{"total":97,"rows":[{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2502.02673","title":"MedRAX: Medical Reasoning Agent for Chest X-ray","created":"2025-02-04","cited_by_count":70,"area":null},{"id":"2407.03103","title":"Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory","created":"2024-07-03","cited_by_count":60,"area":null},{"id":"2506.22405","title":"Sequential Diagnosis with Language Models","created":"2025-06-27","cited_by_count":60,"area":null},{"id":"2409.15277","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","created":"2024-09-23","cited_by_count":33,"area":null},{"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":"2501.08579","title":"LLM-based Human Simulations Have Not Yet Been Reliable","created":"2025-01-15","cited_by_count":30,"area":null},{"id":"2505.20510","title":"CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic","created":"2025-05-26","cited_by_count":29,"area":null},{"id":"2507.23486","title":"A Novel Evaluation Benchmark for Medical LLMs: Illuminating Safety and Effectiveness in Clinical Domains","created":"2025-07-31","cited_by_count":28,"area":null},{"id":"2410.23426","title":"Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?","created":"2024-10-30","cited_by_count":26,"area":null},{"id":"2508.14880","title":"MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework","created":"2025-08-20","cited_by_count":22,"area":null},{"id":"2410.13191","title":"MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2411.04788","title":"Enhancing Investment Analysis: Optimizing AI-Agent Collaboration in Financial Research","created":"2024-11-07","cited_by_count":14,"area":null},{"id":"2504.09754","title":"Integrating Large Language Models for Automated Structural Analysis","created":"2025-04-13","cited_by_count":12,"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":"2605.23204","title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","created":"2026-05-22","cited_by_count":10,"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":"2410.01812","title":"From Text to Multimodality: Exploring the Evolution and Impact of Large Language Models in Medical Practice","created":"2024-09-14","cited_by_count":8,"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":"2501.09484","title":"Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators","created":"2025-01-16","cited_by_count":8,"area":null},{"id":"2510.12255","title":"Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs","created":"2025-10-14","cited_by_count":8,"area":null},{"id":"2601.18706","title":"Health-SCORE: Towards Scalable Rubrics for Improving Health-LLMs","created":"2026-01-26","cited_by_count":8,"area":null},{"id":"2601.22964","title":"EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2605.16679","title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2503.05768","title":"A Collection of Innovations in Medical AI for patient records in 2024","created":"2025-02-25","cited_by_count":7,"area":null},{"id":"2509.07188","title":"DischargeSim: A Simulation Benchmark for Educational Doctor-Patient Communication at Discharge","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2512.24181","title":"MedKGI: Iterative Differential Diagnosis with Medical Knowledge Graphs and Information-Guided Inquiring","created":"2025-12-30","cited_by_count":7,"area":null},{"id":"2605.23559","title":"PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA","created":"2026-05-22","cited_by_count":7,"area":null},{"id":"2502.17475","title":"ECG-Expert-QA: A Benchmark for Evaluating Medical Large Language Models in Heart Disease Diagnosis","created":"2025-02-16","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":"2510.18988","title":"Timely Clinical Diagnosis through Active Test Selection","created":"2025-10-21","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":"2601.06636","title":"MedEinst: Benchmarking the Einstellung Effect in Medical LLMs through Counterfactual Differential Diagnosis","created":"2026-01-10","cited_by_count":4,"area":null},{"id":"2601.12661","title":"MedConsultBench: A Full-Cycle, Fine-Grained, Process-Aware Benchmark for Medical Consultation Agents","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2602.16747","title":"LiveClin: A Live Clinical Benchmark without Leakage","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2604.06846","title":"MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2605.11224","title":"ABRA: Agent Benchmark for Radiology Applications","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2605.20506","title":"Reinforcing Human Behavior Simulation via Verbal Feedback","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2606.09365","title":"Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory","created":"2026-06-08","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":"2603.29373","title":"Beyond Idealized Patients: Evaluating LLMs under Challenging Patient Behaviors in Medical Consultations","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2605.07305","title":"MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2606.11702","title":"MedCTA: A Benchmark for Clinical Tool Agents","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2606.12291","title":"Measuring Epistemic Resilience of LLMs Under Misleading Medical Context","created":"2026-06-10","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":"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":"2601.04219","title":"AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","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":"2606.05112","title":"Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2506.23107","title":"Can Large Language Models Capture Human Risk Preferences? A Cross-Cultural Study","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2509.00891","title":"ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2509.12282","title":"AISSISTANT: Human-AI Collaborative Review and Perspective Research Workflows in Data Science","created":"2025-09-14","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":"2601.21551","title":"Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2607.08257","title":"MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2609.09678","title":"Safe to Stop? Risk-Constrained Stopping for Sequential Clinical Diagnosis Agents","created":"2026-09-09","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":"2502.17383","title":"Which Questions Improve Learning the Most? Utility Estimation of Questions with LM-based Simulations","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2507.18143","title":"HIVMedQA: Benchmarking large language models for HIV medical decision support","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2509.08087","title":"Performance Assessment Strategies for Language Model Applications in Healthcare","created":"2025-09-09","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":"2512.04107","title":"Rethinking AI Evaluation in Education: The TEACH-AI Framework and Benchmark for Generative AI Assistants","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2603.02097","title":"ClinConsensus: A Physician-Calibrated Benchmark for Evaluating Clinical Rubric Coverage in Chinese Medical LLMs","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.05129","title":"MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.25821","title":"Doctorina MedBench: A Dialogue-Based Benchmark and Evaluation Framework for Agent-Based Medical AI","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.10441","title":"VeriSim: A Configurable Framework for Stress-Testing Medical AI Under Patient Communication Noise","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.14656","title":"Rethinking Patient Education as Multi-turn Multi-modal Interaction","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.30529","title":"Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.01094","title":"CAREAgent: Clinical Agent with Structured Reasoning and Tool-Integrated for Order Generation","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.13931","title":"DLawBench: Evaluating LLMs Through Multi-Turn Legal Consultation","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.28715","title":"SEATauBench: Progressively Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.09142","title":"MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.17341","title":"Understanding From Human Perspective: A Multi-agent System for Interactive Egocentric Medical Image Segmentation","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2607.18999","title":"MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.28788","title":"EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.01012","title":"MedUPS: Towards Diagnostic Assistance in Uncommon Medical Cases with Large Language Models","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.04772","title":"Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05993","title":"Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.12745","title":"A Cloud-Edge System for Multimodal Clinical Screening in Resource-Constrained Rural Settings","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.28599","title":"CDPR: Counterfactual Advantage-based Credit Assignment for Cost-Aware Sequential Medical Diagnosis","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2609.02191","title":"Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.03221","title":"Instability Floors: Separating Bias from Noise in Fairness Audits of Clinical LLM Agents with FairMedAgent","created":"2026-09-02","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":"2609.16739","title":"Japanese Stroke LLM Evaluation: A Conversational Benchmark for Safe Stroke Care in Japanese Using Large Language Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.20827","title":"DischargeBench: Pre-Deployment Evaluation of LLM Discharge Educators through Persona-Grounded Patient Simulation","created":"2026-07-22","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":"2609.32740","title":"AnesTRACE: Benchmarking Intraoperative Anesthesia from Multimodal Perception to Multi-step Decision-Making","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32810","title":"OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34112","title":"Unknown is not normal: separating language-model extraction from rule-based decision logic for clinical risk scores","created":"2026-09-28","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":"2610.01278","title":"SCOPE-AD: Sequential cost-aware ordinal-belief planning with energy-based models for diagnostic agents","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01306","title":"DAYJOB: A Benchmark for Long-Horizon Professional Work","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.12023","title":"InterviewPlayground: A Validated Simulation Environment for Evaluating AI Interviewers","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15714","title":"MedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18813","title":"Self-Evolving Agent Harness","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}