Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs

• URL: http://arxiv.org/abs/2506.14731v2
• Date: Wed, 18 Jun 2025 02:53:14 GMT
• Title: Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs
• Authors: Ling Team, Bin Hu, Cai Chen, Deng Zhao, Ding Liu, Dingnan Jin, Feng Zhu, Hao Dai, Hongzhi Luan, Jia Guo, Jiaming Liu, Jiewei Wu, Jun Mei, Jun Zhou, Junbo Zhao, Junwu Xiong, Kaihong Zhang, Kuan Xu, Lei Liang, Liang Jiang, Liangcheng Fu, Longfei Zheng, Qiang Gao, Qing Cui, Quan Wan, Shaomian Zheng, Shuaicheng Li, Tongkai Yang, Wang Ren, Xiaodong Yan, Xiaopei Wan, Xiaoyun Feng, Xin Zhao, Xinxing Yang, Xinyu Kong, Xuemin Yang, Yang Li, Yingting Wu, Yongkang Liu, Zhankai Xu, Zhenduo Zhang, Zhenglei Zhou, Zhenyu Huang, Zhiqiang Zhang, Zihao Wang, Zujie Wen,
• Abstract summary: Ring-lite is a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL)<n>Our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks.
• Score: 51.21041884010009
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Ring-lite, a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL) to achieve efficient and robust reasoning capabilities. Built upon the publicly available Ling-lite model, a 16.8 billion parameter model with 2.75 billion activated parameters, our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks (e.g., AIME, LiveCodeBench, GPQA-Diamond) while activating only one-third of the parameters required by comparable models. To accomplish this, we introduce a joint training pipeline integrating distillation with RL, revealing undocumented challenges in MoE RL training. First, we identify optimization instability during RL training, and we propose Constrained Contextual Computation Policy Optimization(C3PO), a novel approach that enhances training stability and improves computational throughput via algorithm-system co-design methodology. Second, we empirically demonstrate that selecting distillation checkpoints based on entropy loss for RL training, rather than validation metrics, yields superior performance-efficiency trade-offs in subsequent RL training. Finally, we develop a two-stage training paradigm to harmonize multi-domain data integration, addressing domain conflicts that arise in training with mixed dataset. We will release the model, dataset, and code.

Related papers

• DiRL: An Efficient Post-Training Framework for Diffusion Language Models [54.405206032785706]
  Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models.<n>Existing methods suffer from computational inefficiency and objective mismatches between training and inference.<n>We introduce DiRL, an efficient post-training framework that tightly integrates FlexAttention-accelerated blockwise training with LMDeploy-optimized inference.
  arXiv  Detail & Related papers  (2025-12-23T08:33:19Z)
• 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)
• DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning [37.20873499361773]
  We propose a unified framework for training masked diffusion large language models (dLLMs) to reason better (furious)<n>We first unify the existing baseline approach by proposing to train surrogate policies via off-policy RL, whose likelihood is much more tractable as an approximation to the true dLLM policy.<n>We also propose a new direction of joint training efficient samplers/controllers of dLLMs policy. Via RL, we incentivize dLLMs' natural multi-token prediction capabilities by letting the model learn to adaptively allocate an inference threshold for each prompt.
  arXiv  Detail & Related papers  (2025-10-02T16:57:24Z)
• Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS [62.22644307952087]
  We introduce AIRL-S, the first natural unification of RL-based and search-based TTS.<n>We leverage adversarial inverse reinforcement learning (AIRL) combined with group relative policy optimization (GRPO) to learn a dense, dynamic PRM directly from correct reasoning traces.<n>Our results show that our unified approach improves performance by 9 % on average over the base model, matching GPT-4o.
  arXiv  Detail & Related papers  (2025-08-19T23:41:15Z)
• How to Train Your LLM Web Agent: A Statistical Diagnosis [102.04125085041473]
  We present the first statistically grounded study on compute allocation for LLM web-agent post-training.<n>Our approach uses a two-stage pipeline, training a Llama 3.1 8B student to imitate a Llama 3.3 70B teacher via supervised fine-tuning (SFT) and on-policy reinforcement learning.<n>Our results show that combining SFT with on-policy RL consistently outperforms either approach alone on both WorkArena and MiniWob++.
  arXiv  Detail & Related papers  (2025-07-05T17:12:33Z)
• Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning [93.00629872970364]
  Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks.<n>We introduce SPARKLE, a fine-grained analytic framework to dissect the effects of RL across three key dimensions.<n>We study whether difficult problems -- those yielding no RL signals and mixed-quality reasoning traces -- can still be effectively used for training.
  arXiv  Detail & Related papers  (2025-06-05T07:53:59Z)
• Flow-GRPO: Training Flow Matching Models via Online RL [75.70017261794422]
  We propose Flow-GRPO, the first method integrating online reinforcement learning (RL) into flow matching models.<n>Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Equation (ODE) into an equivalent Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original inference timestep number.
  arXiv  Detail & Related papers  (2025-05-08T17:58:45Z)
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining [74.83412846804977]
  Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models.<n>We present a systematic end-to-end study of RL fine-tuning for mathematical reasoning by training models entirely from scratch.
  arXiv  Detail & Related papers  (2025-04-10T17:15:53Z)
• On the Emergence of Thinking in LLMs I: Searching for the Right Intuition [34.32871896067864]
  We propose a post-training framework called Reinforcement Learning via Self-Play (RLSP)<n> RLSP involves three steps: supervised fine-tuning with human or synthetic demonstrations of the reasoning process, using an exploration reward signal to encourage diverse and efficient reasoning behaviors, and RL training with an outcome verifier to ensure correctness while preventing reward hacking.<n> Empirical studies in the math domain show that RLSP improves reasoning.
  arXiv  Detail & Related papers  (2025-02-10T18:52:04Z)
• Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging [36.00016254809852]
  This paper systematically compares the effectiveness of model merging and data mixture methods in constructing 3H-aligned LLMs.<n>We propose a novel textbfReweighting textbfEnhanced task textbfSingular textbfMerging method, textbfRESM, through outlier weighting and sparsity-aware rank selection strategies.
  arXiv  Detail & Related papers  (2025-02-08T11:56:58Z)
• Model-Based Transfer Learning for Contextual Reinforcement Learning [5.5597941107270215]
  We introduce Model-Based Transfer Learning to solve contextual RL problems.<n>We show theoretically that the method exhibits sublinear regret in the number of training tasks.<n>We experimentally validate our methods using urban traffic and standard continuous control benchmarks.
  arXiv  Detail & Related papers  (2024-08-08T14:46:01Z)
• Heuristic Algorithm-based Action Masking Reinforcement Learning (HAAM-RL) with Ensemble Inference Method [0.0]
  This paper presents a novel reinforcement learning approach called HAAMRL (Heuristic ensemble-based Action Masking Reinforcement Learning) The proposed approach exhibits superior performance and capability generalization, indicating superior effectiveness in optimizing complex manufacturing processes.
  arXiv  Detail & Related papers  (2024-03-21T03:42:39Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Task Aware Modulation using Representation Learning: An Approach for Few Shot Learning in Environmental Systems [15.40286222692196]
  TAM-RL is a novel framework for few-shot learning in heterogeneous systems. We evaluate TAM-RL on two real-world environmental datasets.
  arXiv  Detail & Related papers  (2023-10-07T07:55:22Z)
• Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration [87.53543137162488]
  We propose an easy-to-implement online reinforcement learning (online RL) framework called textttMEX. textttMEX integrates estimation and planning components while balancing exploration exploitation automatically. It can outperform baselines by a stable margin in various MuJoCo environments with sparse rewards.
  arXiv  Detail & Related papers  (2023-05-29T17:25:26Z)

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.