MedLatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis

arXiv cs.CL Papers

Summary

MedLatentDx proposes a latent multi-agent communication framework for cross-hospital rare-disease diagnosis, using latent KV blocks to share diagnostic evidence without exposing clinical text, and introduces the CrossRare-Bench benchmark.

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.
Original Article
View Cached Full Text

Cached at: 06/15/26, 08:57 AM

# MedLatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis
Source: [https://arxiv.org/abs/2606.13945](https://arxiv.org/abs/2606.13945)
[View PDF](https://arxiv.org/pdf/2606.13945)

> 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\.

## Submission history

From: Ziqing Wang \[[view email](https://arxiv.org/show-email/f11fa665/2606.13945)\] **\[v1\]**Thu, 11 Jun 2026 22:11:25 UTC \(1,501 KB\)

Similar Articles

MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs

arXiv cs.CL

This paper introduces MedAction, a framework for training LLMs on active, multi-turn clinical diagnosis by simulating iterative test ordering and hypothesis updates. It presents a new dataset, MedAction-32K, and demonstrates state-of-the-art performance for open-source models on medical benchmarks.