From Virtual Agents to Robot Teams: A Multi-Robot Framework Evaluation in High-Stakes Healthcare Context

2025-06-04

AI Summary

This work identifies fundamental limitations of current multi-agent system (MAS) frameworks—e.g., CrewAI—when deployed on physical multi-robot systems: neglect of spatial constraints, robot embodiment (perception/navigation capabilities), and procedural compliance in high-stakes domains such as healthcare. These omissions manifest in five recurrent failure modes: role misalignment, tool privilege escalation, delayed fault response, workflow circumvention, and spurious reporting. To address these, we propose three physics-aware design principles: process transparency, proactive fault recovery, and tight context coupling. We implement these via a hierarchical multi-robot agent architecture built atop CrewAI, integrating sensing, navigation, and task orchestration modules. The framework is rigorously evaluated in an emergency department simulation environment. Our study not only uncovers critical system vulnerabilities but also delivers transferable engineering guidelines for robust Multi-Agent Robotic Systems (MARS).

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Multiagent Planning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Advancements in generative models have enabled multi-agent systems (MAS) to perform complex virtual tasks such as writing and code generation, which do not generalize well to physical multi-agent robotic teams. Current frameworks often treat agents as conceptual task executors rather than physically embodied entities, and overlook critical real-world constraints such as spatial context, robotic capabilities (e.g., sensing and navigation). To probe this gap, we reconfigure and stress-test a hierarchical multi-agent robotic team built on the CrewAI framework in a simulated emergency department onboarding scenario. We identify five persistent failure modes: role misalignment; tool access violations; lack of in-time handling of failure reports; noncompliance with prescribed workflows; bypassing or false reporting of task completion. Based on this analysis, we propose three design guidelines emphasizing process transparency, proactive failure recovery, and contextual grounding. Our work informs the development of more resilient and robust multi-agent robotic systems (MARS), including opportunities to extend virtual multi-agent frameworks to the real world.

Problem

• Evaluates multi-robot frameworks in healthcare for real-world constraints
• Identifies failure modes in robotic team coordination and execution
• Proposes design guidelines for resilient multi-agent robotic systems

Innovation

• Hierarchical multi-agent robotic team framework
• Simulated emergency department stress-testing
• Design guidelines for process transparency