Abstract
The emergence of Vision Language Action (VLA) models marks a paradigm shift from traditional policy-based control to generalized robotics, reframing Vision Language Models (VLMs) from passive sequence generators into active agents for manipulation and decision-making in complex, dynamic environments. This survey delves into advanced VLA methods, aiming to provide a clear taxonomy and a systematic, comprehensive review of existing research. It presents a comprehensive analysis of VLA applications across different scenarios and classifies VLA approaches into several paradigms: autoregression-based, diffusion-based, reinforcement-based, hybrid, and specialized methods; while examining their motivations, core strategies, and implementations in detail. In addition, foundational datasets, benchmarks, and simulation platforms are introduced. Building on the current VLA landscape, the review further proposes perspectives on key challenges and future directions to advance research in VLA models and generalizable robotics. By synthesizing insights from over three hundred recent studies, this survey maps the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose VLA methods.
Abstract (translated)
视觉语言行动（VLA）模型的出现标志着从传统的基于策略控制向通用机器人技术的根本转变，将视觉语言模型（VLMs）从被动序列生成器转变为能够在复杂动态环境中进行操作和决策的主动代理。这项综述深入探讨了先进的VLA方法，旨在提供一个清晰的分类体系，并对现有的研究成果进行全面系统地回顾。它提供了关于VLA应用在不同场景下的全面分析，并将VLA方法分为几个范式：自回归基础、扩散基础、强化学习基础、混合和专门化方法；同时详细考察它们的动机、核心策略和实现方式。此外，综述还介绍了基础知识集、基准测试和仿真平台。 基于当前的VLA领域状况，综述进一步提出了关于关键挑战和未来方向的观点，以推进在VLA模型和通用机器人技术的研究。通过综合超过三百项近期研究的见解，这项调查绘制了这一快速发展的领域的轮廓，并突显了将塑造可扩展、通用目的VLA方法的发展机遇与挑战。
URL
https://arxiv.org/abs/2509.19012
