Model release notes

​

Laguna XS 2.1

• Context window: 256K tokens
• Model type: Mixture of Experts (MoE)
• Supported modes: Agentic, Chat
• Modality: Text only

• Native reasoning support: Interleaved thinking between tool calls, with the ability to enable or disable thinking per request.
• Better multilingual coding results: Improves SWE-bench Multilingual by +5.4% (57.7% to 63.1%) over XS.2.
• Better terminal task execution: Improves Terminal-Bench 2.0 by +1.8% (35.7% to 37.5%) over XS.2.
• Lower memory per token: KV cache quantized to FP8.

• Laguna XS 2.1 is designed for Poolside Agent CLI workflows and OpenAI-compatible API integrations.
• Laguna XS 2.1 is text-in, text-out only and does not support vision inputs.

​

Laguna M.1

• Context window: 256K tokens
• Model type: Mixture of Experts (MoE)
• Supported modes: Agentic, Chat
• Modality: Text only

• Debug and fix issues across multiple files
• Explore unfamiliar code and explain what it finds
• Run longer task sequences that require tool use and verification
• Work through coding tasks where tests, commands, or other checks are available

• Stronger coding performance: Laguna M.1 improves SWE-bench Verified from 55.6% in Malibu 2.2 to 65.4%.
• Better multilingual coding results: Laguna M.1 improves SWE-bench Multilingual from 31.1% in Malibu 2.2 to 57.4%.
• Better agentic task execution: Laguna M.1 improves Terminal-Bench 2.0 from 16.9% in Malibu 2.2 to 32.7%.

• Give Laguna M.1 a clear task with the specific outcome you want.
• Include relevant context such as file paths, error messages, failing tests, or reference material.
• State any important constraints up front, such as coding standards, files to avoid, or commands the agent should run.
• Expect better results when the environment includes tools the agent can use to verify its work.

• Laguna M.1 is designed for Poolside Agent CLI workflows and OpenAI-compatible API integrations.
• Laguna M.1 is text-in, text-out only and does not support vision inputs.
• Performance depends on the quality of the instructions and context you provide, the tools available to the agent, and whether the environment supports validation steps such as tests or executable checks.

​

Laguna XS.2

• Context window: 256K tokens
• Model type: Mixture of Experts (MoE)
• Supported modes: Agentic, Chat
• Modality: Text only

• Debug and fix issues across multiple files
• Explore unfamiliar code and explain what it finds
• Run well-defined coding tasks that require fast performance
• Deploy Poolside on hardware with GPU constraints

• Stronger coding performance: Laguna XS.2 improves SWE-bench Verified from 55.6% in Malibu 2.2 to 64%.
• Better multilingual coding results: Laguna XS.2 improves SWE-bench Multilingual from 31.1% in Malibu 2.2 to 60%.
• Better agentic task execution: Laguna XS.2 improves Terminal-Bench 2.0 from 16.9% in Malibu 2.2 to 29%.

• Give Laguna XS.2 a clear task with the specific outcome you want.
• Include relevant context such as file paths, error messages, failing tests, or reference material.
• State any important constraints up front, such as coding standards, files to avoid, or commands the agent should run.
• Expect better results when the environment includes tools the agent can use to verify its work.
• Keep tasks self-contained by planning with the model.

• Laguna XS.2 is designed for Poolside Agent CLI workflows and OpenAI-compatible API integrations.
• Laguna XS.2 is text-in, text-out only and does not support vision inputs.
• Performance depends on the quality of the instructions and context you provide, the tools available to the agent, and whether the environment supports validation steps such as tests or executable checks.

​

Malibu 2.2

• Context window: 128,000 tokens
• Model type: Dense
• Supported modes: Agentic, Chat

• Please figure out why step_events is null in @trajectory.jsx.
• Can you debug this 500 request? <insert-your-stack-trace>.
• Can you give me an overview of how ResponseProvider works and how it interacts with TrajectorySource? Where does it store trajectories?

• Read files and folders to understand project structure.
• Edit files.
• Run programs, such as linters, compilers, tests, or local services, to validate its edits.

• Give Malibu Agent as much context as possible if you have a specific bug, including stack traces and references to files that may be useful.
• If Malibu Agent is unable to solve an issue, break your request down into smaller, incremental changes, or be more direct. For example, write Make X change instead of Implement this feature.

• Malibu Agent can be over-reactive to simple commands like hi or how are you today?. Because it is trained to solve issues, it interprets these simple commands as problems to solve and attempts to solve them. This is a known issue.
• Malibu Agent can make edits to files unrelated to the task. If this occurs, use the checkpointing feature to roll back its changes.
• Malibu Agent can sometimes create test scripts to validate its changes, but forget to delete them. Check to make sure you do not commit these to version control.

​

Malibu 2.1

• Context window: 32,000 tokens

• Code editing: Malibu 2.1 was trained on an expanded set of RLCEF tasks, leading to better downstream performance at generating code edits that solve real-world problems.
• Instruction following: Malibu 2.1 went through additional training to understand and follow user instructions more accurately, especially over the course of long conversations.
• Multi-turn and long-context performance: Malibu v2 sometimes failed to generate high-quality edits in longer conversations and had degraded performance with many files added to its context. Malibu 2.1 addresses these limitations and performs better in these scenarios.
• Agent mode improvements: Malibu 2.1 has improved tool-calling abilities, which improves its accuracy when generating Agent mode commands to search for files.