The study introduces a scaffolding-oriented multi-agent Large Language Model (LLM) AI Standardized Patient (AI-SP) platform designed to train medical students in patient interviews. In a randomized controlled trial with 100 students, the multi-agent system—comprising a patient agent, a Socratic tutor agent, and a turn-level evaluator—did not improve diagnostic accuracy but significantly enhanced overall OSCE scores, especially in communication, empathy, and history-taking. The authors also release a richly annotated dataset to support further research in AI-supported clinical reasoning training.
arXiv:2608. 07418v1 Announce Type: new Abstract: In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy.
arXiv:2606. 17474v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly considered for use in clinical consultation tasks, yet most medical evaluations remain static, single-turn, or narrowly outcome-based, limiting their ability to reflect the sequential, uncertain, and interactive nature of real-world care.
arXiv:2603. 25821v3 Announce Type: replace-cross Abstract: We present Doctorina MedBench, an evaluation framework for agent-based medical AI based on the simulation of physician-patient interactions.
arXiv:2603. 25821v2 Announce Type: replace-cross Abstract: We present Doctorina MedBench, a comprehensive evaluation framework for agent-based medical AI based on the simulation of realistic physician-patient interactions.
The study investigates whether coded dialogue logs from generative AI-powered virtual patients can provide teacher-interpretable evidence of clinical reasoning. Analyzing 1,030 dialogues from 210 second-year medical learners, the researchers applied behavioural prevalence, Epistemic Network Analysis, and Transition Network Analysis to identify process patterns linked to high-rated history-taking performance. Findings show that high-rated consultations involve more integrated information gathering, communication, and synthesis, rather than merely increased volume of activity.
The paper introduces MACD, a Multi-Agent Clinical Diagnosis framework that enables large language models to self‑learn clinical knowledge through a multi‑agent pipeline of summarization, refinement, and application. MACD is extended into a human‑AI collaborative workflow where multiple diagnostician agents consult iteratively, guided by a judge agent and human oversight. Evaluation on the MIMIC‑MACD cohort shows significant gains in diagnostic accuracy—an average 11.6 percentage‑point improvement over authoritative knowledge for open‑weight LLMs and an 18.3‑percentage‑point boost over physician‑only diagnosis in text‑only vignettes.
arXiv:2509. 02594v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions requires going beyond conventional benchmarks to assess how these systems behave in complex, high-stakes clinical scenarios.
arXiv:2606. 28900v1 Announce Type: new Abstract: Doctor agents are moving beyond single-turn answer generation toward evolving clinical decision systems.
arXiv:2601. 16529v4 Announce Type: replace Abstract: Large language models (LLMs) deployed in clinical decision support may acquiesce to patient requests for care that conflicts with evidence-based guidelines.
The paper introduces Debate-Mixture-of-Agents (DMoA), a multi‑agent framework that structures role‑based interactions to mimic iterative diagnostic reasoning in clinical settings. Evaluated on 297 rare disease cases and 1,719 challenging cases, DMoA outperformed a GPT‑4o baseline, improving most likely diagnosis accuracy by 10.21 percentage points and safety rate by 11.36 percentage points. Ablation studies and further analyses revealed that these gains stem from the structured workflow rather than merely adding more models or longer outputs, and that performance benefits are influenced by the chosen structure, base model strength, and token budget.
arXiv:2512. 01241v4 Announce Type: replace-cross Abstract: Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized.
The paper introduces a retrieval‑augmented multi‑agent framework that automatically generates instance‑specific evaluation rubrics for medical language models. By retrieving authoritative medical evidence, decomposing it into atomic facts, and combining these with user interaction constraints, the system produces fine‑grained criteria that outperform GPT‑4o on HealthBench and LLMEval‑Med. The generated rubrics also guide response refinement, improving medical LLM output quality by 9.2%.