Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge
Abstract
Recent advancements in multimodal large language models and vision-languageaction models have significantly driven progress in Embodied AI. As the field transitions toward more complex task scenarios, multi-agent system frameworks are becoming essential for achieving scalable, efficient, and collaborative solutions. This shift is fueled by three primary factors: increasing agent capabilities, enhancing system efficiency through task delegation, and enabling advanced human-agent interactions. To address the challenges posed by multi-agent collaboration, we propose the Multi-Agent Robotic System (MARS) Challenge, held at the NeurIPS 2025 Workshop on SpaVLE. The competition focuses on two critical areas: planning and control, where participants explore multi-agent embodied planning using vision-language models (VLMs) to coordinate tasks and policy execution to perform robotic manipulation in dynamic environments. By evaluating solutions submitted by participants, the challenge provides valuable insights into the design and coordination of embodied multi-agent systems, contributing to the future development of advanced collaborative AI systems.
Cite
@article{arxiv.2601.18733,
title = {Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge},
author = {Li Kang and Heng Zhou and Xiufeng Song and Rui Li and Bruno N. Y. Chen and Ziye Wang and Ximeng Meng and Stone Tao and Yiran Qin and Xiaohong Liu and Ruimao Zhang and Lei Bai and Yilun Du and Hao Su and Philip Torr and Zhenfei Yin and Ruihao Gong and Yejun Zeng and Fengjun Zhong and Shenghao Jin and Jinyang Guo and Xianglong Liu and Xiaojun Jia and Tianqi Shan and Wenqi Ren and Simeng Qin and Jialing Yang and Xiaoyu Ma and Tianxing Chen and Zixuan Li and Zijian Cai and Yan Qin and Yusen Qin and Qiangyu Chen and Kaixuan Wang and Zhaoming Han and Yao Mu and Ping Luo and Yuanqi Yao and Haoming Song and Jan-Nico Zaech and Fabien Despinoy and Danda Pani Paudel and Luc Van Gool},
journal= {arXiv preprint arXiv:2601.18733},
year = {2026}
}
Comments
MARS Challenge @ NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI. Challenge page: https://mars-eai.github.io/MARS-Challenge-Webpage/