The rapid emergence of Vision-Language-Action models (VLAs) has a significant impact on robotics. However, their deployment remains complex due to the fragmented interfaces and the inherent communication latency in distributed setups. To address this, we introduce VLAgents, a modular policy server that abstracts VLA inferencing behind a unified Gymnasium-style protocol. Crucially, its communication layer transparently adapts to the context by supporting both zero-copy shared memory for high-speed simulation and compressed streaming for remote hardware. In this work, we present the architecture of VLAgents and validate it by integrating seven policies -- including OpenVLA and Pi Zero. In a benchmark with both local and remote communication, we further demonstrate how it outperforms the default policy servers provided by OpenVLA, OpenPi, and LeRobot. VLAgents is available at https://github.com/RobotControlStack/vlagents
@article{arxiv.2601.11250,
title = {VLAgents: A Policy Server for Efficient VLA Inference},
author = {Tobias Jülg and Khaled Gamal and Nisarga Nilavadi and Pierre Krack and Seongjin Bien and Michael Krawez and Florian Walter and Wolfram Burgard},
journal= {arXiv preprint arXiv:2601.11250},
year = {2026}
}