few-shot mapping, change detection, and unsupervised exploration. April 23, 2026 [**OlmPool: How small architectural choices compound to undermine long context extension**](/content/blog/olmpool/index.html) OlmPool is a controlled suite of 26 models showing how small architecture choices can compound to make long-context extension much harder, even when training data and extension recipes are held constant. April 20, 2026 [**Train separately, merge together: Modular post-training with mixture-of-experts**](/content/blog/bar/index.html) BAR is a recipe for post-training language models one capability at a time—train domain experts independently, merge them into a single mixture-of-experts model, and upgrade any expert without impacting the others. April 13, 2026 [**Evaluating agents for scientific discovery**](/content/blog/evaluating-scientific-discovery-agents/index.html) Two benchmarks developed at Ai2 – ScienceWorld and DiscoveryWorld – reveal that even incredibly strong AI science agents struggle with problems human scientists solve routinely. April 7, 2026 [**Introducing WildDet3D: Open-world 3D detection from a single image**](/content/blog/wilddet3d/index.html) WildDet3D is an open model that predicts 3D bounding boxes from a single image. It generalizes across cameras and object categories, and folds in depth signals when available—alongside a new dataset of verified 3D annotations. March 24, 2026 [**MolmoWeb: An open agent for automating web tasks**](/content/blog/molmoweb/index.html) Introducing MolmoWeb, an open visual web agent that navigates and completes tasks in a browser using screenshots alone, along with MolmoWebMix, the largest public dataset for training web agents. March 18, 2026 [**MolmoPoint: Better pointing architecture for vision-language models**](/content/blog/molmopoint/index.html) MolmoPoint is a new vision-language model architecture that replaces text-based coordinate outputs with a more natural, token-based pointing mechanism that directly selects regions from visual features. March 11, 2026 [**MolmoBot: Training robot manipulation entirely in simulation**](/content/blog/molmobot-robot-manipulation/index.html) MolmoBot is an open robotic manipulation model suite trained entirely in simulation—demonstrating zero-shot transfer to real-world robots without any real-world data collection or fine-tuning.