collaborators

6 papers

cs.DC2026

RollArt: Disaggregated Multi-Task Agentic RL Training at Scale

Wei Gao, Yuheng Zhao, Tianyuan Wu +15

Agentic Reinforcement Learning (RL) trains LLMs through multi-turn interactions with environments, producing workloads that mix compute-bound prefill, bandwidth-bound decoding, CPU…

cs.OS2026

Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes

Tianyuan Wu, Chaokun Chang, Lunxi Cao +2

Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore (C/R) of this state is neede…

cs.DC2025

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

Tianyuan Wu, Lunxi Cao, Yining Wei +11

Rollout-training disaggregation is emerging as the standard architecture for Reinforcement Learning (RL) post-training, where memory-bound rollout and compute-bound training are ph…

cs.DC2025

AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs

Ran Yan, Youhe Jiang, Tianyuan Wu +7

Maximizing training throughput and cost-efficiency of RL for LLMs is essential to democratize this advanced technique. One promising but challenging approach is to deploy such a co…

cs.LG2025

Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony

Han Lu, Zichen Liu, Shaopan Xiong +19

Synchronous Reinforcement Learning (RL) post-training has emerged as a crucial step for enhancing Large Language Models (LLMs) with diverse capabilities. However, many systems desi…

cs.DC2025

RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training

Wei Gao, Yuheng Zhao, Dakai An +11

Reinforcement Learning (RL) is a pivotal post-training technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, synchronous RL post-training oft…