Reinforcement Mid-Training

• URL: http://arxiv.org/abs/2509.24375v1
• Date: Mon, 29 Sep 2025 07:21:24 GMT
• Title: Reinforcement Mid-Training
• Authors: Yijun Tian, Shaoyu Chen, Zhichao Xu, Yawei Wang, Jinhe Bi, Peng Han, Wei Wang,
• Abstract summary: We propose a framework for efficient, adaptive, and unified reinforcement mid-training.<n>We show that RMT achieves up to +64.91% performance improvement with only 21% of the reasoning length in language modeling.<n>We also show that checkpoints obtained after reinforcement mid-training can benefit the subsequent post-training, yielding up to +18.76% improvement in the mathematical domain.
• Score: 16.826401071555704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training with potential for strong performance gains. In this paper, we formally define the problem and identify three key challenges: (1) inefficient training due to excessive reasoning steps, (2) disregard of the imbalanced token entropy distribution, and (3) underutilization of token information. To address these challenges, we propose RMT, a framework for efficient, adaptive, and unified reinforcement mid-training with various innovative components. In particular, we first introduce a dynamic token budget mechanism that constrains unnecessary reasoning steps and mitigates model overthinking. Next, we design a curriculum-based adaptive sampling method that fosters a progressive learning trajectory from easy to hard tokens. Finally, we present a dual training strategy that combines reinforcement learning with next-token prediction, ensuring targeted learning on key tokens and full exploitation of all token information. Extensive experiments demonstrate the superiority of RMT over state-of-the-art methods, achieving up to +64.91% performance improvement with only 21% of the reasoning length in language modeling. We also show that checkpoints obtained after reinforcement mid-training can benefit the subsequent post-training, yielding up to +18.76% improvement in the mathematical domain.

Related papers

• ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution [49.496216822640974]
  We analyze training dynamics and identify the mid-training phase as a critical turning point for model capabilities.<n>We introduce ReMiT (Reinforcement Learning-Guided Mid-Training), which prioritizes tokens during the mid-training phase, prioritizing those pivotal for reasoning.
  arXiv  Detail & Related papers  (2026-02-03T04:04:41Z)
• On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models [73.10315509190623]
  Recent reinforcement learning techniques have yielded impressive reasoning improvements in language models.<n>It remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during pre-training.<n>We develop a fully controlled experimental framework that isolates the causal contributions of pre-training, mid-training, and RL-based post-training.
  arXiv  Detail & Related papers  (2025-12-08T18:12:10Z)
• RLP: Reinforcement as a Pretraining Objective [103.45068938532923]
  We present an information-driven reinforcement pretraining objective that brings the core spirit of reinforcement learning -- exploration -- to the last phase of pretraining.<n>This training objective essentially encourages the model to think for itself before predicting what comes next, thus teaching an independent thinking behavior earlier in the pretraining.<n> Specifically, RLP reframes reinforcement learning for reasoning as a pretraining objective on ordinary text, bridging the gap between next-token prediction and the emergence of useful chain-of-thought reasoning.
  arXiv  Detail & Related papers  (2025-09-26T17:53:54Z)
• Thinking Augmented Pre-training [88.04395622064708]
  Thinking augmented Pre-Training is a universal methodology that augments text with automatically generated thinking trajectories.<n>This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories.
  arXiv  Detail & Related papers  (2025-09-24T14:45:13Z)
• EvoLM: In Search of Lost Language Model Training Dynamics [97.69616550374579]
  EvoLM is a model suite that enables systematic and transparent analysis of LMs' training dynamics across pre-training, continued pre-training, supervised fine-tuning, and reinforcement learning.<n>By training over 100 LMs with 1B and 4B parameters from scratch, we rigorously evaluate both upstream (language modeling) and downstream (problem-solving) reasoning capabilities.
  arXiv  Detail & Related papers  (2025-06-19T04:58:47Z)
• The Surprising Effectiveness of Test-Time Training for Few-Shot Learning [59.309477460893916]
  Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks.<n>We investigate the effectiveness of test-time training (TTT) as a mechanism for improving LMs' reasoning and few-shot learning capabilities.<n>Our findings highlight the limitations of in-context learning for novel tasks and demonstrate the potential of test-time training to enhance language model adaptability.
  arXiv  Detail & Related papers  (2024-11-11T18:59:45Z)
• How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies [3.1836117900874825]
  Early exits enable the network's forward pass to terminate early by attaching trainable internal classifiers to the backbone network.<n>Existing early-exit methods typically adopt either a joint training approach, where the backbone and exit heads are trained simultaneously, or a disjoint approach, where the heads are trained separately.<n>This paper introduces a set of metrics to analyze early-exit training dynamics and guide the choice of training strategy.
  arXiv  Detail & Related papers  (2024-07-19T13:56:57Z)
• Boosting Meta-Training with Base Class Information for Few-Shot Learning [35.144099160883606]
  We propose an end-to-end training paradigm consisting of two alternative loops. In the outer loop, we calculate cross entropy loss on the entire training set while updating only the final linear layer. This training paradigm not only converges quickly but also outperforms existing baselines, indicating that information from the overall training set and the meta-learning training paradigm could mutually reinforce one another.
  arXiv  Detail & Related papers  (2024-03-06T05:13:23Z)
• Efficient Stagewise Pretraining via Progressive Subnetworks [53.00045381931778]
  The prevailing view suggests that stagewise dropping strategies, such as layer dropping, are ineffective when compared to stacking-based approaches. This paper challenges this notion by demonstrating that, with proper design, dropping strategies can be competitive, if not better, than stacking methods. We propose an instantiation of this framework - Random Part Training (RAPTR) - that selects and trains only a random subnetwork at each step, progressively increasing the size in stages.
  arXiv  Detail & Related papers  (2024-02-08T18:49:09Z)
• Curriculum Learning: A Regularization Method for Efficient and Stable Billion-Scale GPT Model Pre-Training [18.640076155697415]
  We present a study of a curriculum learning based approach, which helps improve the pre-training convergence speed of autoregressive models. Our evaluations demonstrate that curriculum learning enables training GPT-2 models with 8x larger batch size and 4x larger learning rate.
  arXiv  Detail & Related papers  (2021-08-13T06:32:53Z)

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.