From MAS to MARS: Coordination Failures and Reasoning Trade-offs in Hierarchical Multi-Agent Robotic Systems within a Healthcare Scenario

2025-08-06

AI Summary

Multi-agent robotic systems (MARS) deployed in clinical settings suffer from two critical deployment bottlenecks: coordination failures—including tool contention and delayed fault response—and inherent trade-offs between reasoning overhead and decision quality—both of which cannot be resolved solely through contextual knowledge. Method: We construct a hierarchical multi-robot simulation environment to empirically analyze system behavior under coupled physical constraints and task logic; propose a principled transition framework from generic multi-agent systems to MARS, exposing the fundamental tension between autonomy and stability; identify six context-insoluble coordination failure patterns using CrewAI; and quantify the performance–cost trade-off between reasoning and non-reasoning models on realistic collaborative tasks via AutoGen. Contribution/Results: Our work delivers a reproducible taxonomy of MARS failures and empirically grounded guidelines for model selection, advancing the reliable deployment of autonomous robotic systems in safety-critical medical environments.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Coordination and Collaboration
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Multi-agent robotic systems (MARS) build upon multi-agent systems by integrating physical and task-related constraints, increasing the complexity of action execution and agent coordination. However, despite the availability of advanced multi-agent frameworks, their real-world deployment on robots remains limited, hindering the advancement of MARS research in practice. To bridge this gap, we conducted two studies to investigate performance trade-offs of hierarchical multi-agent frameworks in a simulated real-world multi-robot healthcare scenario. In Study 1, using CrewAI, we iteratively refine the system's knowledge base, to systematically identify and categorize coordination failures (e.g., tool access violations, lack of timely handling of failure reports) not resolvable by providing contextual knowledge alone. In Study 2, using AutoGen, we evaluate a redesigned bidirectional communication structure and further measure the trade-offs between reasoning and non-reasoning models operating within the same robotic team setting. Drawing from our empirical findings, we emphasize the tension between autonomy and stability and the importance of edge-case testing to improve system reliability and safety for future real-world deployment. Supplementary materials, including codes, task agent setup, trace outputs, and annotated examples of coordination failures and reasoning behaviors, are available at: https://byc-sophie.github.io/mas-to-mars/.

Problem

• Investigating coordination failures in hierarchical multi-agent robotic healthcare systems
• Evaluating trade-offs between reasoning and non-reasoning models in robotic teams
• Addressing autonomy-stability tension for reliable real-world MARS deployment

Innovation

• Iterative refinement of knowledge base
• Bidirectional communication structure redesign
• Trade-offs between reasoning models