Autoregressive Rollout

Ask about this topic

Momentum

19 papers in the last four weeks, up 90% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 88

All topics
CardsList

  1. ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents

    Oct 6, 2026Yupeng Su, Jiayi Tian, Zheng Zhang +1Interaction HistoryAutoregressive Rollout

    University of California, Santa Barbara · Intel

  2. Flash-OPD: Fast On-Policy Distillation

    Oct 5, 2026Wei Chen, Junle Chen, Yitong Yang +6Student-Generated TrajectoriesAutoregressive Rollout

    Tencent Hy · HKUST(GZ) · HKUST

  3. Network World Models as Environments for Algorithm Design on Complex Systems

    Oct 1, 2026Rishab Alagharu, Hongji Pu, Zeeshan Memon +3Efficient World-Action ModelAgent-Based Model

    Emory University · University of Illinois Urbana-Champaign

  4. Frame Differential On-Policy Self-Distillation for Video Reasoning

    Sep 30, 2026Haiying He, Xin Zheng, Shaoli Hu +4Unsupervised On-Policy Self-DistillationOffline Reinforcement Learning

    HKUST · NKU · SEU +1

  5. Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History

    Sep 29, 2026Weiqiang Wang, Zhuokun Chen, Yusheng Dai +5Autoregressive Video Diffusion ModelsVideo Diffusion Models

    Monash University · Vivix AI · Lancaster University

  6. RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts

    Sep 29, 2026Hongbin Lin, Chaoda Zheng, Yiming Yang +11Autonomous DrivingDrives

    The Chinese University of Hong Kong, Shenzhen · XPeng Motors · Xidian University

  7. Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations

    Sep 29, 2026Guanghui Min, Liang Wu, Mingjia Shi +4Long-Horizon AgentsInteraction History

    University of Virginia · Nokia

  8. ROSS: Relearning from Self-Generated Rollouts through Selective Supervision

    Sep 28, 2026Zhiwei Zhang, Huayu Deng, Fei Zhao +4Autoregressive RolloutUnsupervised On-Policy Self-Distillation

    AllSpark Team

  9. Inductive Feedback for Mixed-Policy Distillation

    Sep 28, 2026Amir Moeini, Huaijiang Zhu, Daniel Havir +1FeedbackAutoregressive Rollout

    Alquist Robotics · University of Virginia

  10. One Rollout Is All You Get: Fully Test-Time Adaptation for GUI Agents

    Sep 28, 2026Ziqiang Wang, Li Gu, Zhixiang Chi +6Graphical User Interface AgentsTest-Time Adaptation

    Concordia University · Mila – Qu´ebec AI Institute · University of Toronto +1

  11. Opera: A Verbal Critic Framework for Long-horizon Coding Agents

    Sep 27, 2026Kai Mei, Zhiyuan Hu, Yutong Dai +7CriticLong-Horizon Agents

    Salesforce AI Research · Rutgers University · Lehigh University

  12. Beyond One-Step Accuracy: State-Affine Latent Transition for Reliable Visual Planning

    Sep 27, 2026Boyuan Zhang, Yingjun Du, Xiantong Zhen +1Low-Latency Latent PlanningLatent World Models

    UCAS-Terminus AI Lab, School of Engineering Science, University of Chinese Academy of Sciences · VIS Lab, University of Amsterdam · Central Research Institute, United Imaging Healthcare, Co., Ltd.

  13. Trust Guided Decision Transformer

    Sep 25, 2026Chainesh Gautam, Raghuram Bharadwaj Diddigi, Chandramouli Kamanchi +3Autoregressive RolloutGoal-Conditioned Value Function

    International Institute of Information Technology Bangalore · IBM Research Bangalore

  14. Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model

    Sep 23, 2026Xiwen Chen, Rigaudiere Z. Li, Zhiruo Zhou +2Latent FlowLatent Motion

    Shenzhen International Graduate School, Tsinghua University · Shanghai Jiaotong University · Wuhan University of Technology

  15. Faithful Faithfulness Evaluations: Challenges & Pitfalls Learned from a Breast MRI Case Study

    Sep 22, 2026Peachapong Poolpol, Henrik H. J. Detjen, Eike PetersenExplainabilitySaliency

    Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany · Deggendorf Institute of Technology, Deggendorf, Germany

  16. EPIG-Tree: Compute-Optimal Branching for Gradient-Efficient Reinforcement Learning

    Sep 17, 2026Nikita Khomich, Leopold Hermansson, Ido HakimiAutoregressive RolloutCredit Assignment

  17. Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents

    Sep 16, 2026Yi Yu, Liuyi Yao, Yaliang Li +2RollbackLong-Horizon Agents

    Wuhan University · Alibaba Group

  18. GrowMTP: Can RL Grow Its Own Draft Head?

    Sep 15, 2026Minghua He, Lingzhe Zhang, Yuan Liu +2Autoregressive RolloutDrafts

    WeChat AI, Tencent · Peking University

  19. Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization

    Sep 9, 2026Andy Zeyi Liu, Haoran Sun, Lucas Baker +2Joint-Embedding Predictive ArchitecturesS-Jepa

    Yale University · Jump Trading · Brown University

  20. Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

    Sep 8, 2026Zhuoran Zhao, Shengju Qian, Tongtong Liang +7Autoregressive Video Diffusion ModelsVideo Diffusion Models

    1HKUST(GZ) · 2HKUST · 3LIGHTSPEED +3

  21. Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR

    Sep 8, 2026Youngjun Yu, Sanghwan Jang, Hwanjo YuReinforcement Learning With Verifiable RewardAutoregressive Rollout

    Pohang University of Science and Technology (POSTECH)

  22. Environment Evolution for Terminal Agents

    Sep 3, 2026Zhiyuan Fan, Tinghao Yu, Yuanjun Cai +9Synthetic EnvironmentsEvolutionary Optimization Methods

    Hunyuan Team, Tencent

  23. MemoryWalker: Stop Training Agents on Contexts They Never Saw

    Sep 1, 2026Zinco J, Xunjie Zhu, Shen Huang +3Autoregressive RolloutParallel Rollouts

    Token Foundry, Alibaba Group

  24. Online Self-Weighted Fine-Tuning

    Sep 1, 2026Haiquan Wen, Yiwei He, Bei Peng +1Model Fine-TuningModel Weights

    University of Liverpool · University of Sheffield

  25. A Model with No Head and Many Thoughts

    Aug 31, 2026Nikita Koriagin, Yaroslav Aksenov, George Bredis +3Latent ThoughtsThoughts

    1Yandex · 2T-Tech

  26. SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning

    Aug 20, 2026Dayang Liang, Lang Feng, Bo An +1Agentic Reinforcement LearningAutoregressive Rollout

    Xiamen University, China

  27. Distillation of Foundation Models for Time-dependent PDEs

    Aug 12, 2026Daniel Musekamp, Boshra Ariguib, Andrei Manolache +1Autoregressive RolloutKnowledge Distillation

    University of Stuttgart · University of Cologne · Bitdefender

  28. GCPO: Diagnosing and Constraining Subspace Geometry in Rollout RL for LLMs

    Aug 12, 2026Kai Yang, Jingwei Xu, Wanyu Wang +4Autoregressive RolloutRollout

    School of Computer Science, Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · NovaCore +3

  29. Keep the Future, Drop the Rollout: RIFT for World Action Models

    Aug 12, 2026Chushan Zhang, Jinguang Tong, Xuesong Li +2World ModelsAutoregressive Rollout

    Australian National University

  30. Scheduling Mixed RL Rollouts Beyond Prefix Locality

    Aug 11, 2026Zetao Hong, Song Yuan, Yuanhao Ding +4Parallel RolloutsAutoregressive Rollout

    State Key Laboratory of Novel Software Technology, Nanjing University · StepFun

  31. Twin Rollouts: Noise-Coupled Counterfactual Branching in Interactive Video World Models

    Aug 10, 2026Yu Ma, Hongli Shi, Xinran XuCounterfactual GenerationVideo World Models

  32. A Structural Dynamics Graph World Model: Unified Modeling, Constrained Rollout, and Interpretable Calibration

    Aug 9, 2026Wei Wang, Yaosen Chen, Han Yang +5World ModelsContracts

    Sobey Media Intelligence Laboratory

  33. Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models

    Aug 8, 2026Xuning He, Zinan Sheng, Yongding Tao +4Diffusion Language ModelsDiffusion Models

    School of Computer Science, Shanghai Jiao Tong University · College of Artificial Intelligence, Nankai University · School of Computer Science, Peking University

  34. LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction

    Aug 6, 2026Yingqing Guo, Hui Yuan, Zijian He +2Reward GradientsLangevin Dynamics

  35. SpecRoll: Fast-Slow Verifier-Feedback Adaptation for Speculative Reinforcement Learning Rollouts

    Aug 5, 2026Nhat Minh Pham, Duy Tung Doan, Thi Duyen Ngo +2Autoregressive RolloutLarge Language Model Reinforcement Learning

    VNU University of Engineering and Technology, Vietnam National University, Hanoi, Vietnam · Viettel AI, Viettel Group, Hanoi, Vietnam

  36. PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud

    Aug 4, 2026Chenghua Wang, Daliang Xu, Dongqi Cai +21Physics-Aware ModelsArtificial Intelligence Systems

    1Beijing University of Posts and Telecommunications · 2Nanjing University · 6ModelBest +3

  37. Look Where It Matters: Adaptive Visual Refinement for Vision-Language-Action Models

    Aug 3, 2026Jin Cui, Yanbin Hu, Xinyue Long +3Diffusion-Based Vision-Language-ActionsVision Encoders

    1State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University · School of Software Engineering, Xi’an Jiaotong University

  38. Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models

    Aug 3, 2026Wonseok Lee, Jimyeong Kim, Jungmin Ko +1Large Language Model Reinforcement LearningAutoregressive Rollout

    Interdisciplinary Program in Artificial Intelligence, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, South Korea · Artificial Intelligence Institute, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, South Korea · Department of Intelligence and Information, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, South Korea

  39. Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning

    Aug 2, 2026Wenhao Zhang, Yibo Xie, Rui Wang +9Autoregressive RolloutLarge Language Model Reinforcement Learning

    1Tencent · 2Harbin Institute of Technology · 3Jinan University +1

  40. Adaptive FastOPD: Progress-Aware Rollout Horizon Expansion for Efficient On-Policy Distillation

    Jul 31, 2026Qian Tan, Huaifei Liang, Xuanyu Zhu +2Efficient On-Policy DistillationAutoregressive Rollout

    University of Science and Technology of China · 3Shanghai Jiao Tong University · 2Shanghai Artificial Intelligence Laboratory

  41. HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators

    Jul 31, 2026Jiaquan Zhang, Shuxu Chen, Haifan Meng +6Autoregressive RolloutNeural Operators

    School of Computer Science and Engineering, UESTC · Electronics and Information Convergence Engineering, KHU · Department of Mathematical Sciences, UOL +3

  42. Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control

    Jul 30, 2026Takumi Shioda, Kohei Terashima, Tatsuo NagaiHvac ControlReinforcement Fine-Tuning

    The University of Tokyo · Tokyo University of Science

  43. ActSWM: Action-Sensitive World Models for Long-Horizon Planning in Open-World Games

    Jul 29, 2026Zhenfeng Gan, ZiTong Zeng, Jiajun Cheng +3Latent World ModelsLong-Horizon Planning

  44. Q-Steer: Action-Value Guidance for Molecular Policy Optimization

    Jul 29, 2026Xinyu Wang, Jinbo Bi, Minghu SongMolecular OptimizationFrictive Policy Optimization

    Department of Computer Science and Engineering, University of Connecticut · 1Storrs, CT 06269, USA · Institute of Health and Medicine, Hefei Comprehensive National Science Center +1

  45. Diffusion ReRoll: Revisable Denoising for Robotic Sequential Prediction

    Jul 22, 2026Seonsoo Kim, Seongil Hong, Jun-Gill KangDiffusion PoliciesDenoising Trajectory

    Agency for Defense Development

  46. QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides

    Jul 17, 2026Zhengyang Zhuge, Hao Yu, Xin Wang +4Fp8Autoregressive Rollout

    Qwen Team, Alibaba Inc.

  47. Process Reward Informed Tree Rollout for Effective Multi-Turn RL

    Jul 17, 2026Xintong Li, Sha Li, Yuwei Zhang +8Autoregressive RolloutRollout

    1UC San Diego · 2Amazon · 3MIT Alumni

  48. Adaptive Compute in Latent World Models: When Depth Helps, Hurts, or Doesn't Matter

    Jul 11, 2026Achyuthan SivasankarAutoregressive RolloutWorld Model Planning

    New York University

  49. OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

    Jul 9, 2026Hongyu Liu, Chun Wang, Feng Gao +6Autoregressive Video Diffusion ModelsAutoregressive Video Generation

    Meituan · HKUST · City University of Hong Kong

  50. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

    Jul 8, 2026Zhenyu Hou, Yujiang Li, Jie Tang +1Agentic LearningAutoregressive Rollout

    Tsinghua University · Work done while ZH and YL interned at Z.AI.

  51. The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought

    Jul 8, 2026Zhiyuan LiOptimal Sample ComplexitySample Complexity

    Toyota Technological Institute at Chicago

  52. Latency-Aware Bid Acceptance under Operational Feasibility: A Public Benchmark with Hindsight Ceilings

    Jul 8, 2026Aswin ChandrasekaranLogisticsFeasibility

    Bubba AI

  53. Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation

    Jul 7, 2026Songbur Wong, Xiaosong Jia, Junqi You +12Autonomous Driving SimulationAutonomous Driving

    1Shanghai Jiao Tong University · 3Fudan University · 4Shanghai Artificial Intelligence Laboratory +3

  54. Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

    Jul 7, 2026Yijun Zhang, Fan Xu, Jiaxin Ding +6Autoregressive RolloutFrictive Policy Optimization

    Shanghai Jiao Tong University

  55. Deployment-Side Adaptiveness in Multi-Horizon Volatility Forecasting

    Jun 26, 2026Riku Green, Zahraa S. Abdallah, Telmo M Silva FilhoVolatilityPost-Deployment Adaptation

    The University of Bristol Bristol, UK

  56. Conformal Orbit-Valid Trust Horizons for Equivariant World Models

    Jun 23, 2026Hongbo WangWorld ModelsHorizon

    Department of Mathematics, Stony Brook University, Stony Brook, NY 11794, USA

  57. A Differentiable Atari VCS:A Complex, Fully Known Ground Truth for Explainable AI

    Jun 21, 2026Andreas Maier, Siming Bayer, Patrick KraussExplainable Artificial IntelligenceXai

    Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nuremberg, Germany · Mannheim Center for Neuromodulation and Neuroprosthetics, Heidelberg University, Germany

  58. EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

    Jun 17, 2026Minseo Kim, Minjae Lee, Seunghyuk Oh +7Autoregressive RolloutParallel Rollouts

    FuriosaAI · University of California, Berkeley

  59. Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation

    Jun 17, 2026Zirui Zheng, Jiaqian Yu, Xiongfeng Peng +7Efficient World-Action ModelRobotic Manipulation

    1Dalian University of Technology · 2Samsung R&D Institute China-Beijing (SRCB), China

  60. SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation

    Jun 17, 2026Wei-Cheng Tseng, Gashon Hussein, Yuzhu Dong +9Video World ModelsAutoregressive Rollout

    University of Toronto · Vector Institute · NVIDIA +3