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

• URL: http://arxiv.org/abs/2602.13367v1
• Date: Fri, 13 Feb 2026 13:10:46 GMT
• Title: Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts
• Authors: Chen Yang, Guangyue Peng, Jiaying Zhu, Ran Le, Ruixiang Feng, Tao Zhang, Xiyun Xu, Yang Song, Yiming Jia, Yuntao Wen, Yunzhi Xu, Zekai Wang, Zhenwei An, Zhicong Sun, Zongchao Chen,
• Abstract summary: Nanbeige4.1-3B is an open-source small language model (SLM)<n>It simultaneously achieves strong agentic behavior, code generation, and general reasoning with only 3B parameters.<n>Our results demonstrate that small models can achieve both broad competence and strong specialization simultaneously.
• Score: 16.810363861148513
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents [75.67445299298949]
  AgentCPM-Explore is a compact 4B agent model with high knowledge density and strong exploration capability.<n>We introduce a holistic training framework featuring parameter-space model fusion, reward signal denoising, and contextual information refinement.<n>AgentCPM-Explore achieves state-of-the-art (SOTA) performance among 4B-class models, matches or surpasses 8B-class SOTA models on four benchmarks, and even outperforms larger-scale models such as Claude-4.5-Sonnet or DeepSeek-v3.2 in five benchmarks.
  arXiv  Detail & Related papers  (2026-02-06T08:24:59Z)
• Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models [23.832817775138675]
  Nanbeige4-3B is a family of small-scale but high-performing language models.<n>Pretrained on 23T high-quality tokens and finetuned on over 30 million diverse instructions, we extend the boundary of the scaling law for small language models.
  arXiv  Detail & Related papers  (2025-12-06T03:36:27Z)
• Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time [6.741914038966904]
  We introduce a lightweight component, Test-Time Steering Vectors (TTSV), which is prepended to the input while keeping the model's parameters entirely frozen.<n>TTSV is both lightweight and highly efficient to optimize, making it a true plug-and-play enhancement.<n>Our approach exhibits robust generalization, with its steering vectors proving highly transferable across diverse tasks.
  arXiv  Detail & Related papers  (2025-12-04T12:36:16Z)
• One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning [54.580646706013965]
  Reward models (RMs) play a critical role in aligning large language models with human preferences.<n>We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios.<n>To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling.
  arXiv  Detail & Related papers  (2025-10-30T06:08:27Z)
• SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models [88.29990536278167]
  We introduce SPaR, a self-play framework integrating tree-search self-refinement to yield valid and comparable preference pairs.<n>Our experiments show that a LLaMA3-8B model, trained over three iterations guided by SPaR, surpasses GPT-4-Turbo on the IFEval benchmark without losing general capabilities.
  arXiv  Detail & Related papers  (2024-12-16T09:47:43Z)
• Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
  We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T16:25:30Z)
• CodingTeachLLM: Empowering LLM's Coding Ability via AST Prior Knowledge [0.0]
  We introduce CodingTeachLLM, a large language model (LLM) designed for coding teaching.<n>Our model realizes the structural disassembly and incremental guided output of educational knowledge.<n>Our model also achieves state-of-the-art in code abilities compared to open-source models.
  arXiv  Detail & Related papers  (2024-03-13T05:38:39Z)
• Large Language Models Are Also Good Prototypical Commonsense Reasoners [11.108562540123387]
  Traditional fine-tuning approaches can be resource-intensive and potentially compromise a model's generalization capacity. We draw inspiration from the outputs of large models for tailored tasks and semi-automatically developed a set of novel prompts. With better designed prompts we can achieve the new state-of-art(SOTA) on the ProtoQA leaderboard.
  arXiv  Detail & Related papers  (2023-09-22T20:07:24Z)
• Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models [125.91897197446379]
  We find that MoE models benefit more from instruction tuning than dense models. Our most powerful model, FLAN-MOE-32B, surpasses the performance of FLAN-PALM-62B on four benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-24T04:22:26Z)
• Sparse MoEs meet Efficient Ensembles [49.313497379189315]
  We study the interplay of two popular classes of such models: ensembles of neural networks and sparse mixture of experts (sparse MoEs) We present Efficient Ensemble of Experts (E$3$), a scalable and simple ensemble of sparse MoEs that takes the best of both classes of models, while using up to 45% fewer FLOPs than a deep ensemble.
  arXiv  Detail & Related papers  (2021-10-07T11:58:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.