Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；the School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Balancing high-level semantic reasoning with low-level reactive control remains a core challenge in visual robotic manipulation. While Vision-Language Models (VLMs) excel at cognitive planning, their inference latency precludes real-time execution. Conversely, fast Vision-Language-Action (VLA) models often lack the semantic depth required for complex, long-horizon tasks. To bridge this gap, we introduce Critic in the Loop, an adaptive hierarchical framework driven by dynamic VLM-Expert scheduling. At its core is a bionic Tri-System architecture comprising a VLM brain for global reasoning, a VLA cerebellum for reactive execution, and a lightweight visual Critic. By continuously monitoring the workspace, the Critic dynamically routes control authority. It sustains rapid closed-loop execution via the VLA for routine subtasks, and adaptively triggers the VLM for replanning upon detecting execution anomalies such as task stagnation or failures. Furthermore, our architecture seamlessly integrates human-inspired rules to intuitively break infinite retry loops. This visually-grounded scheduling minimizes expensive VLM queries, while substantially enhancing system robustness and autonomy in out-of-distribution (OOD) scenarios. Comprehensive experiments on challenging, long-horizon manipulation benchmarks reveal that our approach achieves state-of-the-art performance.
VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
University of Sydney（悉尼大学）；Central South University（中央南大学）；University of Science and Technology of China（中国科学技术大学）；Sensetime Research（商汤科技研究院）；Hong Kong University of Science and Technology（香港理工大学）
Imagine-RL: Residual-Confidence-Guided Cross-Attention for World-Model-Augmented VLA Reinforcement Learning
Korea Advanced Institute of Science and Technology（韩国科学技术院）；University of Science and Technology Beijing（北京科技大学）；Shanghai Jiao Tong University（上海交通大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
eRLT: Efficient VLA Reinforcement Learning via Action-Relevant Token Routing
Southern University of Science and Technology（南方科技大学）；Beijing Zhongguancun Academy（北京中关村学院）；Samsung Robotics eXperience（三星机器人体验中心）；Wuhan University（武汉大学）；Sun Yat-sen University（中山大学）
TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors
School of Computer Science, Wuhan University（武汉大学计算机科学学院）；D-Robotics（D-机器人公司）；HUST（华中科技大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness
School of Computer Science, Peking University（北京大学计算机科学学院）；ZTE Corporation（中兴通讯）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；School of Computer Science, China University of Geosciences (Wuhan)（中国地质大学（武汉）计算机科学学院）；School of Electronics Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）
VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesis
School of computing and data science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）；School of Software Engineering, Sun Yat-sen University（软件工程学院，中山大学）；GuangDong Engineering Technology Research Center of Blockchain, China（区块链工程技术研发中心，中国）；Northwest A&F University（西北农林科技大学）
Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning
Stanford University（斯坦福大学）；Technical University of Munich（慕尼黑技术大学）；University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（人工智能研究院）
VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action Models
Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China（南方科技大学电子与电气工程系，深圳，中国）；Zhongguancun Academy, Beijing, China（中关村学院，北京，中国）；National Cybersecurity Academy, Wuhan University, Wuhan, China（武汉大学国家网络安全学院，武汉，中国）
DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation
Institute for Artificial Intelligence（人工智能研究院）；School of Integrated Circuits, Peking University（集成电路学院，北京大学）；Shenzhen Institute of Artificial Intelligence（深圳人工智能研究所）；School of Electronics Engineering and Computer Science, Peking University（电子工程与计算机科学学院，北京大学）；Beijing Advanced Innovation Center for Integrated Circuits（北京集成电路先进制造创新中心）
TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation
Meituan（美团）；Beijing Institute of Technology（北京理工大学）；Beihang University（北京航空航天大学）；State Key Lab of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；China University of Mining and Technology (Beijing)（中国矿业大学（北京））
QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing Zhongke Huiling Robot Technology Co.（北京中科创联机器人科技有限公司）
VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
School of Computer Science, University of Sydney（悉尼大学计算机科学学院）；John Hopcropt Center for Computer Science, Shanghai Jiao Tong University（上海交通大学约翰·霍普克罗夫特计算机科学中心）
