{"total":30,"rows":[{"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":"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":"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":"2606.16723","title":"AgentFairBench: Do LLM Agents Discriminate When They Act?","created":"2026-06-15","cited_by_count":3,"area":"agents"},{"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":"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":"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":"2605.18768","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":"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":"2607.15314","title":"Cura 1T: Specialized Model for Agentic Healthcare","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"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":"2608.27219","title":"BALMS: Benchmarking Agentic LLMs for Longitudinal Mental Health Sensing","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"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"}],"next_cursor":null}