Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.09159 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912893473128448 |
|---|---|
| author | Wu, Yichen Oh, Yujin Park, Sangjoon Fan, Kailong Daye, Dania Farzaneh, Hana Li, Xiang Uppot, Raul Li, Quanzheng |
| author_facet | Wu, Yichen Oh, Yujin Park, Sangjoon Fan, Kailong Daye, Dania Farzaneh, Hana Li, Xiang Uppot, Raul Li, Quanzheng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09159 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoMMa: Contribution-Aware Medical Multi-Agents From A Game-Theoretic Perspective Wu, Yichen Oh, Yujin Park, Sangjoon Fan, Kailong Daye, Dania Farzaneh, Hana Li, Xiang Uppot, Raul Li, Quanzheng Artificial Intelligence Multiagent Systems 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. |
| title | CoMMa: Contribution-Aware Medical Multi-Agents From A Game-Theoretic Perspective |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2602.09159 |