MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes

• URL: http://arxiv.org/abs/2509.24945v2
• Date: Tue, 30 Sep 2025 18:16:06 GMT
• Title: MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
• Authors: Changsheng Zhao, Ernie Chang, Zechun Liu, Chia-Jung Chang, Wei Wen, Chen Lai, Sheng Cao, Yuandong Tian, Raghuraman Krishnamoorthi, Yangyang Shi, Vikas Chandra,
• Abstract summary: We show that strong reasoning abilities can emerge with far less data.<n>MobileLLM-R50M achieves an AIME score of 15.5, compared to just 0.6 for OLMo-2-1.48B and 0.3 for SmolLM-2-1.7B.
• Score: 60.57770396565211
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The paradigm shift in large language models (LLMs) from instinctive responses to chain-of-thought (CoT) reasoning has fueled two prevailing assumptions: (1) reasoning capabilities only emerge in sufficiently large models, and (2) such capabilities require training on massive datasets. While the first assumption has already been challenged by recent sub-billion-parameter reasoning models such as Qwen3-0.6B and DeepSeek distilled variants, the second remains largely unquestioned. In this work, we revisit the necessity of scaling to extremely large corpora (>10T tokens) for reasoning emergence. By carefully curating and resampling open-source datasets that we identify as beneficial under our designed metrics, we demonstrate that strong reasoning abilities can emerge with far less data. Specifically, we show that only ~2T tokens of high-quality data are sufficient, and pre-training with 4.2T tokens on the dataset resampled from these ~2T tokens, followed by a established post-training procedure, enables the development of MobileLLM-R1, a series of sub-billion-parameter reasoning models that substantially outperform prior models trained on fully open-sourced data. For example, MobileLLM-R1-950M achieves an AIME score of 15.5, compared to just 0.6 for OLMo-2-1.48B and 0.3 for SmolLM-2-1.7B. Remarkably, despite being trained on only 11.7% of the tokens compared to Qwen3's proprietary 36T-token corpus for pretraining, MobileLLM-R1-950M matches or surpasses Qwen3-0.6B across multiple reasoning benchmarks. To facilitate further research in this direction, we have released the complete training recipe, data sources, data mixing ratio, and model checkpoints, together with the key insights obtained throughout this study.

Related papers

• RefineBench: Evaluating Refinement Capability of Language Models via Checklists [71.02281792867531]
  We evaluate two refinement modes: guided refinement and self-refinement.<n>In guided refinement, both proprietary LMs and large open-weight LMs can leverage targeted feedback to refine responses to near-perfect levels within five turns.<n>These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses.
  arXiv  Detail & Related papers  (2025-11-27T07:20:52Z)
• Diffusion Language Models are Super Data Learners [61.721441061210896]
  When unique data is limited, diffusion language models (DLMs) consistently surpass autoregressive (AR) models by training for more epochs.<n>We attribute the gains to three compounding factors: (1) any-order modeling, (2) super-dense compute from iterative bidirectional denoising, and (3) built-in Monte Carlo augmentation.
  arXiv  Detail & Related papers  (2025-11-05T08:17:42Z)
• Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model [100.86587937568832]
  Ring-1T is the first open-source, state-of-the-art thinking model with a trillion-scale parameter.<n>It features 1 trillion total parameters and activates approximately 50 billion per token.
  arXiv  Detail & Related papers  (2025-10-21T17:46:14Z)
• CoRT: Code-integrated Reasoning within Thinking [44.778344623138025]
  Large Reasoning Models (LRMs) like o1 and DeepSeek-R1 have shown remarkable progress in natural language reasoning with long chain-of-thought (CoT)<n>Addressing these limitations through computational tools is promising, but it introduces a technical challenge: Code Interpreter (CI) brings external knowledge beyond the model's internal text representations.<n>This paper introduces CoRT, a post-training framework for teaching LRMs to leverage CI effectively and efficiently.
  arXiv  Detail & Related papers  (2025-06-11T14:59:02Z)
• Not All Correct Answers Are Equal: Why Your Distillation Source Matters [16.441081996257576]
  Distillation has emerged as a practical and effective approach to enhance the reasoning capabilities of open-source language models.<n>We collect verified outputs from three state-of-the-art teacher models-AM-Thinking-v1, Qwen3-235B-A22B, and DeepSeek-R1-on a shared corpus of 1.89 million queries.<n>Student models trained on each dataset are evaluated on reasoning benchmarks including AIME2024, AIME2025, MATH500, and LiveCodeBench.
  arXiv  Detail & Related papers  (2025-05-20T15:00:51Z)
• R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model [70.77691645678804]
  We present the first successful replication of emergent characteristics for multimodal reasoning on only a non-SFT 2B model.<n>Our model achieves 59.47% accuracy on CVBench, outperforming the base model by approximately 30% and exceeding both SFT setting by 2%.<n>In addition, we share our failed attempts and insights in attempting to achieve R1-like reasoning using RL with instruct models.
  arXiv  Detail & Related papers  (2025-03-07T04:21:47Z)
• LIMR: Less is More for RL Scaling [25.477841726836836]
  We introduce Learning Impact Measurement (LIM), an automated method to evaluate and prioritize training samples.<n>Our method achieves comparable or even superior performance using only 1,389 samples versus the full 8,523 samples dataset.<n>For reproducible research and future innovation, we are open-sourcing LIMR, including implementation of LIM, training and evaluation code, curated datasets, and trained models.
  arXiv  Detail & Related papers  (2025-02-17T15:13:29Z)
• T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling [52.34735382627312]
  Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks.<n>Existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling.<n>We present T1 to scale reinforcement learning by encouraging exploration and understand inference scaling.
  arXiv  Detail & Related papers  (2025-01-20T18:33:33Z)
• TextSquare: Scaling up Text-Centric Visual Instruction Tuning [62.878378882175284]
  We introduce a new approach for creating a massive, high-quality instruction-tuning dataset, Square-10M.<n>Our model, TextSquare, considerably surpasses open-source previous state-of-the-art Text-centric MLLMs.<n>It even outperforms top-tier models like GPT4V and Gemini in 6 of 10 text-centric benchmarks.
  arXiv  Detail & Related papers  (2024-04-19T11:38:08Z)

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.