LearnActCoder introduces a role‑aware error memory system for clinical coding agents, converting labeled errors into a structured Mistake Knowledge Database (MistakeKDB). The framework routes false‑negative lessons to a recall‑oriented coder and false‑positive lessons to a precision‑oriented judge, forming a Coder‑Judge pipeline. On MIMIC‑III and MIMIC‑IV datasets, the MistakeKDB improves CPT F1 by 5.9 percentage points and shifts ICD‑10 coding toward higher precision, while maintaining stable performance on held‑out notes.
arXiv:2509. 08604v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated significant potential in medicine, with many studies adapting them through continued pre-training or fine-tuning on medical data to enhance domain-specific accuracy and safety.
arXiv:2608. 16831v1 Announce Type: new Abstract: Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a fixed model could adapt its behavior from instructions and demonstrations.
arXiv:2608.22899v1 Announce Type: new Abstract: Unlike static medical question answering, long-horizon diagnosis captures the sequential nature of clinical practice: evidence is progressively acquire...
GLoC-EHR is a multimodal language model that processes electronic health records by combining a fixed-size global memory of the entire patient trajectory with a local memory of selected events. It generates hospital-course summaries and masked concept descriptions, then is fine‑tuned to cite evidence before answering clinical questions, using group relative policy optimization to reward correct, evidence‑supported responses. On MIMIC‑IV outcome tasks, GLoC‑EHR achieves the highest macro AUROC among compared models when answering directly, and maintains strong performance with evidence‑cited reasoning while adding distinct supported findings from the local memory.
The Agent Error Dataset (AED) presents 50,228 error–diagnosis pairs collected from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text‑based agent systems. A five‑stage Agentic Error‑to‑Training (AET) pipeline generates diagnoses and proposed corrections, verifies them against recorded evidence, and creates separate training views for diagnosis and actor recovery. Experiments show that first‑proposal corrections improve verifier pass rates from 18.4% to 51.1%, and fine‑tuning with full‑diagnosis data raises Qwen3‑8B’s exact‑step agreement from 47.2% to 63.6% on a holdout set.
arXiv:2607. 19020v1 Announce Type: cross Abstract: Background: Clinical decision support systems degrade silently as treatment protocols evolve, yet standard adaptation methods treat models as monolithic blocks, unable to distinguish stable patient physiology from shifting institutional practice.
arXiv:2607. 28788v1 Announce Type: new Abstract: Clinical diagnosis at hospital admission must be made rapidly from limited, incomplete evidence.
The paper investigates how memory systems can answer a current query correctly yet fail to retain distinctions needed for later updates. Using a paired‑history audit, the authors evaluate 24 history pairs across six synthetic mechanisms and two model backends, achieving perfect reveal accuracy on DeepSeek and high accuracy on GLM. Record‑level audits reveal specific failures in structured reveal memories and frontier late‑reference adequacy, and the authors test a label‑equivariant repair that only partially restores correctness.
arXiv:2609.39371v1 Announce Type: new Abstract: In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements refe...
arXiv:2606. 09365v1 Announce Type: new Abstract: Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering.
CohortFlow is a steerable agent for clinical cohort curation that applies natural language corrections as localized updates to a structured specification, allowing selective invalidation of affected computations while keeping valid results. In experiments on 100 clinical‑trial eligibility scenarios, it achieved a micro‑F1 of 77.0% versus 76.4% for full regeneration, a non‑significant difference, but reduced correction latency by 64.8% after completion and 44.3% during execution, and cut model calls by 38.1%. A proof‑of‑concept run on MIMIC showed all 13 cohort states executed successfully, with corrections preserving unaffected computations and recomputing only changed or dependent nodes.
arXiv:2604. 26283v3 Announce Type: replace-cross Abstract: High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during image interpretation.