# Before Humans Join the Team: Diagnosing Coordination Failures in Healthcare Robot Team Simulation

arXiv: https://arxiv.org/abs/2508.04691 · HTML: https://mlsanity.com/paper/2508.04691/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 14 of 14)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse](https://mlsanity.com/paper/2410.21333/) (2024)
- [ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2503.09501/) (2025)
- [Reinforce LLM Reasoning through Multi-Agent Reflection](https://mlsanity.com/paper/2506.08379/) (2025)
- [Advancing Multi-Agent Systems Through Model Context Protocol: Architecture, Implementation, and Applications](https://mlsanity.com/paper/2504.21030/) (2025)
- [Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS](https://mlsanity.com/paper/2506.01245/) (2025)
- [Can Large Language Models Be Trusted Paper Reviewers? A Feasibility Study](https://mlsanity.com/paper/2506.17311/) (2025)
- [AutoGen Driven Multi Agent Framework for Iterative Crime Data Analysis and Prediction](https://mlsanity.com/paper/2506.11475/) (2025)

## Built on by (most cited first, 1 of 1)

- [Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge](https://mlsanity.com/paper/2609.10724/) (2026)

## Abstract (arXiv)

As humans move toward collaborating with coordinated robot teams, understanding how these teams coordinate and fail is essential for building trust and ensuring safety. However, exposing human collaborators to coordination failures during early-stage development is costly and risky, particularly in high-stakes domains such as healthcare. We adopt an agent-simulation approach in which all team roles, including the supervisory manager, are instantiated as LLM agents, allowing us to diagnose coordination failures before humans join the team. Using a controllable healthcare scenario, we conduct two studies with different hierarchical configurations to analyze coordination behaviors and failure patterns. Our findings reveal that team structure, rather than contextual knowledge or model capability, constitutes the primary bottleneck for coordination, and expose a tension between reasoning autonomy and system stability. By surfacing these failures in simulation, we prepare the groundwork for safe human integration. These findings inform the design of resilient robot teams with implications for process-level evaluation, transparent coordination protocols, and structured human integration. 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/.