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

2026-01-26

AI Summary

This work addresses the challenges of multi-agent collaboration in complex dynamic environments, particularly in task allocation, coordinated execution, and human–robot interaction. To advance this field, the authors launched the MARS Challenge—the first systematic initiative at a NeurIPS Workshop to promote collaborative planning and control in embodied multi-agent AI. The proposed approach integrates vision–language models (VLMs) for high-level task planning with policy execution techniques to enable robotic manipulation. Evaluation of competition submissions yielded critical insights into scalable architectures, efficient coordination mechanisms, and advanced human–agent interaction for embodied multi-agent systems, significantly advancing the development of collaborative AI.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Intelligent Robots: Multi-Robot Systems
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• multi-agent collaboration
• embodied AI
• vision-language models
• robotic manipulation
• dynamic environments

Innovation

• Multi-Agent Robotic System
• Vision-Language Models
• Embodied AI
• Collaborative Planning
• Task Delegation