{"total":101,"rows":[{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2502.11211","title":"A Survey of LLM-based Agents in Medicine: How far are we from Baymax?","created":"2025-02-16","cited_by_count":85,"area":"agents"},{"id":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82,"area":"agents"},{"id":"2408.09955","title":"MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs","created":"2024-08-19","cited_by_count":47,"area":"agents"},{"id":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46,"area":"agents"},{"id":"2503.07459","title":"MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks","created":"2025-03-10","cited_by_count":40,"area":"lr"},{"id":"2503.22678","title":"Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions","created":"2025-03-28","cited_by_count":40,"area":"agents"},{"id":"2506.00555","title":"MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning","created":"2025-05-31","cited_by_count":40,"area":"lr"},{"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":"2505.19630","title":"Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning","created":"2025-05-26","cited_by_count":27,"area":"agents"},{"id":"2410.02551","title":"ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration","created":"2024-10-03","cited_by_count":23,"area":"agents"},{"id":"2505.03735","title":"Multi-Agent System for Comprehensive Soccer Understanding","created":"2025-05-06","cited_by_count":18,"area":"agents"},{"id":"2601.05111","title":"Agent-as-a-Judge","created":"2026-01-08","cited_by_count":17,"area":"agents"},{"id":"2410.12532","title":"MedAide: Information Fusion and Anatomy of Medical Intents via LLM-based Agent Collaboration","created":"2024-10-16","cited_by_count":16,"area":"agents"},{"id":"2504.13861","title":"3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark","created":"2025-03-26","cited_by_count":16,"area":"mllm"},{"id":"2510.04284","title":"Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning","created":"2025-10-05","cited_by_count":14,"area":"agents"},{"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":"2507.04037","title":"Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments","created":"2025-07-05","cited_by_count":13,"area":"agents"},{"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":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2509.24958","title":"The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry Capability","created":"2025-09-29","cited_by_count":10,"area":"agents"},{"id":"2503.20666","title":"TAMA: A Human-AI Collaborative Thematic Analysis Framework Using Multi-Agent LLMs for Clinical Interviews","created":"2025-03-26","cited_by_count":9,"area":"agents"},{"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":"2507.00814","title":"Many LLMs Are More Utilitarian Than One","created":"2025-07-01","cited_by_count":8,"area":"lr"},{"id":"2606.31179","title":"HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents","created":"2026-06-30","cited_by_count":8,"area":"agents"},{"id":"2412.09429","title":"From Intention To Implementation: Automating Biomedical Research via LLMs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2504.09421","title":"ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model","created":"2025-04-13","cited_by_count":7,"area":"lr"},{"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":"2503.16547","title":"Empowering Medical Multi-Agents with Clinical Consultation Flow for Dynamic Diagnosis","created":"2025-03-19","cited_by_count":5,"area":"agents"},{"id":"2507.10448","title":"FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios","created":"2025-07-05","cited_by_count":5,"area":"agents"},{"id":"2510.09275","title":"Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation","created":"2025-10-10","cited_by_count":5,"area":"lr"},{"id":"2603.02798","title":"Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification","created":"2026-03-03","cited_by_count":5,"area":"agents"},{"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":"2510.07309","title":"Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain","created":"2025-10-08","cited_by_count":4,"area":"agents"},{"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":"2604.16175","title":"MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation","created":"2026-04-17","cited_by_count":4,"area":"agents"},{"id":"2606.03416","title":"MeDxAgent: Multi-Agent Consultation for Interactive Medical Diagnosis","created":"2026-06-02","cited_by_count":4,"area":"agents"},{"id":"2410.07561","title":"AI-Press: A Multi-Agent News Generating and Feedback Simulation System Powered by Large Language Models","created":"2024-10-10","cited_by_count":3,"area":"agents"},{"id":"2503.09808","title":"Fine-tuning Vision Language Models with Graph-based Knowledge for Explainable Medical Image Analysis","created":"2025-03-12","cited_by_count":3,"area":"mllm"},{"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":"2606.01552","title":"RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2606.31966","title":"MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments","created":"2026-06-30","cited_by_count":3,"area":"mllm"},{"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":"2509.11078","title":"Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient Data","created":"2025-09-14","cited_by_count":2,"area":"agents"},{"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":"2604.08788","title":"MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2605.13542","title":"RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation","created":"2026-05-13","cited_by_count":2,"area":"agents"},{"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":"2507.22902","title":"Toward the Autonomous AI Doctor: Quantitative Benchmarking of an Autonomous Agentic AI Versus Board-Certified Clinicians in a Real World Setting","created":"2025-06-27","cited_by_count":1,"area":"agents"},{"id":"2508.07950","title":"FEAT: A Multi-Agent Forensic AI System with Domain-Adapted Large Language Model for Automated Cause-of-Death Analysis","created":"2025-08-11","cited_by_count":1,"area":"agents"},{"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":"2602.01297","title":"RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis","created":"2026-02-01","cited_by_count":1,"area":"lr"},{"id":"2602.04813","title":"Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"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":"2609.15161","title":"EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse","created":"2026-09-14","cited_by_count":1,"area":"agents"},{"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":"2507.03726","title":"Agent-Based Detection and Resolution of Incompleteness and Ambiguity in Interactions with Large Language Models","created":"2025-07-04","cited_by_count":0,"area":"agents"},{"id":"2507.10911","title":"Lessons Learned from Evaluation of LLM based Multi-agents in Safer Therapy Recommendation","created":"2025-07-15","cited_by_count":0,"area":"agents"},{"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":"2602.05407","title":"H-AdminSim: A Multi-Agent Simulator for Realistic Hospital Administrative Workflows with FHIR Integration","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2602.09159","title":"CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support","created":"2026-02-09","cited_by_count":0,"area":"agents"},{"id":"2602.14160","title":"Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2603.28393","title":"Within the MDT Room: Situated in Multidisciplinary Team-Grounded Agent Debate for Clinical Diagnosis","created":"2026-03-30","cited_by_count":0,"area":"agents"},{"id":"2604.24348","title":"OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents","created":"2026-04-27","cited_by_count":0,"area":"mllm"},{"id":"2605.09661","title":"MedMeta: A Benchmark for LLMs in Synthesizing Meta-Analysis Conclusion from Medical Studies","created":"2026-05-10","cited_by_count":0,"area":"rag"},{"id":"2606.01862","title":"RadioMaster: Multi-Agent System for Autonomous Radio Signal Generation","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"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":"2607.25489","title":"Agentic AI in medicine: architectures, applications, evaluation, and challenges for clinical translation","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.07627","title":"From Single Chatbots to Governed Agent Ecosystems: An Agentic AI Pattern Catalogue and Orchestration Framework for Mission-Critical Hospital Information Management Systems","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2608.22323","title":"MedReaMM: Evaluating Large Multimodal Models on Expert-Level Clinical Diagnostic Synthesis","created":"2026-08-23","cited_by_count":0,"area":"mllm"},{"id":"2608.26849","title":"LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"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":"2608.30188","title":"GPAgentBench-2K: Benchmarking Large Language Model Agents in Complex Clinical Action Space","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"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":"2609.13543","title":"Asclepius: An Adaptive Harness for Long-Horizon Clinical Agents","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"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":"2610.04672","title":"MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability","created":"2026-10-03","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}