Cover Image

RollMux: Phase-Level Multiplexing for Disaggregated RL Post-Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Tianyuan, Cao, Lunxi, Wei, Yining, Gao, Wei, Zhao, Yuheng, An, Dakai, Xiong, Shaopan, Lv, Zhiqiang, Huang, Ju, Yang, Siran, Yu, Yinghao, Wang, Jiamang, Qu, Lin, Wang, Wei
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training
by: Gao, Wei, et al.
Published: (2025)

RollArt: Scaling Agentic RL Training via Disaggregated Infrastructure
by: Gao, Wei, et al.
Published: (2025)

ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL
by: Gao, Wei, et al.
Published: (2026)

Adaptra: Straggler-Resilient Hybrid-Parallel Training with Pipeline Adaptation
by: Wu, Tianyuan, et al.
Published: (2025)

FALCON: Pinpointing and Mitigating Stragglers for Large-Scale Hybrid-Parallel Training
by: Wu, Tianyuan, et al.
Published: (2024)

Complementary Reinforcement Learning
by: Muhtar, Dilxat, et al.
Published: (2026)

Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
by: Wu, Tianyuan, et al.
Published: (2026)

Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
by: Liu, Zihe, et al.
Published: (2025)

MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving
by: Duan, Jiangfei, et al.
Published: (2024)

MuxServe
by: Anonymous
Published: (2026)

MuxHand: A Cable-driven Dexterous Robotic Hand Using Time-division Multiplexing Motors
by: Xu, Jianle, et al.
Published: (2024)

Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
by: Wang, Weixun, et al.
Published: (2025)

MuxGel: Simultaneous Dual-Modal Visuo-Tactile Sensing via Spatially Multiplexing and Deep Reconstruction
by: Hu, Zhixian, et al.
Published: (2026)

Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony
by: Lu, Han, et al.
Published: (2025)

MuxTune: Efficient Multi-Task LLM Fine-Tuning in Multi-Tenant Datacenters via Spatial-Temporal Backbone Multiplexing
by: Xue, Chunyu, et al.
Published: (2026)

OrchestrRL: Dynamic Compute and Network Orchestration for Disaggregated RL
by: Tan, Xin, et al.
Published: (2026)

AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs
by: Yan, Ran, et al.
Published: (2025)

Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning
by: Liao, Xinyao, et al.
Published: (2025)

StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation
by: Zhong, Yinmin, et al.
Published: (2025)

A Comprehensive PPG-based Dataset for HR/HRV Studies
by: Xu, Jingye, et al.
Published: (2025)

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
by: Li, Yang, et al.
Published: (2025)

Validating LLM-Generated Programs with Metamorphic Prompt Testing
by: Wang, Xiaoyin, et al.
Published: (2024)

Efficiently Serving Large Multimodal Models Using EPD Disaggregation
by: Singh, Gursimran, et al.
Published: (2024)

The Observability Gap: Why Output-Level Human Feedback Fails for LLM Coding Agents
by: Wang, Yinghao, et al.
Published: (2026)

Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
by: Wang, Zhenting, et al.
Published: (2026)

Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training
by: Wang, Chen, et al.
Published: (2026)

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
by: Wang, Weixun, et al.
Published: (2025)

Bose-Hubbard Model on a Honeycomb Superlattice: Quantum Phase Transitions and Lattice Effects
by: Wang, Wei-Wei, et al.
Published: (2025)

DiFache: Efficient and Scalable Caching on Disaggregated Memory using Decentralized Coherence
by: Zhang, Hanze, et al.
Published: (2025)

AERO: Adaptive and Efficient Runtime-Aware OTA Updates for Energy-Harvesting IoT
by: Wei, Wei, et al.
Published: (2026)

MOGNET: A Mux-residual quantized Network leveraging Online-Generated weights
by: Nguyen, Van Thien, et al.
Published: (2025)

Structure and realizability for rational maps
by: Wei, Zhiqiang
Published: (2025)

Isometric immersions of constant curvature one metrics on the 2-sphere with two conical singularities into Euclidean 3-space: A partial solution to the Gálvez-Hauswirth-Mira problem
by: Wei, Zhiqiang
Published: (2025)

Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism
by: Pan, Xinglin, et al.
Published: (2025)

High-Capacity Metasurface at Limits of Polarization and Wavelength Multiplexing
by: Bao, Yanjun, et al.
Published: (2024)

Difluorocarbene (: CF 2 ) as a Minimal Perfluorocarbon linker for the Synthesis of gem ‐Difluoromethylenated Compounds ( G 1 ‐ CF 2 ‐ G 2 , G 1 , G 2 ≠ H, F): From 2019 to 2025
by: Haoyu Yan, et al.
Published: (2026)

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
by: Cen, Zhepeng, et al.
Published: (2025)

Adaptive Trajectory Bundle Method for Roll-to-Roll Manufacturing Systems
by: Li, Jiachen, et al.
Published: (2025)

Model Predictive Path Integral Control for Roll-to-Roll Manufacturing
by: Martin, Christopher, et al.
Published: (2025)

Multi-Target Flexible Angular Emulation for ISAC Base Station Testing Using a Conductive Amplitude and Phase Matrix Setup: Framework and Experimental Validation
by: Li, Chunhui, et al.
Published: (2025)