Reinforcement Learning Post-Training

Ask about this topic

Momentum

13 papers in the last four weeks, up 333% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 63

All topics
CardsList

  1. Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning

    Oct 5, 2026Chen Henry Wu, Thomas Zhang, Aditi RaghunathanReplay-Based Continual LearningOff-Policy Learning

    Carnegie Mellon University

  2. Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning

    Oct 5, 2026Shen Ruan, Wenchang Gao, Jin Wang +4Post-Training QuantizationReinforcement Learning Post-Training

    Soochow University · Independent Researcher · Shanghai Jiao Tong University +2

  3. Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State

    Oct 4, 2026Weihan Li, Tianshi Zheng, Junhao Wu +1Reinforcement Learning Post-TrainingHidden States

    The University of Tokyo · The Hong Kong University of Science and Technology · RWTH Aachen University +1

  4. Sharpening Tax in Post-Training

    Oct 1, 2026Changdae Oh, Qi Zeng, Qi Qi +7Reinforcement Learning Post-TrainingPost-Training

    Meta Superintelligence Labs · University of Wisconsin–Madison · Work done at Meta +2

  5. What Pretraining and Midtraining Make Learnable from Rewards?

    Sep 29, 2026Chiwun Yang, Xiaoyu LiReinforcement Learning Post-TrainingPretraining

    City University of Hong Kong · University of New South Wales

  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. Mutually Adversarial Self-Training with Evolving Data for Unified Multimodal Models

    Sep 28, 2026Wentao Zhou, Weijie Gan, Jiayun WangMultimodal ModelAdversarial Training

    Georgia Institute of Technology · Washington University in St. Louis

  8. Not All Rollouts Are Worth Learning: On Trajectory Valuation for Post-Training Reinforcement Learning

    Sep 28, 2026Xuesong Jia, Ziao Yang, Zhanhe Huang +1Reinforcement Learning Post-TrainingTrajectory Generation

    Department of Computer Science, Brandeis University

  9. Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training

    Sep 27, 2026Xinyu Che, Hang Yan, Yanchen Liu +5Next-State PredictionWorld Models

    Xi’an Jiaotong University · University of Southern California · University of the Chinese Academy of Sciences +1

  10. CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model

    Sep 19, 2026Ziming Xu, Shuang Liang, Ruobing Han +10Efficient World-Action ModelFuture Video Prediction

    Aether AI · University of California, San Diego · Vanderbilt University

  11. OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher

    Sep 17, 2026Damiano Da Col, Maximilian Igl, Peter Karkus +5Autonomous DrivingReinforcement Learning Post-Training

    KE:SAI · ETH Zürich · NVIDIA Research +2

  12. Compositional Reasoning in Language Models under Reinforcement Learning Post-Training

    Sep 16, 2026Yu He, Yingxi Li, Yifei Wang +1Compositional GeneralizationReinforcement Learning Post-Training

    Stanford University · Amazon AGI Labs

  13. Performance, Efficiency and Collapse -- Advantages and Challenges in Offline Post-training of Code LLMs

    Sep 14, 2026Abhinav Anand, Sanjana Reddy Pachika, Shweta Verma +1Reinforcement Learning Post-TrainingLarge Language Model Training

    TU Darmstadt · Hessian Center for Artificial Intelligence, Darmstadt, Germany · National Research Center for Applied Cybersecurity ATHENE

  14. Miles v0.1: Production-Level Post-Training

    Sep 8, 2026RadixArk, :, Tom Chen +11Reinforcement Learning Post-Training

    RadixArk

  15. NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

    Sep 8, 2026NeoHorse Team, Guoliang Cao, Guohao Dai +34Self-Improving AgentsReinforcement Learning Post-Training

    TokenRhythm

  16. From Rollouts to Recipes: Self-Contained Post-Training for LLMs

    Sep 1, 2026Yifei Li, Lingling Zhang, Muye Huang +3Post-TrainingReinforcement Learning Post-Training

    School of Computer Science and Technology, Xi’an Jiaotong University, China · Shaanxi Province Key Laboratory of Big Data Knowledge Engineering · Zhongguancun Academy, Beijing, China +1

  17. MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training

    Aug 11, 2026Yikai Wang, Chuansai Zhou, Yuhang Zhou +10Large Language Model TrainingReinforcement Learning Post-Training

    State Key Laboratory for Novel Software Technology, Nanjing University, China · Huawei, China

  18. RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation

    Aug 10, 2026Boxiong Wang, Hui Kang, Geng Sun +3Aerial Vision-Language NavigationReinforcement Learning Post-Training

    1Jilin University · 4Zhongguancun Academy · 2Tsinghua University +1

  19. Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models

    Aug 8, 2026Jianqi Zhang, Xingyu Zhang, Zeen Song +3Time Series Foundation ModelsReinforcement Learning Post-Training

    Institute of Software, Chinese Academy of Sciences, Beijing, China

  20. TEMPO: Semantic-Action Decoupled RL Post-Training for Vision-Language-Action Models

    Aug 7, 2026Ziheng Liu, Quantao YangDiffusion-Based Vision-Language-ActionsReinforcement Fine-Tuning

    School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou 310018, China. · Department of Robotics, Perception, and Learning, KTH Royal Institute of Technology, Sweden.

  21. RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement Learning

    Jul 31, 2026Chengbo Liu, Lifang Zhou, Ruijie Yan +8Offline Reinforcement LearningReinforcement Learning Post-Training

    1Microsoft, Beijing, China · 2Southeast University, Nanjing, China

  22. HARGO: Heterogeneity-Aware Reward-Guided Optimization for RL Post-Training of LLMs on HPC Tasks

    Jul 30, 2026Tiangang Li, Xiangbo TianReinforcement Learning Post-TrainingSupervised Finetuning

    School of Computer Science, Wuhan University, Wuhan, China

  23. HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

    Jul 29, 2026Hei Yi Mak, Shadan Golestan, Hoang Le +10Fp8Full-Precision Performance

    Huawei

  24. Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback

    Jul 15, 2026Patrick Wilhelm, Odej KaoReinforcement Learning Post-TrainingPost-Training

    BIFOLD Technische Universität Berlin Germany

  25. Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals

    Jul 13, 2026Daocheng Fu, Rong Wu, Yu Yang +7Reinforcement Learning Post-TrainingPost-Training

    Shanghai AI Laboratory · Fudan University · Zhejiang University +2

  26. PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers

    Jul 10, 2026Yujie Pang, Zudong LiAction ChunksSoft Actor-Critic

    Dept. of Mechanical and Energy Engineering · Southern University of Science and Technology · Shenzhen, China

  27. RL Post-Training Builds Compositional Reasoning Strategies

    Jul 8, 2026Azwar Abdulsalam, Nishil Patel, Andrew SaxeReinforcement Learning Post-TrainingRewrite

    Gatsby Computational Neuroscience Unit, UCL, London, United Kingdom.

  28. Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment

    Jul 6, 2026Yu Li, Xiuyu Li, Mingyang Yi +4Reinforcement Learning Post-TrainingPlug-And-Play

    Renmin University of China

  29. CONFLUX: A Latent Diffusion Model for 3D Chest-CT Synthesis with RL Post-Training

    Jul 3, 2026Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge +1Medical Image GenerationCone-Beam Computed Tomography

    Department of Biomedical Data Science, Stanford University School of Medicine · Department of Mathematical Modelling, Statistics & Bioinformatics, Ghent University · Department of Electrical Engineering, Stanford University

  30. The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning

    Jul 1, 2026Daniel Thi Graviet, Lovre Pesut, Ivan Dagelic +2Coding AgentsRollout

    Daytona United States

  31. When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon

    Jun 29, 2026Huaqing Zhang, Jingchu Gai, Juno Kim +2Imitation LearningReinforcement Learning Post-Training

    Tsinghua University · Carnegie Mellon University · UC Berkeley +1

  32. Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

    Jun 24, 2026Changdae Oh, Wendi Li, Seongheon Park +3Reinforcement Learning Post-TrainingAgentic Reinforcement Learning

    University of Wisconsin–Madison · Argonne National Laboratory

  33. Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training

    Jun 17, 2026Jianzhe LinRecursive Self-ImprovementReinforcement Learning Post-Training

    MetaAI · *Work done at Meta

  34. Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training

    Jun 17, 2026Ruiqi Lai, Dakai An, Wei Gao +6Diffusion-Based Reinforcement Learning MethodsReinforcement Learning Post-Training

    NTU Singapore · Hong Kong University of Science and Technology · Alibaba Group

  35. LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents

    Jun 16, 2026Haoyang Fang, Wei Zhu, Boran Han +11Reinforcement Learning Post-TrainingLarge Language Model Training

    †LLMZero Project Core Team. · ∗Work done at Amazon.

  36. STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training

    Jun 16, 2026Jinjie Shen, Wei Deng, Xian Hu +2Reinforcement Learning Post-Training

  37. Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack

    Jun 12, 2026He Zhang, Lingzhu Xiang, Haitao Lin +23Scalable Robot LearningRobot Systems

    Tencent Robotics X × Tencent Hy Team

  38. Select and Improve: Understanding the Mechanics of Post-Training for Reasoning

    Jun 11, 2026Akshay Krishnamurthy, Audrey Huang, Nived RajaramanReinforcement Learning Post-TrainingLarge Reasoning Models

    Microsoft Research NYC · UIUC

  39. CRePE: Convolution-aware Relative Importance in Post-training Pruning with Efficient Search

    Jun 1, 2026Cheonjun ParkUnstructured PruningLarge Language Model Compression

    Hankuk University of Foreign Studies

  40. A Predictive Law for On-Policy Self-Distillation From World Feedback

    May 28, 2026Tommy He, Jerome Sieber, Matteo SaponatiUnsupervised On-Policy Self-DistillationReinforcement Learning Post-Training

    Tufa Labs, Zürich, Switzerland

  41. LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training

    May 28, 2026Minju Gwak, Minseo Kwak, Dongseok Lee +3Reinforcement Learning Post-TrainingRepresentation-Level Misalignment

    Yonsei University · Seoul National University · Georgia Institute of Technology

  42. Label-Free Reinforcement Learning via Cross-Model Entropy

    May 27, 2026Matt Gorbett, Hossein ShiraziReinforcement Learning Post-TrainingCross-Entropy Losses

    Independent Researcher · San Diego State University

  43. Training-Inference Kernel Contracts: Bounding Divergence in Post-Training and Deployment

    May 26, 2026Bruce Changlong Xu, Lan WuReinforcement Learning Post-TrainingPost-Training

  44. GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training

    May 25, 2026Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2Reinforcement Learning Post-TrainingNoise-Aware

    Shanghai Jiao Tong University · Shanghai Maritime University

  45. Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models

    May 22, 2026Jade Zou, Tao Huang, Weijie Kong +7Accelerated SamplingReward Gradients

    Peking University · Tencent Hunyuan

  46. Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management

    May 16, 2026Carol Xuan Long, David Simchi-Levi, Feng Zhu +3Autonomous AgentsSupply Chain Optimization

    Harvard University · MIT/Purdue · MIT +2

  47. CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL

    May 14, 2026Zhenyang Ni, Yijiang Li, Ruochen Jiao +7Video GenerationReinforcement Learning Post-Training

    Northwestern University · University of California, San Diego · University of Oxford

  48. Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping

    May 11, 2026Haoyuan Sun, Jing Wang, Yuxin Song +9Modern Text-To-Image ModelsText-To-Image

    Nanyang Technological University · Baidu Inc. · Zhejiang University +3

  49. Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models

    May 11, 2026Andreas Bergmeister, Stefanie Jegelka, Nikolas Nüsken +2Generative Flow NetworksDiffusion Models

    1TU Munich, MCML · 2MIT CSAIL · 3King’s College London +2

  50. Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training

    May 8, 2026Jiaxuan Gao, Yongjian Guo, Zhong Guan +5World ModelsReinforcement Learning Post-Training

    Tianjin University · Tsinghua University · Swinburne University of Technology +1

  51. Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models

    May 8, 2026Xiaoze Liu, Dhananjay Ram, Yuting Zhang +3Reinforcement Learning Post-TrainingBetter Call Group Relative Policy Optimization

    1Purdue University · *Work done during an internship at Amazon. · 2AWS Agentic AI

  52. How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment

    May 7, 2026Rui Zhu, Weiheng Bai, Qiushi Wu +3Key-Value Cache CompressionReinforcement Learning Post-Training

    Yale University · University of Minnesota Twin Cities · Indiana University Bloomington

  53. On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR

    May 7, 2026Hao Ye, Jisheng Dang, Junfeng Fang +7Reinforcement Learning With Verifiable RewardReinforcement Learning Post-Training

    Lanzhou University · National University of Singapore · Beijing Institute of Technology

  54. SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models

    Apr 22, 2026Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr +2Multimodal Large Language ModelsRecent Vision-Language Models

    Max Planck Institute for Informatics, SIC · VIA Research Center · Google

  55. A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions

    Apr 19, 2026Zhiyin Yu, Yuchen Mou, Juncheng Yan +17Large Language Model Reinforcement LearningLarge Language Model Training

    1Peking University · 2Shanghai Artificial Intelligence Laboratory · 3National University of Singapore +6

  56. Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training

    Apr 17, 2026Moein Salimi, Babak Hosseini Mohtasham, Amin Aghakasiri +6Scientific IdeationLarge Language Model Reinforcement Learning

    Sharif University of Technology · University of Tehran · Sharif University of Technology[cs.AI]

  57. Policy Improvement Reinforcement Learning

    Apr 1, 2026Huaiyang Wang, Xiaojie Li, Xiaohan Wang +10Reinforcement Learning Post-TrainingDistributional Reinforcement Learning

    Beihang University · Meituan · Peking University

  58. Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models

    Mar 13, 2026David McAllister, Miika Aittala, Tero Karras +4Text-To-Image Diffusion ModelsReinforcement Learning Post-Training

    UC Berkeley · NVIDIA

  59. When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On

    Mar 5, 2026Wisdom Ikezogwo, Mehmet Saygin Seyfioglu, Ranjay Krishna +1Reward SignalVirtual Try-On

    University of Washington, Seattle, USA · Amazon, Seattle, USA · Allen Institute for AI

  60. Understanding Reward Hacking in Text-to-Image Reinforcement Learning

    Jan 6, 2026Yunqi Hong, Kuei-Chun Kao, Hengguang Zhou +1Text-To-ImageReinforcement Learning Post-Training

    Department of Computer Science, University of California, Los Angeles