{"total":24,"rows":[{"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":"2606.12736","title":"Benchmarking AI Agents for Addressing Scientific Challenges Across Scales","created":"2026-06-10","cited_by_count":12,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2606.28900","title":"MedEvoEval: Evaluating Continual Evolution of Doctor Agents through Simulated Clinical Episodes","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.18999","title":"MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents","created":"2026-07-21","cited_by_count":0,"area":null},{"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":"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":"2609.30027","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":"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}