AISEMay 26

Laguna M.1/XS.2 Technical Report

arXiv:2605.2760541.6h-index: 13Has Code
Predicted impact top 12% in AI · last 90 daysOriginality Synthesis-oriented
AI Analysis

For researchers and practitioners in agentic software engineering, this work provides competitive open models and a systematic approach to model development, though it is incremental as it combines known techniques (MoE, training pipeline) without introducing new paradigms.

The authors present Laguna M.1 and XS.2, Mixture-of-Experts foundation models for agentic coding, trained using a tightly-integrated Model Factory system. On benchmarks like SWE-bench Verified and Terminal-Bench 2.0, they are competitive with state-of-the-art open models in their weight classes.

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. On 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes