{"total":43,"rows":[{"id":"2505.17818","title":"PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions","created":"2025-05-23","cited_by_count":32,"area":null},{"id":"2406.02394","title":"Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in Medicine","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2503.22353","title":"Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions","created":"2025-03-28","cited_by_count":13,"area":null},{"id":"2601.03023","title":"MedDialogRubrics: A Comprehensive Benchmark and Evaluation Framework for Multi-turn Medical Consultations in Large Language Models","created":"2026-01-06","cited_by_count":12,"area":null},{"id":"2603.12152","title":"LifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluation","created":"2026-03-12","cited_by_count":11,"area":null},{"id":"2506.00386","title":"Adaptive-VP: A Framework for LLM-Based Virtual Patients that Adapts to Trainees' Dialogue to Facilitate Nurse Communication Training","created":"2025-05-31","cited_by_count":9,"area":null},{"id":"2411.13902","title":"PIORS: Personalized Intelligent Outpatient Reception based on Large Language Model with Multi-Agents Medical Scenario Simulation","created":"2024-11-21","cited_by_count":8,"area":null},{"id":"2412.09429","title":"From Intention To Implementation: Automating Biomedical Research via LLMs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2512.05671","title":"ClinTutor-R1: Advancing Scalable and Robust One-to-Many Alignment in Clinical Socratic Education","created":"2025-12-05","cited_by_count":6,"area":null},{"id":"2508.20996","title":"ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recovery","created":"2025-08-28","cited_by_count":4,"area":null},{"id":"2512.10206","title":"CP-Env: Evaluating Large Language Models on Clinical Pathways in a Controllable Hospital Environment","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2604.04325","title":"Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2601.19773","title":"Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2608.23397","title":"MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2505.19667","title":"LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.14774","title":"MedSyn: Enhancing Diagnostics with Human-AI Collaboration","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2508.04915","title":"ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2512.13297","title":"MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2601.04195","title":"MedPI: Evaluating AI Systems in Medical Patient-facing Interactions","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2605.30637","title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2504.13969","title":"Tinker Tales: Interactive Storytelling Framework for Early Childhood Narrative Development and AI Literacy","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2510.20001","title":"Beyond MedQA: Towards Real-world Clinical Decision Making in the Era of LLMs","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2601.10951","title":"Multi-Stage Patient Role-Playing Framework for Realistic Clinical Interactions","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2601.21551","title":"Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.13291","title":"Agent Mars: Multi-Agent Simulation for Multi-Planetary Life Exploration and Settlement","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2604.05397","title":"Confidence Should Be Calibrated More Than One Turn Deep","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.23629","title":"DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2607.08257","title":"MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2608.25085","title":"MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2501.10642","title":"Iterative Tree Analysis for Medical Critics","created":"2025-01-18","cited_by_count":0,"area":null},{"id":"2503.16433","title":"The Application of MATEC (Multi-AI Agent Team Care) Framework in Sepsis Care","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2503.21138","title":"A Computational Theory for Efficient Mini Agent Evaluation with Causal Guarantees","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2510.17764","title":"Evaluating Medical LLMs by Levels of Autonomy: A Survey Moving from Benchmarks to Applications","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2511.00265","title":"AgentBnB: A Browser-Based Cybersecurity Tabletop Exercise with Large Language Model Support and Retrieval-Aligned Scaffolding","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2601.02123","title":"DeCode: Decoupling Content and Delivery for Medical QA","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2606.03157","title":"ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.28900","title":"MedEvoEval: Evaluating Continual Evolution of Doctor Agents through Simulated Clinical Episodes","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2608.27847","title":"From Uncertainty to Clinical Risk: Severity-Aware Conformal Planning for Interactive Medical Diagnosis","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.09887","title":"When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.12851","title":"MedRoundsQA: A Persona and Difficulty Aware Evaluation for Multi-Turn Medical Consultations","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.30027","title":"Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.35627","title":"Can LLMs Value the Right Evidence? Evidence-Value Misalignment in Dynamic Medical Diagnosis","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.18605","title":"From Hindsight to Foresight: Dissecting Clinical Evidence Acquisition in Large Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}