Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge

TL;DR

The paper introduces the MARS Challenge at NeurIPS 2025, focusing on advancing multi-agent embodied planning and control in robotics using vision-language models to foster scalable and collaborative AI solutions.

Contribution

It presents a new competition framework for evaluating multi-agent embodied planning and control, highlighting innovative approaches in vision-language models for robotics.

Findings

Insights into multi-agent system coordination

Evaluation of vision-language models in dynamic environments

Advancements in collaborative robotic manipulation

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.