RealICU is a new benchmark using physician hindsight labels on MIMIC-IV ICU data that exposes LLM failures in long-horizon clinical assessment, acute problem detection, action recommendation, and red-flag identification.
Ai hospital: Benchmarking large language models in a multi-agent medical interaction simulator
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
EHR-derived standardized patients and dual-track evaluation reveal LLMs trail clinicians by 37.28 points on full psychiatric encounters, with mental-status assessment the main bottleneck.
DDX-TRACE is a physician-adjudicated benchmark for evaluating VLMs on evidence-supported diagnostic trajectories rather than final answers alone in multimodal neuroradiology.
citing papers explorer
-
RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
RealICU is a new benchmark using physician hindsight labels on MIMIC-IV ICU data that exposes LLM failures in long-horizon clinical assessment, acute problem detection, action recommendation, and red-flag identification.
-
MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters
EHR-derived standardized patients and dual-track evaluation reveal LLMs trail clinicians by 37.28 points on full psychiatric encounters, with mental-status assessment the main bottleneck.
-
DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
DDX-TRACE is a physician-adjudicated benchmark for evaluating VLMs on evidence-supported diagnostic trajectories rather than final answers alone in multimodal neuroradiology.