collaborators

7 papers

cs.OS2026

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

Chaokun Chang, Yukun Zhou, Kaihua Fu +10

Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state. However, th…

cs.CV2026

WorldOlympiad: Can Your World Model Survive a Triathlon?

Yuke Zhao, Wangbo Zhao, Weijie Wang +8

We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fidelity. While existing benchm…

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.DC2026

ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL

Wei Gao, Yuheng Zhao, Dilxat Muhtar +13

Agentic reinforcement learning (RL) is reshaping LLM post-training, but end-to-end training time is dominated by compute-intensive, multi-turn rollouts whose resource demand varies…

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

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…