Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs
This work addresses the challenge of scalable and efficient reasoning for AI applications, though it appears incremental as it builds upon existing models and methods.
The paper tackled the problem of achieving efficient reasoning in large language models by introducing Ring-lite, a Mixture-of-Experts model optimized via reinforcement learning, which matches state-of-the-art performance on benchmarks like AIME and GPQA-Diamond while activating only one-third of the parameters of comparable models.
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.