Parallel Rollouts

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 26

All topics

Watch-Think-Interact: Bootstrapping Long-Horizon Multi-Turn Streaming Video Reasoning with Reinforcement Learning
Sep 29, 2026Ziheng Huang, Yicheng Bao, Xueheng Li +8Streaming Video Understanding Long-Horizon Task Planning
East China Normal University · University of Science and Technology of China · Xiamen University
PEARL: Adaptive Prefill-Decode Execution with Elasticity for Agentic Reinforcement Learning
Sep 28, 2026Jiaan Zhu, Wei Gao, Youhui Bai +6Parallel Rollouts Agentic Reinforcement Learning
USTC China
Sample What You Say: Aligning Language Models to Sample the Distributions They State
Sep 28, 2026Kasra Arabi, Virginia Smith, Chhavi YadavDistributions Parallel Rollouts
New York University · Carnegie Mellon University
From Base Rollouts to RL Reasoning: A Budgeted Search Perspective
Sep 1, 2026Wenhe Sun, Cunxiang Wang, Zijun Yao +1Offline Reinforcement Learning Parallel Rollouts
1Fudan University · 2Zhipu AI · 3Tsinghua University +1
MemoryWalker: Stop Training Agents on Contexts They Never Saw
Sep 1, 2026Zinco J, Xunjie Zhu, Shen Huang +3Autoregressive Rollout Parallel Rollouts
Token Foundry, Alibaba Group
Scheduling Mixed RL Rollouts Beyond Prefix Locality
Aug 11, 2026Zetao Hong, Song Yuan, Yuanhao Ding +4Parallel Rollouts Autoregressive Rollout
State Key Laboratory of Novel Software Technology, Nanjing University · StepFun
Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks
Aug 4, 2026Chenyu Wang, Yunbo Lyu, Junda He +4Retrying Swe-Bench Verified
Singapore Management University · University of Alberta · Nanjing University of Science and Technology +1
Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning
Aug 2, 2026Wenhao Zhang, Yibo Xie, Rui Wang +9Autoregressive Rollout Large Language Model Reinforcement Learning
1Tencent · 2Harbin Institute of Technology · 3Jinan University +1
ArmnetBench v0.1: Parallel Real-World Evaluation of Manipulation Policies on a Low-Cost Arm Farm
Jul 27, 2026Praveen Selvaraj, Lorenzo Uttini, Ville KuosmanenEvaluation Benchmarks Parallel Rollouts
Armnet
ADP: Adversarial Dynamics Priors for Physically Grounded Humanoid Locomotion
Jul 3, 2026Seokju Lee, Jeongtae Lee, Jeonghyeok Lim +6Full-Body Humanoid Control Kinematic Priors
Mechatronics, Systems and Control Lab (MSC Lab), Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon 34141, Republic of Korea · Samsung Electronics, Future Robotics AI Group, Seoul, Republic of Korea · School of Electrical Engineering, Hanyang University, Ansan 15588, Republic of Korea +1
Scaling Laws for Collapse in Asynchronous GRPO
Jul 1, 2026Jingwei Song, Haofeng Xu, Jie Xiao +7Parallel Rollouts Better Call Group Relative Policy Optimization
The University of Hong Kong · Shanghai Jiao Tong University · Gradient +2
Understanding Rollout Error in Graph World Models
Jun 26, 2026Xinyuan Song, Zekun CaiWorld Models Prediction Error
Emory University, Atlanta, GA, USA · The University of Tokyo, Tokyo, Japan · LocationMind, Tokyo, Japan
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
Jun 17, 2026Minseo Kim, Minjae Lee, Seunghyuk Oh +7Autoregressive Rollout Parallel Rollouts
FuriosaAI · University of California, Berkeley
CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward
Jun 12, 2026Md Amirul Islam, Sumiran Thakur, Huancheng Chen +3Large Language Model Agents Agentic Benchmarks
Center for Advanced AI, Accenture
Rollout-Level Advantage-Prioritized Experience Replay for GRPO
Jun 3, 2026Gyeongtae Yoo, Sanghyeok Park, Soohyuk Jang +2Parallel Rollouts Replay
Department of Electrical and Computer Engineering, Seoul National University · Interdisciplinary Program in AI, Seoul National University · AIIS, ASRI, INMC, and ISRC, Seoul National University
Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR
Jun 2, 2026Chuanyu Qin, Chenxu Yang, Qingyi Si +3Reinforcement Learning With Verifiable Reward Verifiable Rewards
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China
Libra: Efficient Resource Management for Agentic RL Post-Training
Jun 2, 2026Kaiwen Chen, Xin Tan, Jingzong Li +6Agentic Reinforcement Learning Resource-Efficient
The Chinese University of Hong Kong · The Hang Seng University of Hong Kong · Independent Researcher
Are Full Rollouts Necessary for On-Policy Distillation?
May 29, 2026Yaocheng Zhang, Jiajun Chai, Yuqian Fu +7Efficient On-Policy Distillation Parallel Rollouts
Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · Meituan +1
Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
May 17, 2026Wenpu Liu, Yuqi Xu, Weichu Xie +8Reinforcement Learning With Verifiable Reward Group-Based Reinforcement Learning
Peking University · Shanghai Innovation Institute
Policy Library CBF: Finite-Horizon Safety at Runtime via Parallel Rollouts
May 15, 2026Taekyung Kim, Hideki Okamoto, Bardh Hoxha +2Safety Filters Control Barrier Functions
Department of Robotics, 3Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI, 48109, USA · Toyota Motor North America, Research & Development, Ann Arbor, MI, 48105, USA
Multi-Rollout On-Policy Distillation via Peer Successes and Failures
May 12, 2026Weichen Yu, Xiaomin Li, Yizhou Zhao +8Token-Level Supervision Parallel Rollouts
1Carnegie Mellon University · 2Microsoft · 3Purdue University
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
May 12, 2026Zhong Guan, Yongjian Guo, Haoran Sun +5Off-Policy Learning Parallel Rollouts
Tianjin University · Tsinghua University · JDT AI Infra +1
Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair
May 8, 2026Jia Li, Yuxin Su, Ting Peng +3Group-Based Reinforcement Learning Automated Program Repair
The Chinese University of Hong Kong · Sun Yat-sen University · Tencent
Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL
May 7, 2026Zhiyuan Zhai, Xin WangGroup-Based Reinforcement Learning Parallel Rollouts
Fudan University
Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale
May 1, 2026Jieming Di, Xiaoyu Chen, Ying She +21Retraining Parallel Rollouts
Meta · USA
DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training
Apr 29, 2026Tianhao Hu, Xiangcheng Liu, Youshao Xiao +15Large Language Model Reinforcement Learning Large Language Model Training
Meituan, China

Sep 29, 2026, cs.AIJ/K move · Enter open · S save

Watch-Think-Interact: Bootstrapping Long-Horizon Multi-Turn Streaming Video Reasoning with Reinforcement Learning

Ziheng Huang, Yicheng Bao, Xueheng Li, Zhenkun Gao+7

East China Normal University · University of Science and Technology of China · Xiamen University

Streaming Video Understanding Long-Horizon Task Planning Parallel Rollouts

Open paper AskPDF arXiv

Streaming video assistance requires models to answer asynchronous questions from an observed prefix under a fixed context budget. Existing approaches model response timing or compress history, but an online state formed before future questions are known can omit visual details before later questions reveal their relevance; the retained state alone cannot recover them. We introduce Watch-Think-Interact (WTI), a closed-loop framework for multi-question streaming video reasoning. WTI maintains compact natural-language memory entries tagged with source-video time ranges; these entries support direct reasoning when sufficient and otherwise anchor selective recall of finer visual evidence. For each question, WTI answers when current context and memory suffice, continues watching when required evidence has not appeared, or recalls a relevant past interval and decides again after incorporating the returned chunks, without replaying the full observed history. To train this behavior, we construct WTI-82K, comprising 82,335 timed questions across 4,812 causally aligned trajectories, and develop Stream-GDPO to optimize complete multi-question streaming rollouts using trajectory-level feedback for response timing, source-video recall, and memory updates. WTI achieves state-of-the-art aggregate performance among the compared open-source streaming baselines, reaching 83.3% on StreamingBench and 73.6% weighted overall accuracy on OVO-Bench.

Momentum

Related topics

Latest papers 26