菜单

关于 🐙 GitHub
arXiv 提交日期: 2025-12-31
📄 Abstract - Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models

We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that rely on distillation, Youtu-LLM (1.96B) is pre-trained from scratch to systematically cultivate reasoning and planning capabilities. The key technical advancements are as follows: (1) Compact Architecture with Long-Context Support: Built on a dense Multi-Latent Attention (MLA) architecture with a novel STEM-oriented vocabulary, Youtu-LLM supports a 128k context window. This design enables robust long-context reasoning and state tracking within a minimal memory footprint, making it ideal for long-horizon agent and reasoning tasks. (2) Principled "Commonsense-STEM-Agent" Curriculum: We curated a massive corpus of approximately 11T tokens and implemented a multi-stage training strategy. By progressively shifting the pre-training data distribution from general commonsense to complex STEM and agentic tasks, we ensure the model acquires deep cognitive abilities rather than superficial alignment. (3) Scalable Agentic Mid-training: Specifically for the agentic mid-training, we employ diverse data construction schemes to synthesize rich and varied trajectories across math, coding, and tool-use domains. This high-quality data enables the model to internalize planning and reflection behaviors effectively. Extensive evaluations show that Youtu-LLM sets a new state-of-the-art for sub-2B LLMs. On general benchmarks, it achieves competitive performance against larger models, while on agent-specific tasks, it significantly surpasses existing SOTA baselines, demonstrating that lightweight models can possess strong intrinsic agentic capabilities.

顶级标签: llm agents model training
详细标签: agentic pretraining lightweight llm reasoning tool use long context 或 搜索:

Youtu-LLM:一个通过智能体导向预训练解锁轻量级大语言模型智能体潜力的模型 / Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models


1️⃣ 一句话总结

本文提出了Youtu-LLM,一个1.96B参数的轻量级大语言模型,通过创新的智能体导向预训练范式、支持长上下文的紧凑架构以及大规模高质量智能体轨迹数据构建,系统性地培养了模型的推理、规划和工具使用等底层认知能力,在智能体任务上显著超越了同类甚至更大规模的模型。


2️⃣ 论文创新点

1. 智能体导向的预训练范式

2. 紧凑架构与长上下文支持

3. 可扩展的高质量智能体轨迹数据构建

4. 结构化智能体思维链(Agentic-CoT)

5. 多维数据分类与质量评分过滤方案


3️⃣ 主要结果与价值

结果亮点

实际价值


4️⃣ 术语表

源自 arXiv: 2512.24618