CoMMa: Contribution-Aware Medical Multi-Agents From A Game-Theoretic Perspective
This work addresses oncology decision-making for medical professionals by improving interpretability and stability in multi-agent systems, though it is incremental as it builds on existing multi-agent frameworks with a novel coordination method.
The paper tackled the problem of oncology decision support by proposing CoMMa, a decentralized LLM-agent framework that uses game-theoretic coordination and deterministic embedding projections for contribution-aware credit assignment, achieving higher accuracy and more stable performance on diverse oncology benchmarks compared to baselines.
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.