从博弈论视角出发的贡献感知医疗多智能体：CoMMa
CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
AI总结：
CoMMa从博弈论视角提出一种去中心化医疗多智能体框架，通过确定性嵌入投影实现贡献感知的信用分配，提升肿瘤学决策支持的准确性和稳定性。
摘要：
最近的多智能体框架扩大了处理需要在动态、异质患者数据上进行推理的肿瘤学决策支持任务的能力。我们提出了贡献感知医疗多智能体（CoMMa），一种去中心化的LLM智能体框架，其中专家在分割的证据上操作，并通过博弈论目标进行协调，以实现稳健的决策制定。与大多数依赖于随机叙述式推理的智能体架构不同，CoMMa使用确定性嵌入投影来近似贡献感知的信用分配。这产生了明确的证据归属，通过估计每个智能体的边际效用，产生可解释且数学上严谨的决策路径，具有改进的稳定性。在多样化的肿瘤学基准上评估，包括一个真实世界的多学科肿瘤委员会数据集，CoMMa在准确性和稳定性方面均优于数据集中化和基于角色的多智能体基线。
英文摘要：
Recent multi-agent frameworks have shown promise for oncology decision support, yet most assume centralized data access and rely on prompt-based assignment, limiting their applicability in privacy-sensitive clinical settings. We propose Contribution-Aware Medical Multi-Agents (CoMMa), a decentralized LLM-agent framework where specialists operate on partitioned clinical data streams. Unlike prior approaches that share inputs across agents, CoMMa enforces data decentralization to include stronger role specialization and further enhances this via agent-specific finetuning. To enable reliable and interpretable coordination, we introduce a contribution-aware aggregation mechanism that replaces stochastic, narrative-based reasoning with deterministic embedding projections to approximate each agent's marginal utility. This yields explicit credit assignment over agents, providing a stable and interpretable decision pathway aligned with clinical requirements. We evaluate CoMMa on multiple oncology benchmarks, including real-world multidisciplinary tumor board datasets from large academic hospitals in North America and East Asia, as well as public datasets, demonstrating strong performance and generalization across heterogeneous clinical settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
