Imagen de Portada

Long-Term Memory for VLA-based Agents in Open-World Task Execution

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Xu, Mao, Weixin, Li, Yinhao, Chen, Hua, Zhao, Jiabao
Formato:	Preprint
Publicado:	2026
Materias:	Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ARM: Advantage Reward Modeling for Long-Horizon Manipulation
por: Mao, Yiming, et al.
Publicado: (2026)

SwitchVLA: Execution-Aware Task Switching for Vision-Language-Action Models
por: Li, Meng, et al.
Publicado: (2025)

RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World
por: Mao, Weixin, et al.
Publicado: (2024)

Sci-VLA: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments
por: Pang, Yiwen, et al.
Publicado: (2026)

Ordering-Flexible Multi-Robot Coordination for MovingTarget Convoying Using Long-TermTask Execution
por: Hu, Bin-Bin, et al.
Publicado: (2024)

SeqVLA: Sequential Task Execution for Long-Horizon Manipulation with Completion-Aware Vision-Language-Action Model
por: Yang, Ran, et al.
Publicado: (2025)

FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model
por: Xu, Xiaoxu, et al.
Publicado: (2026)

EchoVLA: Synergistic Declarative Memory for VLA-Driven Mobile Manipulation
por: Lin, Min, et al.
Publicado: (2025)

WorldVLA: Towards Autoregressive Action World Model
por: Cen, Jun, et al.
Publicado: (2025)

EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks
por: Feng, Tongtong, et al.
Publicado: (2025)

KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
por: Wang, Zixuan, et al.
Publicado: (2024)

Galaxea Open-World Dataset and G0 Dual-System VLA Model
por: Jiang, Tao, et al.
Publicado: (2025)

Dexora: Open-source VLA for High-DoF Bimanual Dexterity
por: Zhang, Zongzheng, et al.
Publicado: (2026)

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
por: Wang, Kaijun, et al.
Publicado: (2025)

Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation
por: Zhang, Zhilong, et al.
Publicado: (2026)

Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning
por: Liu, Yuan, et al.
Publicado: (2026)

RynnVLA-002: A Unified Vision-Language-Action and World Model
por: Cen, Jun, et al.
Publicado: (2025)

MAkEable: Memory-centered and Affordance-based Task Execution Framework for Transferable Mobile Manipulation Skills
por: Pohl, Christoph, et al.
Publicado: (2024)

CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments
por: Lei, Mingcong, et al.
Publicado: (2025)

Reflection-Based Task Adaptation for Self-Improving VLA
por: Li, Baicheng, et al.
Publicado: (2025)

Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation
por: Fan, Yiguo, et al.
Publicado: (2025)

Environment Modeling for Service Robots From a Task Execution Perspective
por: Zhang, Ying, et al.
Publicado: (2025)

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
por: Xiao, Junjin, et al.
Publicado: (2025)

FUTURE-VLA: Forecasting Unified Trajectories Under Real-time Execution
por: Fan, Jingjing, et al.
Publicado: (2026)

LongBench: Evaluating Robotic Manipulation Policies on Real-World Long-Horizon Tasks
por: Chen, Xueyao, et al.
Publicado: (2026)

Long-Horizon Manipulation via Trace-Conditioned VLA Planning
por: Liu, Isabella, et al.
Publicado: (2026)

Language-Augmented Symbolic Planner for Open-World Task Planning
por: Chen, Guanqi, et al.
Publicado: (2024)

LLM-State: Open World State Representation for Long-horizon Task Planning with Large Language Model
por: Chen, Siwei, et al.
Publicado: (2023)

Searching in Space and Time: Unified Memory-Action Loops for Open-World Object Retrieval
por: Chen, Taijing, et al.
Publicado: (2025)

ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration
por: Zhu, Minjie, et al.
Publicado: (2025)

High-Level, Collaborative Task Planning Grammar and Execution for Heterogeneous Agents
por: Fang, Amy, et al.
Publicado: (2024)

StageCraft: Execution Aware Mitigation of Distractor and Obstruction Failures in VLA Models
por: Pangaonkar, Kartikay Milind, et al.
Publicado: (2026)

HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
por: Hu, Mengkang, et al.
Publicado: (2024)

VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
por: Li, Wenhao, et al.
Publicado: (2026)

BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning
por: Wang, Ruiheng, et al.
Publicado: (2026)

VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
por: Jiang, Yuhua, et al.
Publicado: (2026)

SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks
por: Li, Jialiang, et al.
Publicado: (2025)

Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving
por: Liu, Qiqi, et al.
Publicado: (2026)

ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation
por: Qian, Jingjing, et al.
Publicado: (2026)

World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
por: Liu, Xiaokang, et al.
Publicado: (2026)