南北阁4.1-3B：一个具备推理、对齐与行动能力的小型通用模型

摘要

我们推出南贝阁4.1-3B模型，这是一个仅用30亿参数就同时实现强大智能体行为、代码生成与通用推理能力的统一通用语言模型。据我们所知，这是首个在单一模型中实现如此多功能的开源小语言模型（SLM）。为提升推理能力与偏好对齐，我们结合点对点和配对奖励建模技术，确保生成高质量且符合人类偏好的响应。在代码生成方面，我们通过强化学习设计复杂度感知奖励机制，同步优化正确性与执行效率。针对深度搜索任务，我们实施复杂数据合成策略，并在训练阶段引入轮次级监督机制，使模型能够稳定进行长周期工具交互——南贝阁4.1-3B可可靠执行多达600轮工具调用以解决复杂问题。大量实验结果表明，南贝阁4.1-3B显著超越同规模先前模型（如Nanbeige4-3B-2511和Qwen3-4B），甚至在某些任务上优于参数量大得多的Qwen3-30B-A3B模型。我们的研究成果证明，小模型能够同时实现广泛能力与专业优势，重新定义了30亿参数级模型的发展潜力。

English

We present Nanbeige4.1-3B, a unified generalist language model that simultaneously achieves strong agentic behavior, code generation, and general reasoning with only 3B parameters. To the best of our knowledge, it is the first open-source small language model (SLM) to achieve such versatility in a single model. To improve reasoning and preference alignment, we combine point-wise and pair-wise reward modeling, ensuring high-quality, human-aligned responses. For code generation, we design complexity-aware rewards in Reinforcement Learning, optimizing both correctness and efficiency. In deep search, we perform complex data synthesis and incorporate turn-level supervision during training. This enables stable long-horizon tool interactions, allowing Nanbeige4.1-3B to reliably execute up to 600 tool-call turns for complex problem-solving. Extensive experimental results show that Nanbeige4.1-3B significantly outperforms prior models of similar scale, such as Nanbeige4-3B-2511 and Qwen3-4B, even achieving superior performance compared to much larger models, such as Qwen3-30B-A3B. Our results demonstrate that small models can achieve both broad competence and strong specialization simultaneously, redefining the potential of 3B parameter models.

南北阁4.1-3B：一个具备推理、对齐与行动能力的小型通用模型

Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts

摘要

Support