Role-Based Fault Tolerance System for LLM RL Post-Training

• URL: http://arxiv.org/abs/2512.22492v1
• Date: Sat, 27 Dec 2025 06:30:18 GMT
• Title: Role-Based Fault Tolerance System for LLM RL Post-Training
• Authors: Zhenqian Chen, Baoquan Zhong, Xiang Li, Qing Dai, Xinkui Zhao, Miao Ye, Ren Cheng, Lufei Zhang, Jianwei Yin,
• Abstract summary: RL post-training interleaves training and inference workloads, exposing the system to faults from both sides.<n>Our key insight is role-based fault isolation so the failure in one machine does not affect the others.<n>We present RobustRL, the first comprehensive robust system to handle GPU machine errors for RL post-training Effective Training Time Ratio improvement.
• Score: 24.163081819380647
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: RL post-training for LLMs has been widely scaled to enhance reasoning and tool-using capabilities. However, RL post-training interleaves training and inference workloads, exposing the system to faults from both sides. Existing fault tolerance frameworks for LLMs target either training or inference, leaving the optimization potential in the asynchronous execution unexplored for RL. Our key insight is role-based fault isolation so the failure in one machine does not affect the others. We treat trainer, rollout, and other management roles in RL training as distinct distributed sub-tasks. Instead of restarting the entire RL task in ByteRobust, we recover only the failed role and reconnect it to living ones, thereby eliminating the full-restart overhead including rollout replay and initialization delay. We present RobustRL, the first comprehensive robust system to handle GPU machine errors for RL post-training Effective Training Time Ratio improvement. (1) \textit{Detect}. We implement role-aware monitoring to distinguish actual failures from role-specific behaviors to avoid the false positive and delayed detection. (2) \textit{Restart}. For trainers, we implement a non-disruptive recovery where rollouts persist state and continue trajectory generation, while the trainer is rapidly restored via rollout warm standbys. For rollout, we perform isolated machine replacement without interrupting the RL task. (3) \textit{Reconnect}. We replace static collective communication with dynamic, UCX-based (Unified Communication X) point-to-point communication, enabling immediate weight synchronization between recovered roles. In an RL training task on a 256-GPU cluster with Qwen3-8B-Math workload under 10\% failure injection frequency, RobustRL can achieve an ETTR of over 80\% compared with the 60\% in ByteRobust and achieves 8.4\%-17.4\% faster in end-to-end training time.

Related papers

• RollArt: Scaling Agentic RL Training via Disaggregated Infrastructure [49.88201789074532]
  Agentic Reinforcement Learning (RL) enables Large Language Models (LLMs) to perform autonomous decision-making and long-term planning.<n>We present RollArc, a distributed system designed to maximize throughput for multi-task agentic RL on disaggregated infrastructure.
  arXiv  Detail & Related papers  (2025-12-27T11:14:23Z)
• 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)
• Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning [6.742598086990326]
  Reinforcement Learning (RL) has become critical for advancing modern Large Language Models (LLMs), yet existing synchronous RL systems face severe performance bottlenecks.<n>We present Seer, a novel online context learning system that addresses these challenges by exploiting previously overlooked similarities in output lengths and generation patterns among requests sharing the same prompt.<n>Seer introduces three key techniques: divided rollout for dynamic load balancing, context-aware scheduling, and adaptive grouped speculative decoding.
  arXiv  Detail & Related papers  (2025-11-18T16:12:21Z)
• RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs [48.94639777633359]
  We present RLBoost, a systematic solution for cost-efficient RL training that harvests preemptible GPU resources.<n> RLBoost increases training throughput by 1.51x-1.97x while improving cost efficiency by 28%-49% compared to using only on-demand GPU resources.
  arXiv  Detail & Related papers  (2025-10-22T04:19:37Z)
• Laminar: A Scalable Asynchronous RL Post-Training Framework [20.127034898123508]
  Long-tail skewness in RL trajectory generation causes severe GPU underutilization.<n>Current RL systems rely on global weight synchronization between the actor and all rollouts, which creates a rigid model update schedule.<n>We propose Laminar, a scalable and robust RL post-training system built on a fully decoupled architecture.
  arXiv  Detail & Related papers  (2025-10-14T15:29:14Z)
• RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training [19.00988498482758]
  Reinforcement Learning (RL) is a pivotal post-training technique for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Many RL systems attempt to alleviate this problem by relaxing synchronization, but this can compromise accuracy training.<n>We introduce tail, a novel rollout scheduling strategy for synchronous RL that systematically consolidates prompts leading to long-tail responses into a small subset of rollout steps (long rounds)<n>RollPacker achieves a 2.03x-2.56x end-to-end training time reduction compared to veRL and up to 2.24x speedup compared to RLHFuse for the Qwen2.5
  arXiv  Detail & Related papers  (2025-09-25T11:13:22Z)
• History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL [14.506189610798929]
  Reinforcement learning (RL) has emerged as a pivotal methodology for enhancing the reasoning capabilities of large language models (LLMs)<n>We introduce RhymeRL, an LLM RL system designed to accelerate RL training with two key innovations.<n>First, to enhance rollout generation, we present HistoSpec, a speculative decoding inference engine.<n>Second, to tackle rollout bubbles, we introduce HistoPipe, a two-tier scheduling strategy.
  arXiv  Detail & Related papers  (2025-08-26T01:42:46Z)
• AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning [23.24949857136035]
  Reinforcement learning (RL) has become a dominant paradigm for training large language models (LLMs)<n>We present AReaL, a fully asynchronous RL system that completely decouples generation from training.
  arXiv  Detail & Related papers  (2025-05-30T07:18:25Z)
• StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation [55.75008325187133]
  Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs)<n>StreamRL is designed with disaggregation from first principles to address two types of performance bottlenecks.<n> Experiments show that StreamRL improves throughput by up to 2.66x compared to existing state-of-the-art systems.
  arXiv  Detail & Related papers  (2025-04-22T14:19:06Z)
• Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training [71.16258800411696]
  Reinforcement learning (RL) is a critical component of large language model (LLM) post-training.<n>Existing on-policy algorithms used for post-training are inherently incompatible with the use of experience replay buffers.<n>We propose efficiently obtaining this benefit of replay buffers via Trajectory Balance with Asynchrony (TBA)
  arXiv  Detail & Related papers  (2025-03-24T17:51:39Z)
• Unsupervised-to-Online Reinforcement Learning [59.910638327123394]
  Unsupervised-to-online RL (U2O RL) replaces domain-specific supervised offline RL with unsupervised offline RL. U2O RL not only enables reusing a single pre-trained model for multiple downstream tasks, but also learns better representations. We empirically demonstrate that U2O RL achieves strong performance that matches or even outperforms previous offline-to-online RL approaches.
  arXiv  Detail & Related papers  (2024-08-27T05:23:45Z)

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.