_version_ 1866915756422201344
author Kang, Li
Zhou, Heng
Song, Xiufeng
Li, Rui
Chen, Bruno N. Y.
Wang, Ziye
Meng, Ximeng
Tao, Stone
Qin, Yiran
Liu, Xiaohong
Zhang, Ruimao
Bai, Lei
Du, Yilun
Su, Hao
Torr, Philip
Yin, Zhenfei
Gong, Ruihao
Zeng, Yejun
Zhong, Fengjun
Jin, Shenghao
Guo, Jinyang
Liu, Xianglong
Jia, Xiaojun
Shan, Tianqi
Ren, Wenqi
Qin, Simeng
Yang, Jialing
Ma, Xiaoyu
Chen, Tianxing
Li, Zixuan
Cai, Zijian
Qin, Yan
Qin, Yusen
Chen, Qiangyu
Wang, Kaixuan
Han, Zhaoming
Mu, Yao
Luo, Ping
Yao, Yuanqi
Song, Haoming
Zaech, Jan-Nico
Despinoy, Fabien
Paudel, Danda Pani
Van Gool, Luc
author_facet Kang, Li
Zhou, Heng
Song, Xiufeng
Li, Rui
Chen, Bruno N. Y.
Wang, Ziye
Meng, Ximeng
Tao, Stone
Qin, Yiran
Liu, Xiaohong
Zhang, Ruimao
Bai, Lei
Du, Yilun
Su, Hao
Torr, Philip
Yin, Zhenfei
Gong, Ruihao
Zeng, Yejun
Zhong, Fengjun
Jin, Shenghao
Guo, Jinyang
Liu, Xianglong
Jia, Xiaojun
Shan, Tianqi
Ren, Wenqi
Qin, Simeng
Yang, Jialing
Ma, Xiaoyu
Chen, Tianxing
Li, Zixuan
Cai, Zijian
Qin, Yan
Qin, Yusen
Chen, Qiangyu
Wang, Kaixuan
Han, Zhaoming
Mu, Yao
Luo, Ping
Yao, Yuanqi
Song, Haoming
Zaech, Jan-Nico
Despinoy, Fabien
Paudel, Danda Pani
Van Gool, Luc
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18733
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge
Kang, Li
Zhou, Heng
Song, Xiufeng
Li, Rui
Chen, Bruno N. Y.
Wang, Ziye
Meng, Ximeng
Tao, Stone
Qin, Yiran
Liu, Xiaohong
Zhang, Ruimao
Bai, Lei
Du, Yilun
Su, Hao
Torr, Philip
Yin, Zhenfei
Gong, Ruihao
Zeng, Yejun
Zhong, Fengjun
Jin, Shenghao
Guo, Jinyang
Liu, Xianglong
Jia, Xiaojun
Shan, Tianqi
Ren, Wenqi
Qin, Simeng
Yang, Jialing
Ma, Xiaoyu
Chen, Tianxing
Li, Zixuan
Cai, Zijian
Qin, Yan
Qin, Yusen
Chen, Qiangyu
Wang, Kaixuan
Han, Zhaoming
Mu, Yao
Luo, Ping
Yao, Yuanqi
Song, Haoming
Zaech, Jan-Nico
Despinoy, Fabien
Paudel, Danda Pani
Van Gool, Luc
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
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.
title Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.18733