aiqbench analysis
This paper introduces CoMMa, a decentralized multi-agent framework designed for oncology decision support that addresses privacy constraints by partitioning clinical data streams among specialized agents. By replacing stochastic narrative reasoning with deterministic embedding projections, the system achieves explicit credit assignment and interpretable coordination without relying on centralized data access. The approach demonstrates strong generalization across heterogeneous clinical settings using real-world tumor board datasets from North America and East Asia.
CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
arXiv:2602.09159v2 Announce Type: replace 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.
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.
Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
arXiv:2602.09159 [cs.AI]
(or arXiv:2602.09159v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2602.09159 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 247 words
Related coverage
News
Quantum Computing Report · Jun 7, 2026
QoS-Aware Token Scheduling and Private Data Valuation for Multi-Modal Agentic Networks
arXiv · Jun 17, 2026
QoS-Aware Token Scheduling and Private Data Valuation for Multi-Modal Agentic Networks
arXiv · Jun 16, 2026
ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
arXiv · Jun 12, 2026