mlsanityData to 14 Oct 2026

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

arXiv 2606.13945 ↗First posted 11 Jun 2026cs.CLcited by 2

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

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 LatentDx, 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. LatentDx 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, LatentDx improves cross-hospital diagnostic performance while reducing reconstructable clinical content relative to raw-latent communication baselines.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 24 of its 40 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

24 of 40 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025An Agentic System for Rare Disease Diagnosis with Traceable Reasoning25 Jun
  2. 2025MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow21 Mar
  3. 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents5 May

Other references · 21

  1. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  2. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  3. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  4. 2023Learning to Compress Prompts with Gist Tokenscited by 390
  5. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  6. 2023Think before you speak: Training Language Models With Pause Tokenscited by 264
  7. 2023CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Servingcited by 203
  8. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
  9. 2023Towards Building the Federated GPT: Federated Instruction Tuningcited by 185
  10. 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 128
  11. 2025Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Spacecited by 117
  12. 2022Federated Learning Enables Big Data for Rare Cancer Boundary Detectioncited by 84
9 more
  1. 2023DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Passcited by 67
  2. 2025Cache-to-Cache: Direct Semantic Communication Between Large Language Modelscited by 61
  3. 2024RareBench: Can LLMs Serve as Rare Diseases Specialists?cited by 45
  4. 2025Enabling Agents to Communicate Entirely in Latent Spacecited by 34
  5. 2025Depth Gives a False Sense of Privacy: LLM Internal States Inversioncited by 17
  6. 2026Latent Space Communication via K-V Cache Alignmentcited by 17
  7. 2023Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applicationscited by 10
  8. 2025KaVa: Latent Reasoning via Compressed KV-Cache Distillationcited by 8
  9. 2024PFID: Privacy First Inference Delegation Framework for LLMscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMscited by 3
  2. 2026MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records
  2. 2026Evaluating Multi-Agent LLM Architectures for Rare Disease Diagnosis
  3. 2026Within the MDT Room: Situated in Multidisciplinary Team-Grounded Agent Debate for Clinical Diagnosis
  4. 2025MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM
  5. 2026CaseWeaver: A Multi-Agent Framework for Multimodal Virtual Clinical Case Generation ↗
  6. 2026Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?
  7. 2025A Specialized Large Language Model for Clinical Reasoning and Diagnosis in Rare Diseases
  8. 2025TriAgent: Automated Biomarker Discovery with Deep Research Grounding for Triage in Acute Care by LLM-Based Multi-Agent Collaboration