arXiv cs.AI· Yichen Wu, Kailong Fan, Sangjoon Park, Yuhan Liu, Zhiyi Shi, Sekeun Kim, Dania Daye, Hana Farzaneh, Xiang Li, Raul Uppot, Yujin Oh, Quanzheng Li·· 6 天前AI 评分22
CoMMa：贡献感知的医疗多智能体框架，实现去中心化肿瘤决策支持
CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
AI 导读
研究者提出 CoMMa，一个去中心化 LLM 智能体框架，让专科智能体各自在分区的临床数据流上运行，并通过智能体专属微调强化角色专业化。该框架引入贡献感知聚合机制，用确定性嵌入向量投影替代随机叙事式推理来近似各智能体的边际效用，实现显式信用分配。CoMMa 在多个肿瘤学基准上评估，包括北美与东亚大型学术医院的真实多学科肿瘤委员会数据集及公开数据集，展现出跨异构临床环境的性能与泛化能力。
正文 · 原文
Authors:Yichen Wu, Kailong Fan, Sangjoon Park, Yuhan Liu, Zhiyi Shi, Sekeun Kim, Dania Daye, Hana Farzaneh, Xiang Li, Raul Uppot, Yujin Oh, Quanzheng Li
Abstract: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.
| Comments: | 9 pages, 5 figures |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2602.09159 [cs.AI] |
| (or arXiv:2602.09159v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2602.09159 arXiv-issued DOI via DataCite |
Submission history
From: Yichen Wu [view email]
[v1]
Mon, 9 Feb 2026 20:04:58 UTC (7,168 KB)
[v2]
Tue, 25 Aug 2026 01:03:48 UTC (5,070 KB)
[v3]
Thu, 8 Oct 2026 19:22:55 UTC (5,070 KB)
来源：arXiv cs.AI · arxiv.org