VLAgents: A Policy Server for Efficient VLA Inference
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914259310477312 |
|---|---|
| author | Jülg, Tobias Gamal, Khaled Nilavadi, Nisarga Krack, Pierre Bien, Seongjin Krawez, Michael Walter, Florian Burgard, Wolfram |
| author_facet | Jülg, Tobias Gamal, Khaled Nilavadi, Nisarga Krack, Pierre Bien, Seongjin Krawez, Michael Walter, Florian Burgard, Wolfram |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11250 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VLAgents: A Policy Server for Efficient VLA Inference Jülg, Tobias Gamal, Khaled Nilavadi, Nisarga Krack, Pierre Bien, Seongjin Krawez, Michael Walter, Florian Burgard, Wolfram Robotics 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 |
| title | VLAgents: A Policy Server for Efficient VLA Inference |
| topic | Robotics |
| url | https://arxiv.org/abs/2601.11250 |