ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems

• URL: http://arxiv.org/abs/2510.26475v1
• Date: Thu, 30 Oct 2025 13:27:42 GMT
• Title: ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems
• Authors: Qiaoling Chen, Zijun Liu, Peng Sun, Shenggui Li, Guoteng Wang, Ziming Liu, Yonggang Wen, Siyuan Feng, Tianwei Zhang,
• Abstract summary: Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage.<n>We present ReSpec, a system that adapts Speculative decoding (SD) to RL through three complementary mechanisms.<n>On Qwen models (3B--14B), ReSpec achieves up to 4.5x speedup while preserving reward convergence and training stability.
• Score: 36.535922134181995
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in serving systems, but its behavior under RL training remains largely unexplored. We identify three critical gaps that hinder the naive integration of SD into RL systems: diminishing speedups at large batch sizes, drafter staleness under continual actor updates, and drafter-induced policy degradation. To address these gaps, we present ReSpec, a system that adapts SD to RL through three complementary mechanisms: dynamically tuning SD configurations, evolving the drafter via knowledge distillation, and weighting updates by rollout rewards. On Qwen models (3B--14B), ReSpec achieves up to 4.5x speedup while preserving reward convergence and training stability, providing a practical solution for efficient RL-based LLM adaptation.

Related papers

• Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates [53.3717573880076]
  We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates.<n>JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly.<n>Experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods.
  arXiv  Detail & Related papers  (2026-01-26T14:16:51Z)
• Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter [52.111923076688505]
  Training Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving.<n>We propose TLT, a system that accelerates reasoning RL training losslessly by integrating adaptive speculative decoding.
  arXiv  Detail & Related papers  (2025-11-20T18:59:25Z)
• 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)
• Beat the long tail: Distribution-Aware Speculative Decoding for RL Training [75.75462952580796]
  We propose a Distribution Aware Speculative decoding framework that accelerates RL rollouts without altering model outputs.<n>Experiments on math and code reasoning tasks show that DAS reduces rollout time up to 50% while preserving identical training curves.
  arXiv  Detail & Related papers  (2025-11-17T19:02:12Z)
• 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)
• QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs [80.76334908639745]
  We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs)<n>QeRL addresses issues by combining NVFP4 quantization with Low-Rank Adaptation (LoRA)<n>Experiments demonstrate that QeRL delivers over 1.5 times speedup in the rollout phase.
  arXiv  Detail & Related papers  (2025-10-13T17:55:09Z)
• SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts [35.82325476805143]
  SPEC-RL is a framework that integrates SPECulative decoding with the RL rollout process.<n>It reduces rollout time by 2-3x without compromising policy quality.<n>As a purely rollout-stage enhancement, SPEC-RL integrates seamlessly with mainstream algorithms.
  arXiv  Detail & Related papers  (2025-09-27T10:32:34Z)
• Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs [51.21041884010009]
  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.
  arXiv  Detail & Related papers  (2025-06-17T17:12:34Z)
• 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)
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning [125.96848846966087]
  Training large language models (LLMs) as interactive agents presents unique challenges.<n>While reinforcement learning has enabled progress in static tasks, multi-turn agent RL training remains underexplored.<n>We propose StarPO, a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents.
  arXiv  Detail & Related papers  (2025-04-24T17:57:08Z)
• Scalable Volt-VAR Optimization using RLlib-IMPALA Framework: A Reinforcement Learning Approach [11.11570399751075]
  This research presents a novel framework that harnesses the potential of Deep Reinforcement Learning (DRL) The integration of our DRL agent with the RAY platform facilitates the creation of RLlib-IMPALA, a novel framework that efficiently uses RAY's resources to improve system adaptability and control.
  arXiv  Detail & Related papers  (2024-02-24T23:25:35Z)
• Digital Twin Assisted Deep Reinforcement Learning for Online Admission Control in Sliced Network [19.152875040151976]
  We propose a digital twin (DT) accelerated DRL solution to address this issue. A neural network-based DT is established with a customized output layer for queuing systems, trained through supervised learning, and then employed to assist the training phase of the DRL model. Extensive simulations show that the DT-accelerated DRL improves resource utilization by over 40% compared to the directly trained state-of-the-art dueling deep Q-learning model.
  arXiv  Detail & Related papers  (2023-10-07T09:09:19Z)
• RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch [23.104546205134103]
  Training deep reinforcement learning (DRL) models usually requires high costs. compressing DRL models possesses immense potential for training acceleration and model deployment. We propose a novel sparse DRL training framework, "the textbfRigged textbfReinforcement textbfLearning textbfLottery" (RLx2)
  arXiv  Detail & Related papers  (2022-05-30T12:18:43Z)

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.