Laguna XS.2 and M.1: A Deeper Dive — Poolside

We've released the first two models in the Laguna family, Laguna M.1 and Laguna XS.2, alongside the runtime we use to train and operate agents, available through two product experiences in preview.

Laguna M.1 came first, finishing pre-training at the end of last year; it's the foundation for everything else we're building across the family. Laguna XS.2 is a much smaller model, but remarkably capable for its size, and it's our first open-weight release. Both models are free to use for a limited time via our API and on OpenRouter, and Laguna XS.2 weights are also available under an Apache 2.0 license.

Laguna XS.2 and Laguna M.1 are agentic coding models built for long-horizon work. To date, we’ve been focused on serving our government and public sector clients with capable models deployable into the highest-security environments. And while our commitment to these customers remains, we’re now ready to share where we are with the world. We’re also excited to release the weights of Laguna XS.2, our newest generation model, to the open ecosystem to support builders and the wider research community.

We're working toward models that enable more capable agents; and we believe the path runs through coding capability and increasingly long-horizon tasks. Creating software is the core skill through which many other capabilities get expressed.

Today, most agents interact with the world through tool calling, where structured interfaces restrict agents to a fixed set of actions defined in advance. We think this is a transitional pattern. Software is a much more expressive interface. An agent that can write and execute code can compose actions, parallelize work, and build its own ad-hoc systems to interact with the world.

These models are the work of the roughly 60 people who make up our Applied Research organization, across architecture, data, pre-training, and reinforcement learning. We're excited to bring this work into the world and see what the community builds with it.

• Laguna M.1225B-A23B
• Qwen3.5397B-A17B
• Claude Sonnet 4.6-
• Laguna XS.233B-A3B
• Qwen3.535B-A3B
• Qwen3.635B-A3B

SWE-bench Verified

SWE-bench Verified
Resolved tasks on SWE-bench Verified.

Laguna M.1 is our most capable model to date and completed pre-training at the end of last year. It's a 225B total parameter Mixture of Experts (MoE) model with 23B activated parameters, trained completely in-house and from scratch on 30T tokens, using 6,144 interconnected NVIDIA Hopper GPUs. Laguna M.1 reaches 46.9% on SWE-Bench Pro and 40.7% on Terminal-Bench 2.0.

Laguna XS.2 is our second-generation MoE and our first open-weight model, built on everything we've learned since training Laguna M.1 across data, including synthetic, and RL. At 33B total parameters with 3B activated (30T tokens trained), it's a highly capable open-weight agentic coding model in its weight class, reaching 44.5% on SWE-Bench Pro and 30.1% on Terminal-Bench 2.0. The weights are available for download today under Apache 2.0.

Model building

We train all our models from scratch. That means our own data work, our own training codebase (Titan), and our own agent RL infrastructure. Laguna pushed the limits of that stack, particularly across three domains: our data pipeline including synthetic data, how we optimized the efficiency of the Muon optimizer, and our async on-policy RL scheme.

Data and automixing

Both Laguna M.1 and XS.2 were trained on more than 30T tokens. Reaching that scale, and using it productively in training, required pushing the limits of data generation, processing, curation, and mixing.

Large-scale web data

We take great care in building and curating our datasets. We model quality as a continuous, multi-dimensional signal and rank data using a composite score. Crucially, we don't only keep top-quality data, retaining portions of mid- and lower-quality buckets to preserve diversity, critical for generalization.

Synthetic data

In Laguna XS.2, synthetic data contributes about 13% of the final training mix throughout all pre-training stages, building on organic data rather than replacing it, and expanding where it falls short. The Laguna series uses approximately 4.4T+ synthetic tokens.

AutoMixer: data mixture optimization

We developed an automixing framework to systematically explore and optimize pre-training data mixtures, training a swarm of ~60 sufficiently large proxy models on different data mixes and measuring performance across key capability groups.

Muon

Through all training stages of Laguna XS.2 and Laguna M.1, we used an internal distributed implementation of the Muon optimizer. Our implementation assigns each parameter and gradient to only one of the ranks sharding it, which effectively removes the compute bottleneck of the Muon optimizer.

Agent RL

To train our models to excel at long-horizon agentic tasks, we built a fully asynchronous online RL system that uses our agentic harness inside the training loop, running across large quantities of realistic end-to-end software engineering tasks.

Get started

Laguna M.1 and Laguna XS.2 are free to use for a limited time. Jump straight into Shimmer, or download pool. You can also get started on OpenRouter.