Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Han, Liu, Zichen, Xiong, Shaopan, He, Yancheng, Gao, Wei, Wu, Yanan, Wang, Weixun, Liu, Jiashun, Li, Yang, Zhao, Haizhou, Huang, Ju, Yang, Siran, Li, Xiaoyang, Luo, Yijia, Liu, Zihe, Pan, Ling, Yan, Junchi, Wang, Wei, Su, Wenbo, Wang, Jiamang, Qu, Lin, Zheng, Bo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria
by: Hu, Xinyu, et al.
Published: (2026)

RollMux: Phase-Level Multiplexing for Disaggregated RL Post-Training
by: Wu, Tianyuan, et al.
Published: (2025)

Think-J: Learning to Think for Generative LLM-as-a-Judge
by: Huang, Hui, et al.
Published: (2025)

One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning
by: Li, Yiyuan, et al.
Published: (2026)

ProgCo: Program Helps Self-Correction of Large Language Models
by: Song, Xiaoshuai, et al.
Published: (2025)

Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
by: Liu, Jiashun, et al.
Published: (2025)

AMAP Agentic Planning Technical Report
by: AMAP AI Agent Team, et al.
Published: (2025)

GEM: A Gym for Agentic LLMs
by: Liu, Zichen, et al.
Published: (2025)

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)

Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment
by: Li, Yanshi, et al.
Published: (2024)

FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
by: Shah, Jay, et al.
Published: (2024)

ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants
by: Wang, Pei, et al.
Published: (2026)

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

Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation
by: Luo, Yijia, et al.
Published: (2025)

Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers
by: Lin, Hongzhan, et al.
Published: (2025)

2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision
by: Li, Shilong, et al.
Published: (2024)

WEFix: Intelligent Automatic Generation of Explicit Waits for Efficient Web End-to-End Flaky Tests
by: Liu, Xinyue, et al.
Published: (2024)

HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment
by: Liu, Yuexiao, et al.
Published: (2025)

Diffusion on Graph: Augmentation of Graph Structure for Node Classification
by: Wang, Yancheng, et al.
Published: (2025)

Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs
by: Long, Rujiao, et al.
Published: (2025)

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

FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio Generation
by: Liu, Huadai, et al.
Published: (2024)

ROLL OVER, ADAM SMITH
by: FOROOHAR, RANA
Published: (2006)

Private Private Information in Second-Price Auction
by: Liu, Boyu, et al.
Published: (2026)

Linear Dynamics in the RLVR Training of Large Language Models
by: Wang, Tianle, et al.
Published: (2026)

Global well-posedness for one-dimensional compressible Navier--Stokes system in dynamic combustion with small $BV\cap L^1$ initial data
by: Li, Siran, et al.
Published: (2026)

Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
by: Ke, Junlong, et al.
Published: (2026)

Panoptic-FlashOcc: An Efficient Baseline to Marry Semantic Occupancy with Panoptic via Instance Center
by: Yu, Zichen, et al.
Published: (2024)

FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models
by: Cai, Kaitong, et al.
Published: (2025)

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
by: He, Yancheng, et al.
Published: (2025)

Human-Inspired Computing for Robust and Efficient Audio-Visual Speech Recognition
by: Liu, Qianhui, et al.
Published: (2024)

Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization
by: Wang, Ziqi, et al.
Published: (2025)

Generalizing Video DeepFake Detection by Self-generated Audio-Visual Pseudo-Fakes
by: Wei, Zihe, et al.
Published: (2026)