Large language models (LLMs) have proven effective in artificial intelligence, where the multi-agent system (MAS) holds considerable promise for healthcare development by achieving the collaboration of LLMs. However, the absence of a systematic pipeline for agent construction and the rigidity of static collaboration patterns render current MAS-based models vulnerable to collaboration failures, resulting in substantial performance degradation in medical decision-making scenarios. To this end, we propose a novel Masked Agent Collaboration (MAC) framework that harnesses Pareto-optimal agent construction and cross-consistency maximization mechanisms to achieve adaptive progressive propagation of collaborative information, boosting the medical decision-making capacity. Specifically, we first conduct a Pareto-frontier factors analysis towards the LLMs pool to consider their key factors, including the model size, inference time, diversity score, and throughput ratio, where we calculate the similarity between pairwise outputs within an LLM to derive its diversity score. Beyond this analysis, we enable the identification of Pareto-optimal models that balance efficiency and capability, which are subsequently selected as collaborative agents to consider the fundamental trade-offs inherent in practical LLM deployment. Afterward, we measure the pairwise similarity between the outputs from collaborative agents to determine their cross-consistency values, subsequently masking out the agent with the lowest cross-consistency value to eliminate the output that is likely semantically inconsistent. Finally, we conduct collaboration of agents by achieving adaptive progressive propagation, where each agent aggregates the outputs of unmasked agents from the previous layer as its input to generate the corresponding output via prompt engineering.

翻译：大语言模型（LLM）在人工智能领域已展现出显著成效，其中多智能体系统（MAS）通过实现LLM间的协作，在医疗健康领域发展中展现出巨大潜力。然而，由于缺乏系统化的智能体构建流程以及静态协作模式的僵化性，当前基于MAS的模型容易遭遇协作失效问题，导致其在医疗决策场景中性能显著下降。为此，我们提出了一种新颖的掩码智能体协作（MAC）框架，该框架利用帕累托最优智能体构建与跨一致性最大化机制，实现协作信息的自适应渐进式传播，从而提升医疗决策能力。具体而言，我们首先对LLM池进行帕累托前沿因子分析，综合考虑模型规模、推理时间、多样性得分和吞吐率等关键因素；其中，我们通过计算同一LLM内成对输出的相似度来推导其多样性得分。在此分析基础上，我们能够识别出平衡效率与性能的帕累托最优模型，随后将其选为协作智能体，以兼顾实际LLM部署中固有的基础权衡。之后，我们通过度量协作智能体输出间的成对相似度来确定其跨一致性值，进而掩蔽跨一致性值最低的智能体以排除可能语义不一致的输出。最后，我们通过自适应渐进式传播实现智能体协作：每个智能体聚合前一层未掩蔽智能体的输出作为其输入，并通过提示工程生成相应输出。