---
id: 20260529-T0-12
title: "Laguna M.1/XS.2：支持长序列编码的混合专家模型"
title_en: "Laguna M.1/XS.2: Long-Horizon MoE Models for Agentic Coding"
url: https://ai.daily.yangsir.net/daily/20260529-T0-12
issue_date: 2026-05-29
publish_date: 2026-05-28T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2605.27605
---

# Laguna M.1/XS.2：支持长序列编码的混合专家模型

arXiv发布Laguna M.1和XS.2两款面向长序列、智能编程任务的混合专家模型。M.1总参数量2258亿（单token激活234亿），XS.2总参数量334亿（单token激活30亿）。两者均针对长序列任务优化，参数效率显著提升。开发者可用其构建更高效的代码生成助手，降低推理成本。

## English Version

**Laguna M.1/XS.2: Long-Horizon MoE Models for Agentic Coding**

arXiv released Laguna M.1 and XS.2, two MoE models designed for long-horizon, agentic coding. M.1 has 225.8B total parameters (23.4B activated per token), while XS.2 has 33.4B total (3B activated). Both models optimize parameter efficiency for long tasks, enabling developers to build cost-effective code generation assistants with reduced inference overhead.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2605.27605)

**详情页**：https://ai.daily.yangsir.net/daily/20260529-T0-12

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*