Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models

arXiv:2605.13119 · cs.RO, cs.AI, cs.CV · Submitted 2026-05-13 · Read on arXiv

cs.RO, cs.AI, cs.CV

Submitted: 2026-05-13

Updated: 2026-10-12

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fidelity — 1× in this paper · explained in 2 episodes
• Temporal Reasoning — 1× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 4 episodes

Sources

• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• RT-H: Action Hierarchies Using Language
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets
• Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation
• When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
• Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
• LoRA: Low-Rank Adaptation of Large Language Models
• ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
• Inner Monologue: Embodied Reasoning through Planning with Language Models
• BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning
• OpenVLA: An Open-Source Vision-Language-Action Model
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• Code as Policies: Language Model Programs for Embodied Control
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
• RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
• Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning
• PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies