Recent multi-agent frameworks have broadened the ability to tackle oncology decision support tasks that require reasoning over dynamic, heterogeneous patient data. We propose Contribution-Aware Medical Multi-Agents (CoMMa), a decentralized LLM-agent framework in which specialists operate on partitioned evidence and coordinate through a game-theoretic objective for robust decision-making. In contrast to most agent architectures relying on stochastic narrative-based reasoning, CoMMa utilizes deterministic embedding projections to approximate contribution-aware credit assignment. This yields explicit evidence attribution by estimating each agent's marginal utility, producing interpretable and mathematically grounded decision pathways with improved stability. Evaluated on diverse oncology benchmarks, including a real-world multidisciplinary tumor board dataset, CoMMa achieves higher accuracy and more stable performance than data-centralized and role-based multi-agents baselines.

翻译：近年来，多智能体框架拓展了处理肿瘤学决策支持任务的能力，这些任务需要对动态、异质的患者数据进行推理。我们提出贡献感知医疗多智能体（CoMMa），这是一个去中心化的LLM智能体框架，其中各专科智能体基于分区证据进行操作，并通过博弈论目标进行协调以实现稳健决策。与大多数依赖随机叙事推理的智能体架构不同，CoMMa利用确定性嵌入投影来近似实现贡献感知的信用分配。该方法通过估计每个智能体的边际效用，产生明确的证据归因，从而生成可解释且具有数学依据的决策路径，并提高了稳定性。在包括真实世界多学科肿瘤委员会数据集在内的多种肿瘤学基准测试中，CoMMa相比数据集中式和基于角色的多智能体基线方法，实现了更高的准确性和更稳定的性能。