arXiv AI
Jun 30
The Verbose Context Problem in Medical Records
arXiv:2606. 29503v1 Announce Type: cross Abstract: The verbose context problem occurs when structured concepts have token-inefficient textual representations.
The Verbose Context Problem in Medical Records
The verbose context problem occurs when structured concepts have token-inefficient textual representations. This bottleneck is acute in population health: cohort-level analysis of longitudinal patient records requires reasoning over thousands of medically-coded events, often exceeding 400K tokens in total.
Related stories
arXiv AI
Jun 26
Context Recycling for Long-Horizon LLM Inference
arXiv:2606. 26105v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong capabilities in short-context reasoning but degrade in performance over long conversational horizons due to context window limitations and inefficient token usage.
arXiv AI
Aug 7
DoctorAgents: an agentic framework to iteratively refine AutoML pipeline for small clinical temporal data
arXiv:2608. 05375v1 Announce Type: new Abstract: Clinical machine learning (ML) has the potential to support high-stakes medical decision-making, but reliable deployment is often constrained by scarce, heterogeneous, and temporal complexity.
arXiv AI
Aug 25
ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model
ClinicalGPT‑R1 is a reasoning‑enhanced generalist large language model designed for disease diagnosis. It was trained on 20,000 real‑world clinical records and uses diverse training strategies to improve diagnostic reasoning. In benchmarks, it outperforms GPT‑4o on Chinese diagnostic tasks and matches GPT‑4 performance in English, demonstrating superior disease‑diagnosis capabilities.
arXiv AI
Sep 23
Ascent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysis
arXiv:2609.24620v1 Announce Type: new Abstract: Answering epidemiological questions from real-world clinical data requires medical coding, schema-aware SQL, and validation of implicit choices about p...
arXiv AI
Jul 28
MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models
arXiv:2607. 22566v1 Announce Type: new Abstract: MedLoCoMo is a Medical Long-Context Memory benchmark for patient-specific clinical reasoning over multi-admission medical dialogue.
arXiv Machine Learning
Jun 8
GraphWalker: Patient Analogy Meets Information Gain for Clinical Reasoning with Large Language Models
arXiv:2604. 06684v2 Announce Type: replace Abstract: Clinical reasoning over electronic health records (EHRs) is a fundamental yet challenging task in modern healthcare.
arXiv AI
Jun 9
From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
arXiv:2603. 03292v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.
arXiv Machine Learning
Sep 21
HERMES: Contrast-Aware Knowledge Graph Reasoning from Clinical Notes for Patient Outcome Prediction
HERMES is a graph-based framework that uses only clinical text to predict patient outcomes. It builds personalized Knowledge Graphs from clinical notes via Large‑Language‑Model‑guided extraction and Contrastive Logic Modeling, capturing temporal dynamics and treatment changes. A Graph Attention Network then synthesizes patient representations, and experiments on MIMIC‑III and MIMIC‑IV show HERMES outperforms text‑only baselines for in‑hospital mortality and 30‑day readmission prediction.
arXiv Computer Vision
Aug 25
Sparse Multi-Stage Expert-Agent Routing for Complex Clinical Reasoning
arXiv:2608.21948v1 Announce Type: new Abstract: Complex clinical reasoning requires models to update diagnostic hypotheses as new evidence emerges and to coordinate different medical specialities und...
arXiv AI
Aug 24
KREL: Automatic Medical Coding via Knowledge-Guided Reasoning over Clinical Evidence with LLMs
arXiv:2608.20887v1 Announce Type: cross Abstract: Automatic Medical Coding (AMC), which assigns standardized International Classification of Diseases (ICD) codes to clinical notes, is essential for m...
arXiv AI
Sep 7
REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation
REFINE is a framework that refines medical concept representations by creating patient‑specific temporal graphs from a global text‑attributed knowledge graph. It uses a reinforcement learning policy to allocate a personalized graph expansion budget for each observed code, then processes the resulting graph with a heterogeneous GNN and a frozen LLM that refines representations via graph‑aware soft prompts. Experiments on MIMIC‑III and MIMIC‑IV demonstrate that REFINE consistently improves various EHR prediction backbones, surpasses strong baselines, and shows robust gains across ablation studies, KG selection, and data insufficiency scenarios.