Due to their ability of follow natural language instructions, vision-language-action (VLA) models are increasingly prevalent in the embodied AI arena, following the widespread success of their precursors -- LLMs and VLMs. In this paper, we discuss 10 principal milestones in the ongoing development of VLA models -- multimodality, reasoning, data, evaluation, cross-robot action generalization, efficiency, whole-body coordination, safety, agents, and coordination with humans. Furthermore, we discuss the emerging trends of using spatial understanding, modeling world dynamics, post training, and data synthesis -- all aiming to reach these milestones. Through these discussions, we hope to bring attention to the research avenues that may accelerate the development of VLA models into wider acceptability.
@article{arxiv.2511.05936,
title = {10 Open Challenges Steering the Future of Vision-Language-Action Models},
author = {Soujanya Poria and Navonil Majumder and Chia-Yu Hung and Amir Ali Bagherzadeh and Chuan Li and Kenneth Kwok and Ziwei Wang and Cheston Tan and Jiajun Wu and David Hsu},
journal= {arXiv preprint arXiv:2511.05936},
year = {2025}
}