{"slug": "laguna-m-1-xs-2-technical-report", "title": "Laguna M.1/XS.2 Technical Report", "summary": "Researchers at Poolside released two new Mixture-of-Experts AI models, Laguna M.1 and Laguna XS.2, designed for long-horizon software engineering tasks. The 225.8-billion-parameter M.1 and 33.4-billion-parameter XS.2, trained from scratch using the company's proprietary \"Model Factory\" system, match state-of-the-art open models on key coding benchmarks including SWE-bench and Terminal-Bench. The smaller XS.2 model's weights are publicly available under an Apache 2.0 license.", "body_md": "arXiv:2605.27605v1 Announce Type: new\nAbstract: We present Laguna M.1 and Laguna XS.2, two Mixture-of-Experts foundation models built for long-horizon, agentic coding: M.1 has $225.8$B total parameters ($23.4$B activated per token) and XS.2 has $33.4$B total ($3$B activated). Both models were trained from scratch end-to-end inside the same internal system that we refer to as our Model Factory: a tightly-integrated stack of versioned data, training, evaluation, and inference components that turn model development into an industrial process. We describe the principles and design choices of the Model Factory and also detail the end-to-end training process of our models, throughout pre-training data and architecture, post-training stages, evaluation, and quantization.\nOn agentic software engineering and terminal benchmarks (SWE-bench Verified, SWE-bench Multilingual, SWE-Bench Pro, and Terminal-Bench 2.0) M.1 and XS.2 are competitive with state-of-the-art open models in their respective weight classes. Laguna XS.2 weights are released under Apache~2.0 at https://huggingface.co/collections/poolside/laguna-xs2.", "url": "https://wpnews.pro/news/laguna-m-1-xs-2-technical-report", "canonical_source": "https://arxiv.org/abs/2605.27605", "published_at": "2026-05-28 04:00:00+00:00", "updated_at": "2026-05-28 04:32:09.270073+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "machine-learning", "ai-agents", "ai-infrastructure"], "entities": ["Laguna M.1", "Laguna XS.2", "Poolside", "Model Factory", "SWE-bench Verified", "SWE-bench Multilingual", "SWE-Bench Pro", "Terminal-Bench 2.0"], "alternates": {"html": "https://wpnews.pro/news/laguna-m-1-xs-2-technical-report", "markdown": "https://wpnews.pro/news/laguna-m-1-xs-2-technical-report.md", "text": "https://wpnews.pro/news/laguna-m-1-xs-2-technical-report.txt", "jsonld": "https://wpnews.pro/news/laguna-m-1-xs-2-technical-report.jsonld"}}