aiqbench analysis
MedLatentDx proposes a novel framework for cross-hospital rare-disease diagnosis that leverages latent multi-agent communication to balance collaborative AI performance with strict patient privacy constraints. By transmitting compact KV blocks instead of raw clinical text, the system effectively mitigates data leakage risks while supporting both same-backbone and heterogeneous LLM architectures across institutional boundaries. This research advances the practical deployment of large language models in sensitive healthcare environments where distributed training or inference is necessary but regulated by rigorous confidentiality standards.
MedLatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis
arXiv:2606.13945v1 Announce Type: new Abstract: Rare diseases affect over $300$ million patients across more than $7{,}000$ conditions, yet no single hospital encounters enough cases of any one condition for reliable diagnosis. Cross-hospital collaboration could help by allowing a diagnosing institution to use distributed, case-specific diagnostic evidence, but privacy regulations restrict the transmission of identifiable clinical text across institutional boundaries. This setting raises two challenges: existing medical agent systems often rely on textual evidence exchange, while raw latent states such as hidden states and KV caches may still reveal prompt-derived clinical content. We introduce MedLatentDx, a latent multi-agent communication framework in which hospital agents keep private clinical records and retrieved cases local, and send compact latent KV blocks to a host agent for rare-disease diagnosis. MedLatentDx supports two deployment settings: same-backbone hospital agents use latent KV distillation, while hospitals with different LLM backbones use cross-family latent alignment. On CrossRare-Bench, a self-built large-scale rare-disease benchmark with hospital-level partitions, MedLatentDx improves cross-hospital diagnostic performance while reducing reconstructable clinical content relative to raw-latent communication baselines.
Abstract:Rare diseases affect over $300$ million patients across more than $7{,}000$ conditions, yet no single hospital encounters enough cases of any one condition for reliable diagnosis. Cross-hospital collaboration could help by allowing a diagnosing institution to use distributed, case-specific diagnostic evidence, but privacy regulations restrict the transmission of identifiable clinical text across institutional boundaries. This setting raises two challenges: existing medical agent systems often rely on textual evidence exchange, while raw latent states such as hidden states and KV caches may still reveal prompt-derived clinical content. We introduce MedLatentDx, a latent multi-agent communication framework in which hospital agents keep private clinical records and retrieved cases local, and send compact latent KV blocks to a host agent for rare-disease diagnosis. MedLatentDx supports two deployment settings: same-backbone hospital agents use latent KV distillation, while hospitals with different LLM backbones use cross-family latent alignment. On CrossRare-Bench, a self-built large-scale rare-disease benchmark with hospital-level partitions, MedLatentDx improves cross-hospital diagnostic performance while reducing reconstructable clinical content relative to raw-latent communication baselines.
Computation and Language (cs.CL)
arXiv:2606.13945 [cs.CL]
(or arXiv:2606.13945v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.13945 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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 · 261 words
Related coverage
LatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis
arXiv · Sep 10, 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication
arXiv · Sep 30, 2026
News
Quantum Computing Report · Jul 25, 2026