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.
@article{arxiv.2602.09159,
title = {CoMMa: Contribution-Aware Medical Multi-Agents From A Game-Theoretic Perspective},
author = {Yichen Wu and Yujin Oh and Sangjoon Park and Kailong Fan and Dania Daye and Hana Farzaneh and Xiang Li and Raul Uppot and Quanzheng Li},
journal= {arXiv preprint arXiv:2602.09159},
year = {2026}
}