{"total":62,"rows":[{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2604.27470","title":"HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats","created":"2026-04-30","cited_by_count":26,"area":null},{"id":"2509.19319","title":"FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering","created":"2025-09-12","cited_by_count":22,"area":"agents"},{"id":"2512.04535","title":"GTM: Simulating the World of Tools for AI Agents","created":"2025-12-04","cited_by_count":14,"area":"agents"},{"id":"2604.09937","title":"HealthAdminBench: Evaluating Computer-Use Agents on Healthcare Administration Tasks","created":"2026-04-10","cited_by_count":13,"area":"agents"},{"id":"2606.12736","title":"Benchmarking AI Agents for Addressing Scientific Challenges Across Scales","created":"2026-06-10","cited_by_count":12,"area":null},{"id":"2607.04686","title":"ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents","created":"2026-07-06","cited_by_count":11,"area":"agents"},{"id":"2508.19504","title":"Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents","created":"2025-08-27","cited_by_count":10,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2511.20490","title":"MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology","created":"2025-11-25","cited_by_count":6,"area":"lr"},{"id":"2509.15957","title":"EHR-MCP: Real-world Evaluation of Clinical Information Retrieval by Large Language Models via Model Context Protocol","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2603.22767","title":"Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databases","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2604.24696","title":"NeuroClaw Technical Report","created":"2026-04-27","cited_by_count":4,"area":"agents"},{"id":"2606.01961","title":"AutoMedBench: Towards Medical AutoResearch with Agentic AI Models","created":"2026-06-01","cited_by_count":4,"area":"agents"},{"id":"2606.03203","title":"MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents","created":"2026-06-02","cited_by_count":4,"area":"agents"},{"id":"2606.24235","title":"SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2511.13703","title":"Generalist Foundation Models Are Not Clinical Enough for Hospital Operations","created":"2025-11-17","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":"2606.16723","title":"AgentFairBench: Do LLM Agents Discriminate When They Act?","created":"2026-06-15","cited_by_count":3,"area":"agents"},{"id":"2504.03699","title":"Enhancing Clinical Decision-Making: Integrating Multi-Agent Systems with Ethical AI Governance","created":"2025-03-25","cited_by_count":2,"area":null},{"id":"2506.10157","title":"One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligence","created":"2025-06-11","cited_by_count":2,"area":"mllm"},{"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":"2601.09749","title":"R-LAM: Reproducibility-Constrained Large Action Models for Scientific Workflow Automation","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2605.09675","title":"CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents","created":"2026-05-10","cited_by_count":2,"area":"lr"},{"id":"2606.13608","title":"AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2608.16211","title":"BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics","created":"2026-08-17","cited_by_count":2,"area":"agents"},{"id":"2608.24570","title":"EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2509.23415","title":"From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents","created":"2025-09-27","cited_by_count":1,"area":"agents"},{"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":"2605.07058","title":"MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2606.31036","title":"Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.29528","title":"MedCache: Efficient and Temporally Valid Memory for Longitudinal Clinical Agents","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2609.00296","title":"Toward Workflow-Aware Benchmarking for Healthcare NLP Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"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":"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":"2604.02834","title":"ESL-Bench: An Event-Driven Synthetic Longitudinal Benchmark for Health Agents","created":"2026-04-03","cited_by_count":0,"area":"agents"},{"id":"2605.06177","title":"BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"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":"2605.18768","title":"ClinQueryAgent: A Conversational Agent for Population Health Management","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.24699","title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"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":"2606.00189","title":"Learning to Construct Practical Agentic Systems","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.26346","title":"How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"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":"2606.29602","title":"An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios","created":"2026-06-28","cited_by_count":0,"area":"safety"},{"id":"2607.02983","title":"Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.15314","title":"Cura 1T: Specialized Model for Agentic Healthcare","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"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":"2607.25485","title":"PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.09024","title":"ELICITED: EHR-grounded Longitudinal Interactive Conversations for Information-seeking Triage Evaluation and Decision-making","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.22899","title":"CDEG: Learning Decision-Critical Evidence for Long-Horizon Diagnostic Agents","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.27219","title":"BALMS: Benchmarking Agentic LLMs for Longitudinal Mental Health Sensing","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"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":"2609.13582","title":"Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repeated Runs","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":"2609.32810","title":"OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.39566","title":"From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.15714","title":"MedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16175","title":"ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18529","title":"How Reliable Are System-One Decisions in Medicine? A Comparative Study of Jev, Jev-like Models, and LLMs","created":"2026-10-13","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}