Pretrained on large-scale and diverse datasets, VLA models demonstrate strong generalization and adaptability as general-purpose robotic policies. However, Supervised Fine-Tuning (SFT), which serves as the primary mechanism for adapting VLAs to downstream domains, requires substantial amounts of task-specific data and is prone to catastrophic forgetting. To address these limitations, we propose LifeLong-RFT, a simple yet effective Reinforcement Fine-Tuning (RFT) strategy for VLA models independent of online environmental feedback and pre-trained reward models. By integrating chunking-level on-policy reinforcement learning with the proposed multi-dimensional process reward mechanism, LifeLong-RFT quantifies the heterogeneous contributions of intermediate action chunks across three dimensions to facilitate policy optimization. Specifically, (1) the Quantized Action Consistency Reward (QACR) ensures accurate action prediction within the discrete action space; (2) the Continuous Trajectory Alignment Reward (CTAR) aligns decoded continuous action chunks with reference trajectories to ensure precise control; (3) the Format Compliance Reward (FCR) guarantees the structural validity of outputs. Comprehensive experiments across SimplerEnv, LIBERO, and real-world tasks demonstrate that LifeLong-RFT exhibits strong performance in multi-task learning. Furthermore, for continual learning on the LIBERO benchmark, our method achieves a 22% gain in average success rate over SFT, while effectively adapting to new tasks using only 20% of the training data. Overall, our method provides a promising post-training paradigm for VLAs. The project page is available at <https://yuan-liu-lifelong-rft.github.io>.
CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
Technical University of Munich（慕尼黑技术大学）；TUM School of Computation, Information and Technology（TUM计算、信息与技术学院）；Department of Computer Engineering, Learning Systems and Robotics Lab（计算机工程系、学习系统与机器人实验室）；Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与机器智能研究所（MIRMI））；Robotics Institute Germany（德国机器人研究所）；Munich Center for Machine Learning（慕尼黑机器学习中心）
OrthoSkillVLA: Continual Skill Learning via Gradient-Informed Skill Subspace Adaptation
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；School of Electronic Science and Engineering, Southeast University（东南大学电子科学与工程学院）
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics（库勒恩大学，机械工程系，机器人、自动化与机电一体化研究单位）；KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images（库勒恩大学，电气工程系，语音和图像处理研究单位）
VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning
State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
Department of Automation, BNRist, Tsinghua University（自动化系、BNRist、清华大学）；Dexmal；MEGVII Technology（MEGVII技术）；Tianjin University（天津大学）；Harbin Institute of Technology（哈尔滨工业大学）；StepFun
