{"total":61,"rows":[{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250,"area":"lr"},{"id":"2506.06122","title":"Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library","created":"2025-06-06","cited_by_count":101,"area":"lr"},{"id":"2510.01161","title":"Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?","created":"2025-10-01","cited_by_count":53,"area":"lr"},{"id":"2507.01663","title":"AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training","created":"2025-07-02","cited_by_count":41,"area":null},{"id":"2508.18588","title":"History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL","created":"2025-08-26","cited_by_count":38,"area":"lr"},{"id":"2511.14617","title":"Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning","created":"2025-11-18","cited_by_count":25,"area":null},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2505.17826","title":"Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models","created":"2025-05-23","cited_by_count":19,"area":null},{"id":"2510.26475","title":"ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems","created":"2025-10-30","cited_by_count":18,"area":"lr"},{"id":"2511.16665","title":"Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter","created":"2025-11-20","cited_by_count":14,"area":"lr"},{"id":"2512.22560","title":"RollArt: Disaggregated Multi-Task Agentic RL Training at Scale","created":"2025-12-27","cited_by_count":14,"area":"agents"},{"id":"2604.26256","title":"DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training","created":"2026-04-29","cited_by_count":14,"area":null},{"id":"2510.19225","title":"RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs","created":"2025-10-22","cited_by_count":11,"area":"lr"},{"id":"2602.10693","title":"VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training","created":"2026-02-11","cited_by_count":11,"area":"moe"},{"id":"2506.22950","title":"Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models","created":"2025-06-28","cited_by_count":10,"area":"lr"},{"id":"2511.13841","title":"Beat the long tail: Distribution-Aware Speculative Decoding for RL Training","created":"2025-11-17","cited_by_count":10,"area":"alignment"},{"id":"2507.19017","title":"MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster","created":"2025-07-25","cited_by_count":9,"area":"moe"},{"id":"2509.21792","title":"FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2511.00796","title":"AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs","created":"2025-11-02","cited_by_count":9,"area":null},{"id":"2603.28101","title":"Heddle: A Distributed Orchestration System for Agentic RL Rollout","created":"2026-03-30","cited_by_count":8,"area":"agents"},{"id":"2605.17570","title":"How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2508.11553","title":"SeamlessFlow: A Trainer Agent Isolation RL Framework Achieving Bubble-Free Pipelines via Tag Scheduling","created":"2025-08-15","cited_by_count":4,"area":"deeprl"},{"id":"2511.16193","title":"Fast LLM Post-training via Decoupled and Fastest-of-N Speculation","created":"2025-11-20","cited_by_count":4,"area":"inference"},{"id":"2604.09107","title":"TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2606.03077","title":"Libra: Efficient Resource Management for Agentic RL Post-Training","created":"2026-06-02","cited_by_count":4,"area":"agents"},{"id":"2608.10402","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","created":"2026-08-11","cited_by_count":4,"area":"agents"},{"id":"2605.08520","title":"FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration","created":"2026-05-08","cited_by_count":3,"area":"agents"},{"id":"2605.08639","title":"ReLibra: Routing-Replay-Guided Load Balancing for MoE Training in Reinforcement Learning","created":"2026-05-09","cited_by_count":3,"area":"moe"},{"id":"2605.13907","title":"AIS: Adaptive Importance Sampling for Quantized RL","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2606.24143","title":"AsyncOPD: How Stale Can On-Policy Distillation Be?","created":"2026-06-23","cited_by_count":3,"area":"distill"},{"id":"2607.17299","title":"WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning","created":"2026-07-19","cited_by_count":3,"area":"agents"},{"id":"2602.02192","title":"ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2605.08862","title":"BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.30859","title":"DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2606.04560","title":"Rollout-Level Advantage-Prioritized Experience Replay for GRPO","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2607.01083","title":"Staleness-Learning Rate Scaling Laws for Asynchronous RLHF","created":"2026-07-01","cited_by_count":2,"area":"alignment"},{"id":"2608.22788","title":"TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts","created":"2026-08-24","cited_by_count":2,"area":"distill"},{"id":"2601.21476","title":"Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2604.23838","title":"JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2605.07244","title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.13779","title":"MinT: Managed Infrastructure for Training and Serving Millions of LLMs","created":"2026-05-13","cited_by_count":1,"area":"moe"},{"id":"2605.15565","title":"AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs","created":"2026-05-15","cited_by_count":1,"area":"agents"},{"id":"2605.23945","title":"Accelerating Long-Tail Generation in Synchronous RLHF Training via Adaptive Tensor Parallelism","created":"2026-05-03","cited_by_count":1,"area":"alignment"},{"id":"2606.26607","title":"Moebius: Serving Mixture-of-Expert Models with Seamless Runtime Parallelism Switch","created":"2026-06-25","cited_by_count":1,"area":"moe"},{"id":"2608.14498","title":"Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training","created":"2026-08-14","cited_by_count":1,"area":"mllm"},{"id":"2609.34645","title":"Nereus: Adaptive Parallelism for LLM Post-Training","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2603.13019","title":"ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning","created":"2026-03-13","cited_by_count":0,"area":"agents"},{"id":"2606.19004","title":"Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training","created":"2026-06-17","cited_by_count":0,"area":"diffusion"},{"id":"2606.24369","title":"Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.21653","title":"Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning","created":"2026-07-22","cited_by_count":0,"area":"agents"},{"id":"2608.14635","title":"Belayer: Efficient Fault Tolerance for LLM Agentic RL Training","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.27046","title":"Performance Foundations of Parallel & Distributed Reasoning Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2609.25442","title":"WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.25463","title":"Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.27547","title":"EBRL: Asynchronous Embodied RL by Multi-Grained Resource Management","created":"2026-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2609.33848","title":"QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.05935","title":"ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.08430","title":"NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.09914","title":"RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.16592","title":"Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.16866","title":"Efficient Resource-Shiftable RL Post-training with Generative Rewards","created":"2026-10-12","cited_by_count":0,"area":"alignment"}],"next_cursor":null}