mlsanityData to 7 Oct 2026

TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling

arXiv 2608.10402 ↗First posted 11 Aug 2026cs.LG cs.DCcited by 2

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

Reinforcement learning (RL) for large language models is moving toward multi-turn agentic workloads, where rollout tasks repeatedly pause for external environments, resume with growing contexts, and finish at highly variable times. In this setting, RL training goodput, measured by training throughput, matters more than raw GPU occupancy: GPU waiting and repeated prefill recomputation are pure overhead. We present TideRL, a readiness-aware elastic RL system with Continuous Task Batching, Resource-Aware Ref-Actor Pipelining, and Elastic Resource Scaling. CTB preserves useful rollout state, textrmRA2textrmP selects between decoupled streaming and colocated aggregation from the ready backlog and arrival interval, and ERS moves ranks between rollout and training using the same readiness signals. Across text-only and multi-modal agentic workloads, TideRL improves RL training goodput by up to 5.6× over synchronous baselines and over 33% over asynchronous baselines, while reaching similar task performance. It also improves KV cache hit rate by 1.58×, reduces per-step training time by up to 44.3%, and cuts total waiting time by up to 77.6%.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 39 of its 52 references that are in the map. First posted on arXiv 11 Aug 2026.

Builds on

39 of 52 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework5 Oct

Other references · 38

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  4. 2024Qwen2.5 Technical Reportcited by 4,713
  5. 2020Learning to summarize from human feedbackcited by 2,562
  6. 2025Qwen3-VL Technical Reportcited by 2,534
  7. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  8. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  9. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  10. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  11. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  12. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
26 more
  1. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  2. 2021Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LMcited by 621
  3. 2024DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Servingcited by 595
  4. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 344
  5. 2025AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoningcited by 234
  6. 2024Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttentioncited by 159
  7. 2024AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agentscited by 105
  8. 2024VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agentscited by 101
  9. 2020Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learningcited by 68
  10. 2021Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelinescited by 68
  11. 2025StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generationcited by 56
  12. 2025ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflowscited by 47
  13. 2025Continuum: Efficient and Robust Multi-Turn LLM Agent Scheduling with KV Cache Time-to-Livecited by 43
  14. 2024Optimizing RLHF Training for Large Language Models with Stage Fusioncited by 41
  15. 2025AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Trainingcited by 37
  16. 2025Laminar: A Scalable Asynchronous RL Post-Training Frameworkcited by 35
  17. 2024SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applicationscited by 34
  18. 2025APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generationcited by 27
  19. 2024ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Developmentcited by 23
  20. 2025Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learningcited by 21
  21. 2024DistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Modelscited by 16
  22. 2026CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Controlcited by 13
  23. 2026Efficient LLM Serving for Agentic Workflows: A Data Systems Perspectivecited by 10
  24. 2025Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Modelscited by 9
  25. 2025MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Clustercited by 9
  26. 2025Fast LLM Post-training via Decoupled and Fastest-of-N Speculationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directionscited by 0
  2. 2026QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Libra: Efficient Resource Management for Agentic RL Post-Training
  2. 2025RollArt: Disaggregated Multi-Task Agentic RL Training at Scale
  3. 2025Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony
  4. 2025EARL: Efficient Agentic Reinforcement Learning Systems for Large Language Models
  5. 2026PEARL: Adaptive Prefill-Decode Execution with Elasticity for Agentic Reinforcement Learning
  6. 2025RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training
  7. 2026GrowMTP: Can RL Grow Its Own Draft Head?
  8. 2026WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning